CN117094468A - Building energy efficiency management system and method - Google Patents
Building energy efficiency management system and method Download PDFInfo
- Publication number
- CN117094468A CN117094468A CN202311081785.5A CN202311081785A CN117094468A CN 117094468 A CN117094468 A CN 117094468A CN 202311081785 A CN202311081785 A CN 202311081785A CN 117094468 A CN117094468 A CN 117094468A
- Authority
- CN
- China
- Prior art keywords
- data
- energy efficiency
- efficiency management
- building energy
- management platform
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims abstract description 16
- 238000013135 deep learning Methods 0.000 claims abstract description 15
- 238000007726 management method Methods 0.000 claims description 186
- 238000005265 energy consumption Methods 0.000 claims description 108
- 238000005070 sampling Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 239000012634 fragment Substances 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 238000011176 pooling Methods 0.000 claims description 10
- 238000005520 cutting process Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000005406 washing Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 19
- 238000005457 optimization Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 9
- 239000002699 waste material Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000004378 air conditioning Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002737 fuel gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- -1 heating Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a building energy efficiency management system and a method. The method comprises the following steps: the sensor collects environmental data, each electric energy collection node collects electric energy consumed by each electric appliance, and the collected electric energy data is sent to the indoor secondary building energy efficiency management platform through ZigBee; the secondary building energy efficiency management platform analyzes indoor and outdoor environment data and the electric energy data and sends the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network; the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives out suggestions according to the trained model, and adjusts all the equipment according to the suggestions; the corresponding system of the method comprises the following steps: the system comprises a data acquisition module, an analysis data module and a model training module; by the method and the system, an automatic and intelligent solution can be provided for energy efficiency management of the building, the energy utilization efficiency of the building is effectively improved, and the aim of sustainable development is achieved.
Description
Technical Field
The invention provides a building energy efficiency management system and method, and belongs to the technical field of building energy efficiency management.
Background
The ratio of the energy consumption of each industry in China in total energy consumption is greatly changed from the ratio of the energy consumption of the current building in the total energy consumption, which is just as great as the ratio of the energy consumption of the current building in the country. According to the total of living building parts, the proportion of building energy consumption in the total consumption of resources has been increased from 10% at the end of the 70 th century to 27.45% in recent years, and the building energy growth trend has been very remarkable in a gradual trend. The total number of buildings just built in China exceeds 20 hundred million square meters and can continue for a very long time. Meaning that building energy consumption will also increase gradually as the building grows. The energy consumption of the built building covers air conditioning, fuel gas, heating, water supply, illumination and the like.
Urban building energy consumption is always an important point of urban energy consumption, and the following problems exist at present: the intelligent scale is low, part of existing buildings still adopt a manual meter reading mode to collect energy efficiency data due to long building annual limit, and part of building energy efficiency management platforms are relatively independent, but only simple recording and statistical management are carried out on the data, and detailed data analysis and instruction are not carried out on the energy consumption condition of the building; the waste of ineffective energy consumption is serious, a large number of ineffective application scenes in public buildings are frequent, for example, a large number of lamps in the day are still on in the building, people leave a room at night but various electric appliances are still running, for example, the power of lamps in certain areas is too bright or dark, the temperature of an air conditioner is very low in summer, the temperature of the air conditioner is very high in winter, and even windows are opened to adjust the temperature, so that the scenes exceeding the actual requirements are very common in actual life. These conditions not only result in waste of energy consumption, but also result in accelerated consumption of equipment and systems, rapid aging of systems, and degradation of equipment performance, which in turn results in further energy consumption.
Disclosure of Invention
The present invention provides a building energy efficiency management system and method for solving the above-mentioned problems:
the invention provides a building energy efficiency management method, which comprises the following steps:
indoor and outdoor environment data are collected by sensors arranged indoors and outdoors, electric energy consumed by each electric appliance is collected by each electric energy collection node, and the collected electric energy data are sent to an indoor secondary building energy efficiency management platform through ZigBee;
the indoor secondary building energy efficiency management platform analyzes the indoor and outdoor environment data and the electric energy data, and sends the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives out suggestions according to the trained model, and adjusts all the devices according to the suggestions.
Further, a building energy efficiency management method, the indoor and outdoor environment data are collected by the indoor and outdoor sensors, the electric energy consumed by each electric appliance is collected by each electric energy collection node, the collected electric energy data are sent to the indoor two-stage building energy efficiency management platform through ZigBee, the method comprises the following steps:
The temperature, humidity and rainfall sensors arranged on the windows detect the temperature, humidity and rainfall of the external environment, the indoor brightness sensor, the infrared sensor, the temperature sensor and the humidity sensor are respectively arranged in the room to detect whether the indoor brightness, the person, the temperature and the humidity exist or not, and the electric energy collection nodes arranged on the air conditioner, the lighting equipment and the elevator collect the electric energy consumption of each electric appliance;
all sensors collect data according to a sampling period standard, wherein the sampling period standard is as follows:
wherein count represents the total number of times the infrared sensor has detected a person in the last N detections, N i Indicating the number of times the infrared sensor detects the i-th person.
β＝2*α/(C*γ)
Wherein, beta represents the proportionality coefficient of the sampling period, alpha represents the standard deviation of temperature data, gamma represents the average value of all data, C is a constant for adjusting the relation between the sampling period and the fluctuation degree of environmental data, and the value range is between 0.5 and 2.
T＝max(k'*β*α，T0)
Wherein T0 represents a default sampling period, namely, a sampling period used when fluctuation of the environmental data is small, the value range is between [1,10] seconds, max represents the maximum value of the two, k' represents a proportionality coefficient calculated according to count,
k'＝(count/N)^e
Wherein e is an index for controlling the relation between the proportional coefficient and the number of people, and the value range is between [1,3 ].
The data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are sent to an indoor secondary building energy efficiency management platform through ZigBee.
Further, the building energy efficiency management method, the indoor two-stage building energy efficiency management platform analyzes the indoor and outdoor environment data and the electric energy data, and sends the indoor and outdoor environment data and the electric energy data to the one-stage building energy efficiency management platform through a network, includes:
the indoor two-level building energy efficiency management platform receives the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node through ZigBee and stores the data in a database of the platform;
after the secondary building energy efficiency management platform analyzes the data, the received data is compared with first preset data in the platform, and when the data difference exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to user equipment;
and the secondary building energy efficiency management platform sends the data stored in the database to the primary building energy efficiency management platform through a network.
Further, the method for managing building energy efficiency, after analyzing data, compares the received data with preset data in the platform, and when the data differ by more than 5 units, the second-level building energy efficiency management platform sends alarm information to the user equipment, comprising:
the second-level building energy efficiency management platform compares the received data detected by the temperature, humidity and rainfall sensors deployed on the window with first preset data in the platform, if the detected data of the external environment is not different from the first preset data in the platform by more than three units, the data of the electric energy consumption of the air conditioner is checked, and if the air conditioner is in an open state at the moment, the door and window are controlled to be opened, and the air conditioner is closed;
the secondary building energy efficiency management platform receives data sent by an indoor brightness sensor, and if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in a 1/3 scene mode, the lamp is adjusted to be in the 1/3 scene mode;
the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
And the secondary building energy efficiency management platform compares the energy consumption data of each electric appliance with second preset data in the platform, and if the difference between the energy consumption data and the second preset data exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to the user equipment.
Further, the building energy efficiency management method, the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives suggestions according to the trained model, and adjusts each device according to the suggestions, wherein the method comprises the following steps:
after washing, missing value filling and normalization processing are carried out on the received electric energy data, time sequence cutting is carried out on the data to obtain a plurality of time sequence fragments, and each fragment comprises data of a plurality of time steps;
adopting a network structure based on alternating stacking of convolution layers and pooling layers, and carrying out feature extraction on each time sequence segment by using a convolution neural network, wherein the convolution neural network learns the fluctuation and trend in the time sequence segments;
model training is carried out on the extracted features by using a support vector regression algorithm, and the energy consumption of each electric appliance is predicted;
according to the trained model, corresponding advice and second preset data in the platform are given by combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice given by the model.
The invention provides a building energy efficiency management system, which is characterized by comprising:
the system comprises a data acquisition module, an indoor and outdoor environment data acquisition module and an indoor and outdoor environment data acquisition module, wherein each electric energy acquisition node acquires electric energy consumed by each electric appliance, and the acquired electric energy data is sent to an indoor secondary building energy efficiency management platform through ZigBee;
the analysis data module is used for enabling the indoor secondary building energy efficiency management platform to analyze the indoor and outdoor environment data and the electric energy data and sending the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the model training module is used for receiving the electric energy data by the first-level building energy efficiency management platform, training the model by a deep learning algorithm, giving suggestions according to the trained model, and adjusting all the devices according to the suggestions.
Further, a building energy efficiency management system, the data collection module includes:
the detection module is used for detecting the temperature, the humidity and the rainfall of the external environment by using temperature, humidity and rainfall sensors arranged on windows, detecting indoor brightness, people, temperature and humidity by using indoor brightness sensors, infrared sensors, temperature sensors and humidity sensors respectively, and acquiring electric energy consumption of each electric appliance by using electric energy acquisition nodes arranged on air conditioners, lighting equipment and elevators;
All sensors collect data according to a sampling period standard, wherein the sampling period standard is as follows:
wherein count represents the total number of times the infrared sensor has detected a person in the last N detections, N i Indicating the number of times the infrared sensor detects the i-th person.
β＝2*α/(C*γ)
Wherein, beta represents the proportionality coefficient of the sampling period, alpha represents the standard deviation of temperature data, gamma represents the average value of all data, C is a constant for adjusting the relation between the sampling period and the fluctuation degree of environmental data, and the value range is between 0.5 and 2.
T＝max(k'*β*α，T0)
Wherein T0 represents a default sampling period, namely, a sampling period used when fluctuation of the environmental data is small, the value range is between [1,10] seconds, max represents the maximum value of the two, k' represents a proportionality coefficient calculated according to count,
k'＝(count/N)^e
wherein e is an index for controlling the relation between the proportional coefficient and the number of people, and the value range is between [1,3 ].
And the communication module is used for transmitting the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node to the indoor secondary building energy efficiency management platform through ZigBee.
Further, a building energy efficiency management system, the analysis data module includes:
The indoor secondary building energy efficiency management platform receives the data acquired by the sensors and the electric energy data consumed by the electric appliances acquired by the electric energy acquisition nodes through ZigBee and stores the data in a database of the platform;
the comparison module is used for comparing the received data with first preset data in the platform after the data are analyzed by the secondary building energy efficiency management platform, and sending alarm information to the user equipment by the secondary building energy efficiency management platform when the data differ by more than 5 units;
the primary platform and secondary platform communication module is used for the secondary building energy efficiency management platform to send the data stored in the database to the primary building energy efficiency management platform through a network.
Further, a building energy efficiency management system, the comparison module includes:
the air conditioner door and window linkage module is used for comparing the received data detected by the temperature, humidity and rainfall sensors deployed on the windows with first preset data in the platform by the two-stage building energy efficiency management platform, checking the air conditioner electric energy consumption data if the detected data of the external environment is not different from the first preset data in the platform by more than three units, and controlling to open the door and window and close the air conditioner if the air conditioner is in an open state at the moment;
The lighting system adjusting module is used for receiving data sent by the indoor brightness sensor by the secondary building energy efficiency management platform, and adjusting the lamp to be in a 1/3 scene mode if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in the 1/3 scene mode; the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
and the alarm module is used for comparing the energy consumption data of each electric appliance with second preset data in the platform by the two-stage building energy efficiency management platform, and sending alarm information to the user equipment if the difference of the data is found to be more than 5 units.
Further, a building energy efficiency management system, the model training module comprises:
the data preprocessing module is used for carrying out time sequence cutting on the received electric energy data after washing, missing value filling and normalization processing to obtain a plurality of time sequence fragments, wherein each fragment comprises data of a plurality of time steps;
the feature extraction module adopts a network structure based on alternating stacking of a convolution layer and a pooling layer, and uses a convolution neural network to extract features of each time sequence segment, and the convolution neural network learns fluctuation and trend in the time sequence segments;
the prediction module is used for carrying out model training on the extracted characteristics and predicting the energy consumption of each electric appliance by using a support vector regression algorithm;
and the generation advice and second preset data module is used for providing corresponding advice and second preset data in the platform according to the trained model and combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice provided by the model.
The invention has the beneficial effects that: the energy consumption condition of the building can be mastered more accurately by collecting the indoor and outdoor environment data and the electric energy data in real time and analyzing and modeling the indoor and outdoor environment data and the electric energy data, so that the energy utilization efficiency is improved, and the energy consumption and the cost are reduced; through analysis and modeling of the electric energy data, the problems of unnecessary energy consumption behavior, equipment loss and the like can be found, and the use and maintenance modes of the equipment can be timely adjusted, so that energy conservation and emission reduction are effectively promoted; by adopting the scheme, the automatic monitoring and management of the building can be realized, the burden of manual monitoring and management is reduced, and the labor cost is reduced; by adopting the scheme, the automatic monitoring and management of the building can be realized, the time and error of manual operation are reduced, and the working efficiency is improved; according to the scheme, the energy consumption and the most comfortable electric appliance use state in the future are predicted through the deep learning model, the electric appliance use suggestion is given, a user adjusts the electric appliance state according to the electric appliance use suggestion, and when the energy consumption of the electric appliance exceeds the deep learning prediction range, alarm information is sent, so that the intellectualization of building energy consumption management is greatly improved. The invention can provide an automatic and intelligent solution for energy efficiency management of the building, effectively improve the energy utilization efficiency of the building and achieve the aim of sustainable development.
Drawings
FIG. 1 is a schematic diagram of a building energy efficiency management method according to the present invention;
fig. 2 is a schematic diagram of connection relationships between nodes in the system according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The method for managing building energy efficiency according to this embodiment, as shown in fig. 1, includes:
indoor and outdoor environment data are collected by sensors arranged indoors and outdoors, electric energy consumed by each electric appliance is collected by each electric energy collection node, and the collected electric energy data are sent to an indoor secondary building energy efficiency management platform through ZigBee;
the indoor secondary building energy efficiency management platform analyzes the indoor and outdoor environment data and the electric energy data, and sends the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives out suggestions according to the trained model, and adjusts all the devices according to the suggestions.
The working principle and the effect of the technical scheme are as follows: the indoor and outdoor environment data and the electric energy data consumed by each electric appliance are collected through the sensors arranged indoors and outdoors, and the data are sent to an indoor secondary building energy efficiency management platform through ZigBee, so that the real-time monitoring and collection of the data are realized; in the second-level building energy efficiency management platform, the indoor and outdoor environment data and the electric energy data are analyzed, the indoor and outdoor environment data and the electric energy data are sent to the first-level building energy efficiency management platform through a network, so that the energy consumption condition of a building can be comprehensively monitored and analyzed, powerful data support is provided for subsequent optimization, in the first-level building energy efficiency management platform, the electric energy data are received, model training is conducted on the electric energy data through a deep learning algorithm, suggestions are given according to the trained models, and each device is adjusted according to the suggestions. The method can predict and optimize the energy consumption condition of the building, thereby achieving the purposes of reducing the energy consumption and improving the energy efficiency; according to the technical scheme, the energy consumption condition of the building is monitored in real time, rules and problems in the energy consumption condition are analyzed, and optimization suggestions are given out through a deep learning algorithm, so that the energy consumption of the building is effectively managed and optimized, and the purposes of saving energy and reducing carbon emission are achieved.
In this embodiment, a building energy efficiency management method is provided, where indoor and outdoor sensors are deployed to collect indoor and outdoor environmental data, each electric energy collection node collects electric energy consumed by each electric appliance, and sends the collected electric energy data to an indoor secondary building energy efficiency management platform through ZigBee, as shown in fig. 2, including:
the temperature, humidity and rainfall sensors arranged on the windows detect the temperature, humidity and rainfall of the external environment, the indoor brightness sensor, the infrared sensor, the temperature sensor and the humidity sensor are respectively arranged in the room to detect whether the indoor brightness, the person, the temperature and the humidity exist or not, and the electric energy collection nodes arranged on the air conditioner, the lighting equipment and the elevator collect the electric energy consumption of each electric appliance;
all sensors collect data according to a sampling period standard, wherein the sampling period standard is as follows:
wherein count represents the total number of times the infrared sensor has detected a person in the last N detections, N i Indicating the number of times the infrared sensor detects the i-th person.
β＝2*α/(C*γ)
Wherein, beta represents the proportionality coefficient of the sampling period, alpha represents the standard deviation of temperature data, gamma represents the average value of all data, C is a constant for adjusting the relation between the sampling period and the fluctuation degree of environmental data, and the value range is between 0.5 and 2.
T＝max(k'*β*α，T0)
Wherein T0 represents a default sampling period, namely, a sampling period used when fluctuation of the environmental data is small, the value range is between [1,10] seconds, max represents the maximum value of the two, k' represents a proportionality coefficient calculated according to count,
k'＝(count/N)^e
wherein e is an index for controlling the relation between the proportional coefficient and the number of people, and the value range is between [1,3 ].
The data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are sent to an indoor secondary building energy efficiency management platform through ZigBee.
The working principle and the effect of the technical scheme are as follows: according to the technical scheme, through the sensors and the electric energy collection nodes which are arranged on windows, indoor and air-conditioning, lighting equipment and elevators, the real-time monitoring and collection of the building environment and equipment energy consumption are realized, and specifically, the temperature, humidity and rainfall sensors which are arranged on the windows are used for detecting the temperature, humidity and rainfall of the external environment; and the indoor brightness sensor, the infrared sensor, the temperature sensor and the humidity sensor are respectively used for detecting the indoor brightness, the existence of people, the temperature and the humidity. Meanwhile, the electric energy collection nodes deployed on the air conditioner, the lighting equipment and the elevator collect the electric energy consumption condition of each electric appliance. The data are transmitted to an indoor secondary building energy efficiency management platform for analysis and processing through ZigBee, and in the secondary building energy efficiency management platform, the data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are integrated and analyzed, so that comprehensive monitoring and analysis of building energy consumption conditions are realized, and data support is provided for subsequent optimization. According to the technical scheme, through the deployment of the plurality of sensors and the electric energy collection nodes, the real-time monitoring and collection of the building environment and the equipment energy consumption condition are realized, the data analysis and processing are carried out through the two-stage building energy efficiency management platform, and the comprehensive monitoring and optimization of the building energy consumption condition are realized. Finally, the purposes of saving energy and improving energy efficiency are achieved. The formula is used for adaptively adjusting the sampling period according to the number of human bodies detected by the infrared sensor, so that the purposes of increasing the sampling frequency to detect the existence of a human body more quickly when the fluctuation of the environmental data is large and reducing the sampling frequency to save resources and prolong the service life of equipment when the fluctuation of the environmental data is small are achieved. The model can adaptively adjust the sampling period according to actual conditions, so that the existence of people can be timely detected, and resource waste and equipment life shortening caused by over-sampling can be avoided. Meanwhile, the latest N detection results are used as calculation basis, so that the influence of single detection errors on the sampling period can be reduced. The parameters are selected and adjusted according to actual conditions. For example, the value of β is inversely related to the fluctuation degree of the current environmental data, and when the environmental data changes drastically, the value of β increases, thereby increasing the sampling frequency; and when the data fluctuation is small, the value of beta is reduced, so that the sampling frequency is reduced. The value of C also needs to be determined according to specific conditions, and the calculation complexity is reduced as much as possible under the condition that the sampling period is reasonably adjusted. The value of e can be adjusted according to experiments or experience, and generally, the value of e can be set to be an integer greater than 1 so as to reflect the influence degree of the number of people on the sampling period. The C value is typically used to adjust the difference between the predicted and actual values of the algorithm while avoiding over-fitting or under-fitting. When the C value is too small, the classifier is more prone to select a simple model, possibly resulting in a under-fit; when the C value is too large, the classifier is more prone to select complex models, possibly resulting in an overfitting. Thus, setting the C value between 0.5 and 2 balances the generalization ability and accuracy of the model. The T0 value is typically used to control the initial temperature value of the simulated annealing algorithm, i.e., the probability of initially accepting a poor solution. When the value of T0 is larger, the probability of accepting a worse solution is larger, the search space is wider, but the run time is also increased. Conversely, when the value of T0 is smaller, the probability of accepting a worse solution is lower, the search space is narrower, but the run time is also reduced. Thus, setting the T0 value between 1 and 10 seconds may balance search efficiency and accuracy. The e value is typically used to control the sensitivity of the scaling factor. When the value of e is larger, the smaller the number of people changes, the larger the algorithm output result, and vice versa. Thus, setting the e value between 1 and 3 balances the relationship between the output of the algorithm and the change in the number of people according to actual demand.
The building energy efficiency management method of the embodiment includes that an indoor secondary building energy efficiency management platform analyzes indoor and outdoor environment data and electric energy data, and sends the indoor and outdoor environment data and the electric energy data to a primary building energy efficiency management platform through a network, wherein the method comprises the following steps:
the indoor two-level building energy efficiency management platform receives the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node through ZigBee and stores the data in a database of the platform;
after the secondary building energy efficiency management platform analyzes the data, the received data is compared with first preset data in the platform, and when the data difference exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to user equipment;
and the secondary building energy efficiency management platform sends the data stored in the database to the primary building energy efficiency management platform through a network.
The technical scheme has the working principle and the effect that the indoor two-stage building energy efficiency management platform is utilized to receive, store and analyze the data collected by each sensor and the electric energy data consumed by each electric appliance and collected by each electric energy collection node, and particularly, the indoor two-stage building energy efficiency management platform receives the data collected by each sensor and the electric energy data consumed by each electric appliance and collected by each electric energy collection node through a ZigBee protocol and stores the data in a database of the platform. Then, the platform compares the received data with first preset data in the platform by analyzing the data, and when the data differ by more than 5 units, the secondary building energy efficiency management platform can send alarm information to the user equipment to remind the user of paying attention to the running condition of the equipment and timely maintain or repair the equipment. After the data processing and analysis are completed, the secondary building energy efficiency management platform sends the data stored in the database to the primary building energy efficiency management platform through a network, so that the real-time monitoring and analysis of the building energy consumption condition are realized. According to the technical scheme, through the indoor two-level building energy efficiency management platform, the data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are received, stored and analyzed, and a user is prompted to pay attention to the running condition of the equipment through a comparison and alarm mechanism. Meanwhile, the data is sent to the first-level building energy efficiency management platform, so that comprehensive monitoring and grasping of the energy consumption condition of the building are realized. Finally, the purposes of saving energy and improving energy efficiency are achieved.
In this embodiment, after analyzing data, the second-stage building energy efficiency management platform compares the received data with preset data in the platform, and when the data differ by more than 5 units, the second-stage building energy efficiency management platform sends alarm information to the user equipment, including:
the second-level building energy efficiency management platform compares the received data detected by the temperature, humidity and rainfall sensors deployed on the window with first preset data in the platform, if the detected data of the external environment is not different from the first preset data in the platform by more than three units, the data of the electric energy consumption of the air conditioner is checked, and if the air conditioner is in an open state at the moment, the door and window are controlled to be opened, and the air conditioner is closed;
the secondary building energy efficiency management platform receives data sent by an indoor brightness sensor, and if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in a 1/3 scene mode, the lamp is adjusted to be in the 1/3 scene mode;
the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
And the secondary building energy efficiency management platform compares the energy consumption data of each electric appliance with second preset data in the platform, and if the difference between the energy consumption data and the second preset data exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to the user equipment.
The first preset data in the platform is the optimal temperature and humidity of the user in each time period of the first energy efficiency management platform in advance.
The second preset data in the platform is the predicted energy consumption use condition of the electrical appliance, which is given by the second energy efficiency management platform through the training model, and the second energy efficiency management platform can send the second preset data to the first energy efficiency management platform through a network after generating the second preset data of the platform.
Specifically, three levels of brightness, traffic, and lamp brightness may be set with reference to the following examples, indoor brightness: "bright" mode: indoor brightness is between 1000-2000 lumens, "brighter" mode: indoor brightness is between 500-1000 lumens, "dark" mode: indoor brightness is between 0-500 lumen; flow of people: "multiple" mode: the flow of people detected by the infrared sensor is more than 10 people/min, and the mode of 'less': the flow of people detected by the infrared sensor is between 5 and 10 people/min, "less" mode: the flow of people detected by the infrared sensor is below 5 people/min, and the brightness of the lamp is as follows: scene mode 1: the brightness of the lamp is between 70% -100%, 1/2 scene mode: the brightness of the lamp is between 40% -70%, 1/3 scene mode: the brightness of the lamp is between 10% and 40%.
The working principle and the effect of the technical scheme are as follows: and the automatic control and adjustment of the building environment and equipment energy consumption are realized through an indoor two-stage building energy efficiency management platform. Specifically, the secondary building energy efficiency management platform receives data detected by temperature, humidity and rain sensors deployed on windows and compares the data with first preset data in the platform. If the data of the external environment is found to be different from the first preset data in the platform by no more than three units, and the air conditioner is in an open state at the moment, controlling to open doors and windows and closing the air conditioner. Therefore, not only can energy be saved and the energy efficiency be improved, but also air conditioner diseases are avoided, and the secondary building energy efficiency management platform also receives data sent by indoor brightness sensors. If the display room brightness of the brightness sensor is found to be in the "bright" mode and the lamp is not in the 1/3 scene mode, the lamp is adjusted to the 1/3 scene mode. For the corridor situation, if the corridor brightness is found to be in a 'dark' mode, and the data detected by the infrared sensor show that the traffic is in a 'multiple' state, the lamp is adjusted to be in a 1 scene mode; if the corridor brightness is found to be in a 'dark' mode and the data detected by the infrared sensor show that the traffic is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode; if the corridor brightness is found to be in the "dark" mode and the data detected by the infrared sensor indicates that the traffic is in the "less" mode, the light is adjusted to the 1/3 scene mode. Therefore, the brightness and the state of the lighting equipment can be automatically controlled according to the actual situation, and the aim of saving energy is achieved. In addition, the secondary building energy efficiency management platform also compares the energy consumption data of each electric appliance with second preset data in the platform. If the data difference is found to be more than 5 units, alarm information is sent to the user equipment to prompt the user to pay attention to the running condition of the equipment, and maintenance or repair is timely carried out. According to the technical scheme, through automatic control and adjustment of the two-stage building energy efficiency management platform, intelligent monitoring and optimization of building environment and equipment energy consumption conditions are realized, and therefore the purposes of saving energy and improving energy efficiency are achieved.
According to the building energy efficiency management method, the first-level building energy efficiency management platform receives electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives suggestions according to a trained model, adjusts each device according to the suggestions, and comprises the following steps:
after washing, missing value filling and normalization processing are carried out on the received electric energy data, time sequence cutting is carried out on the data to obtain a plurality of time sequence fragments, and each fragment comprises data of a plurality of time steps;
adopting a network structure based on alternating stacking of convolution layers and pooling layers, and carrying out feature extraction on each time sequence segment by using a convolution neural network, wherein the convolution neural network learns the fluctuation and trend in the time sequence segments;
model training is carried out on the extracted features by using a support vector regression algorithm, and the energy consumption of each electric appliance is predicted;
according to the trained model, corresponding advice and second preset data in the platform are given by combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice given by the model.
By taking air conditioner energy consumption prediction as an example, how the technical scheme trains a model, predicts and gives suggestions.
Firstly, collecting the electric energy data of the air conditioner in a period of time (such as one month), and carrying out data preprocessing, feature extraction and model training on the electric energy data according to the technical scheme. In the process, a support vector regression algorithm can be used as a basic framework for model training, and simultaneously, a deep learning model such as a convolutional neural network and the like is utilized for extracting features of time series data. Through the trained model, the electric energy consumption condition of the air conditioner in a period of time in the future can be predicted, and corresponding suggestions are given.
Assuming that the energy consumption of the air conditioner in the future week has been predicted by training the model, the result shows that the energy consumption of the air conditioner gradually increases as the weather becomes more and more hot. In order to save energy and improve energy efficiency, the model may give the following suggestions:
adjusting the service time of the air conditioner: if the weather is cool, the air conditioner is turned off as much as possible during the day or night, and is turned on only when necessary. If the weather is very hot, it is considered to extend the service life of the air conditioner, but care should be taken to make a reasonable arrangement.
Adjusting the temperature of the air conditioner: the temperature of the air conditioner is set within a comfortable range (generally 26-28 ℃), so that the air conditioner is not too low or too high, and the energy waste is avoided.
Regularly maintaining air conditioning equipment: the air conditioner filter screen can be cleaned, the air conditioner filter element can be replaced, and the like, so that the energy efficiency of the air conditioner can be improved, and the energy consumption can be reduced.
Through the proposal, a user can adjust the use mode, the temperature and the equipment maintenance of the air conditioner according to the actual situation, thereby achieving the aims of saving energy and reducing waste.
It should be noted that the technical scheme not only can be applied to the energy prediction and suggestion adjustment of single equipment such as an air conditioner, but also can predict and optimize the overall energy consumption condition of a building, thereby helping users to realize comprehensive energy efficiency management.
According to the technical scheme, after cleaning, missing value filling and normalization processing, time series cutting is carried out on collected electric energy data to obtain a plurality of time series fragments, and feature extraction is carried out on each time series fragment by adopting a network structure based on alternate stacking of convolution layers and pooling layers. And then, using a support vector regression algorithm to carry out model training on the extracted characteristics and predict the energy consumption of each electric appliance. And finally, according to the trained model, combining building energy consumption data acquired in real time, giving corresponding advice and second preset data in the platform, and enabling a user to adjust all equipment in the building according to the advice given by the model, thereby achieving the purposes of saving energy and improving energy efficiency. Specifically, the technical scheme adopts an advanced machine learning algorithm and a neural network architecture, and has strong advantages in processing time sequence data and building energy consumption data, and the working principle and effects are as follows: the collected electric energy data is subjected to preprocessing operations such as cleaning, missing value filling, normalization and the like, and the data is converted into a format suitable for neural network processing; then, feature extraction is performed on each time-series segment by using a network structure based on alternating stacking of convolution layers and pooling layers. In the process, the convolutional neural network can learn information such as fluctuation, trend and the like in the time sequence segment, so that more abundant and useful characteristics are extracted; next, model training is performed on the extracted features and energy consumption of each electrical appliance is predicted by using a support vector regression algorithm. The algorithm can effectively process high-dimensional data and has good generalization performance and accuracy. Through the trained model, corresponding advice and second preset data in the platform can be given according to building energy consumption data acquired in real time; finally, the user can adjust all the devices in the building according to the suggestions given by the model so as to achieve the purposes of saving energy and improving energy efficiency. For example, according to the model prediction result, the factors such as the switching time, the power size and the like can be adjusted according to the energy consumption conditions of different electrical equipment, so that the building energy consumption is optimized, and the energy efficiency level is improved. According to the technical scheme, through advanced data processing and machine learning methods, intelligent prediction and energy efficiency adjustment of building energy consumption are realized, a user can be helped to better manage building energy, the energy efficiency level is improved, and the aims of saving energy and reducing waste are fulfilled.
The embodiment provides a building energy efficiency management system, the system includes:
the system comprises a data acquisition module, an indoor and outdoor environment data acquisition module and an indoor and outdoor environment data acquisition module, wherein each electric energy acquisition node acquires electric energy consumed by each electric appliance, and the acquired electric energy data is sent to an indoor secondary building energy efficiency management platform through ZigBee;
the analysis data module is used for enabling the indoor secondary building energy efficiency management platform to analyze the indoor and outdoor environment data and the electric energy data and sending the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the model training module is used for receiving the electric energy data by the first-level building energy efficiency management platform, training the model by a deep learning algorithm, giving suggestions according to the trained model, and adjusting all the devices according to the suggestions.
The working principle and the effect of the technical scheme are as follows: the indoor and outdoor environment data and the electric energy data consumed by each electric appliance are collected through the sensors arranged indoors and outdoors, and the data are sent to an indoor secondary building energy efficiency management platform through ZigBee, so that the real-time monitoring and collection of the data are realized; in the second-level building energy efficiency management platform, the indoor and outdoor environment data and the electric energy data are analyzed, the indoor and outdoor environment data and the electric energy data are sent to the first-level building energy efficiency management platform through a network, so that the energy consumption condition of a building can be comprehensively monitored and analyzed, powerful data support is provided for subsequent optimization, in the first-level building energy efficiency management platform, the electric energy data are received, model training is conducted on the electric energy data through a deep learning algorithm, suggestions are given according to the trained models, and each device is adjusted according to the suggestions. The method can predict and optimize the energy consumption condition of the building, thereby achieving the purposes of reducing the energy consumption and improving the energy efficiency; according to the technical scheme, the energy consumption condition of the building is monitored in real time, rules and problems in the energy consumption condition are analyzed, and optimization suggestions are given out through a deep learning algorithm, so that the energy consumption of the building is effectively managed and optimized, and the purposes of saving energy and reducing carbon emission are achieved.
The building energy efficiency management system of this embodiment, the data acquisition module includes:
the detection module is used for detecting the temperature, the humidity and the rainfall of the external environment by using temperature, humidity and rainfall sensors arranged on windows, detecting indoor brightness, people, temperature and humidity by using indoor brightness sensors, infrared sensors, temperature sensors and humidity sensors respectively, and acquiring electric energy consumption of each electric appliance by using electric energy acquisition nodes arranged on air conditioners, lighting equipment and elevators;
and the communication module is used for transmitting the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node to the indoor secondary building energy efficiency management platform through ZigBee.
The working principle and the effect of the technical scheme are as follows: according to the technical scheme, through the sensors and the electric energy collection nodes which are arranged on windows, indoor and air-conditioning, lighting equipment and elevators, the real-time monitoring and collection of the building environment and equipment energy consumption are realized, and specifically, the temperature, humidity and rainfall sensors which are arranged on the windows are used for detecting the temperature, humidity and rainfall of the external environment; and the indoor brightness sensor, the infrared sensor, the temperature sensor and the humidity sensor are respectively used for detecting the indoor brightness, the existence of people, the temperature and the humidity. Meanwhile, the electric energy collection nodes deployed on the air conditioner, the lighting equipment and the elevator collect the electric energy consumption condition of each electric appliance. The data are transmitted to an indoor secondary building energy efficiency management platform for analysis and processing through ZigBee, and in the secondary building energy efficiency management platform, the data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are integrated and analyzed, so that comprehensive monitoring and analysis of building energy consumption conditions are realized, and data support is provided for subsequent optimization. According to the technical scheme, through the deployment of the plurality of sensors and the electric energy collection nodes, the real-time monitoring and collection of the building environment and the equipment energy consumption condition are realized, the data analysis and processing are carried out through the two-stage building energy efficiency management platform, and the comprehensive monitoring and optimization of the building energy consumption condition are realized. Finally, the purposes of saving energy and improving energy efficiency are achieved.
The building energy efficiency management system of this embodiment, the analysis data module includes:
the indoor secondary building energy efficiency management platform receives the data acquired by the sensors and the electric energy data consumed by the electric appliances acquired by the electric energy acquisition nodes through ZigBee and stores the data in a database of the platform;
the comparison module is used for comparing the received data with first preset data in the platform after the data are analyzed by the secondary building energy efficiency management platform, and sending alarm information to the user equipment by the secondary building energy efficiency management platform when the data differ by more than 5 units;
the primary platform and secondary platform communication module is used for the secondary building energy efficiency management platform to send the data stored in the database to the primary building energy efficiency management platform through a network.
According to the technical scheme, the indoor two-stage building energy efficiency management platform is used for receiving, storing and analyzing the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node, specifically, the indoor two-stage building energy efficiency management platform receives the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node through a ZigBee protocol and stores the data in a database of the platform. Then, the platform compares the received data with first preset data in the platform by analyzing the data, and when the data differ by more than 5 units, the secondary building energy efficiency management platform can send alarm information to the user equipment to remind the user of paying attention to the running condition of the equipment and timely maintain or repair the equipment. After the data processing and analysis are completed, the secondary building energy efficiency management platform sends the data stored in the database to the primary building energy efficiency management platform through a network, so that the real-time monitoring and analysis of the building energy consumption condition are realized. According to the technical scheme, through the indoor two-level building energy efficiency management platform, the data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are received, stored and analyzed, and a user is prompted to pay attention to the running condition of the equipment through a comparison and alarm mechanism. Meanwhile, the data is sent to the first-level building energy efficiency management platform, so that comprehensive monitoring and grasping of the energy consumption condition of the building are realized. Finally, the purposes of saving energy and improving energy efficiency are achieved.
The building energy efficiency management system of this embodiment is characterized in that the comparison module includes:
the air conditioner door and window linkage module is used for comparing the received data detected by the temperature, humidity and rainfall sensors deployed on the windows with first preset data in the platform by the two-stage building energy efficiency management platform, checking the air conditioner electric energy consumption data if the detected data of the external environment is not different from the first preset data in the platform by more than three units, and controlling to open the door and window and close the air conditioner if the air conditioner is in an open state at the moment;
the lighting system adjusting module is used for receiving data sent by the indoor brightness sensor by the secondary building energy efficiency management platform, and adjusting the lamp to be in a 1/3 scene mode if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in the 1/3 scene mode; the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
And the alarm module is used for comparing the energy consumption data of each electric appliance with second preset data in the platform by the two-stage building energy efficiency management platform, and sending alarm information to the user equipment if the difference of the data is found to be more than 5 units.
The working principle and the effect of the technical scheme are as follows: and the automatic control and adjustment of the building environment and equipment energy consumption are realized through an indoor two-stage building energy efficiency management platform. Specifically, the secondary building energy efficiency management platform receives data detected by temperature, humidity and rain sensors deployed on windows and compares the data with first preset data in the platform. If the data of the external environment is found to be different from the first preset data in the platform by no more than three units, and the air conditioner is in an open state at the moment, controlling to open doors and windows and closing the air conditioner. Therefore, not only can energy be saved and the energy efficiency be improved, but also air conditioner diseases are avoided, and the secondary building energy efficiency management platform also receives data sent by indoor brightness sensors. If the display room brightness of the brightness sensor is found to be in the "bright" mode and the lamp is not in the 1/3 scene mode, the lamp is adjusted to the 1/3 scene mode. For the corridor situation, if the corridor brightness is found to be in a 'dark' mode, and the data detected by the infrared sensor show that the traffic is in a 'multiple' state, the lamp is adjusted to be in a 1 scene mode; if the corridor brightness is found to be in a 'dark' mode and the data detected by the infrared sensor show that the traffic is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode; if the corridor brightness is found to be in the "dark" mode and the data detected by the infrared sensor indicates that the traffic is in the "less" mode, the light is adjusted to the 1/3 scene mode. Therefore, the brightness and the state of the lighting equipment can be automatically controlled according to the actual situation, and the aim of saving energy is achieved. In addition, the secondary building energy efficiency management platform also compares the energy consumption data of each electric appliance with second preset data in the platform. If the data difference is found to be more than 5 units, alarm information is sent to the user equipment to prompt the user to pay attention to the running condition of the equipment, and maintenance or repair is timely carried out. According to the technical scheme, through automatic control and adjustment of the two-stage building energy efficiency management platform, intelligent monitoring and optimization of building environment and equipment energy consumption conditions are realized, and therefore the purposes of saving energy and improving energy efficiency are achieved.
The building energy efficiency management system of this embodiment, the model training module includes:
the data preprocessing module is used for carrying out time sequence cutting on the received electric energy data after washing, missing value filling and normalization processing to obtain a plurality of time sequence fragments, wherein each fragment comprises data of a plurality of time steps;
the feature extraction module adopts a network structure based on alternating stacking of a convolution layer and a pooling layer, and uses a convolution neural network to extract features of each time sequence segment, and the convolution neural network learns fluctuation and trend in the time sequence segments;
the prediction module is used for carrying out model training on the extracted characteristics and predicting the energy consumption of each electric appliance by using a support vector regression algorithm;
and the generation advice and second preset data module is used for providing corresponding advice and second preset data in the platform according to the trained model and combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice provided by the model.
According to the technical scheme, after cleaning, missing value filling and normalization processing, time series cutting is carried out on collected electric energy data to obtain a plurality of time series fragments, and feature extraction is carried out on each time series fragment by adopting a network structure based on alternate stacking of convolution layers and pooling layers. And then, using a support vector regression algorithm to carry out model training on the extracted characteristics and predict the energy consumption of each electric appliance. And finally, according to the trained model, combining building energy consumption data acquired in real time, giving corresponding advice and second preset data in the platform, and enabling a user to adjust all equipment in the building according to the advice given by the model, thereby achieving the purposes of saving energy and improving energy efficiency. Specifically, the technical scheme adopts an advanced machine learning algorithm and a neural network architecture, and has strong advantages in processing time sequence data and building energy consumption data, and the working principle and effects are as follows: the collected electric energy data is subjected to preprocessing operations such as cleaning, missing value filling, normalization and the like, and the data is converted into a format suitable for neural network processing; then, feature extraction is performed on each time-series segment by using a network structure based on alternating stacking of convolution layers and pooling layers. In the process, the convolutional neural network can learn information such as fluctuation, trend and the like in the time sequence segment, so that more abundant and useful characteristics are extracted; next, model training is performed on the extracted features and energy consumption of each electrical appliance is predicted by using a support vector regression algorithm. The algorithm can effectively process high-dimensional data and has good generalization performance and accuracy. Through the trained model, corresponding advice and second preset data in the platform can be given according to building energy consumption data acquired in real time; finally, the user can adjust all the devices in the building according to the suggestions given by the model so as to achieve the purposes of saving energy and improving energy efficiency. For example, according to the model prediction result, the factors such as the switching time, the power size and the like can be adjusted according to the energy consumption conditions of different electrical equipment, so that the building energy consumption is optimized, and the energy efficiency level is improved. According to the technical scheme, through advanced data processing and machine learning methods, intelligent prediction and energy efficiency adjustment of building energy consumption are realized, a user can be helped to better manage building energy, the energy efficiency level is improved, and the aims of saving energy and reducing waste are fulfilled.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A method of building energy efficiency management, the method comprising:
indoor and outdoor environment data are collected by sensors arranged indoors and outdoors, electric energy consumed by each electric appliance is collected by each electric energy collection node, and the collected electric energy data are sent to an indoor secondary building energy efficiency management platform through ZigBee;
the indoor secondary building energy efficiency management platform analyzes the indoor and outdoor environment data and the electric energy data, and sends the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives out suggestions according to the trained model, and adjusts all the devices according to the suggestions.
2. The building energy efficiency management method according to claim 1, wherein the indoor and outdoor environment data are collected by sensors deployed in the indoor and outdoor environment, the electric energy consumed by each electric appliance is collected by each electric energy collection node, and the collected electric energy data are sent to the indoor two-stage building energy efficiency management platform through ZigBee, comprising:
The temperature, humidity and rainfall sensors arranged on the windows detect the temperature, humidity and rainfall of the external environment, the indoor brightness sensor, the infrared sensor, the temperature sensor and the humidity sensor are respectively arranged in the room to detect whether the indoor brightness, the person, the temperature and the humidity exist or not, and the electric energy collection nodes arranged on the air conditioner, the lighting equipment and the elevator collect the electric energy consumption of each electric appliance;
all sensors collect data according to a sampling period standard, wherein the sampling period standard is as follows:
wherein count represents the total number of times the infrared sensor has detected a person in the last N detections, N i Indicating the number of times the infrared sensor detects the i-th person,
β＝2*α/(C*γ)
wherein beta represents the proportionality coefficient of the sampling period, alpha represents the standard deviation of temperature data, gamma represents the average value of all data, C is a constant for adjusting the relation between the sampling period and the fluctuation degree of environmental data, the value range is between 0.5 and 2,
T＝max(k'*β*α，T0)
wherein T0 represents a default sampling period, namely, a sampling period used when fluctuation of the environmental data is small, the value range is between [1,10] seconds, max represents the maximum value of the two, k' represents a proportionality coefficient calculated according to count,
k'＝(count/N)^e
Wherein e is an index for controlling the relation between the proportional coefficient and the number of people, the value range is between [1,3],
the data collected by each sensor and the electric energy data consumed by each electric appliance collected by each electric energy collection node are sent to an indoor secondary building energy efficiency management platform through ZigBee.
3. The building energy efficiency management method according to claim 1, wherein the indoor secondary building energy efficiency management platform analyzes the indoor and outdoor environment data and the electric energy data, and transmits the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network, comprising:
the indoor two-level building energy efficiency management platform receives the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node through ZigBee and stores the data in a database of the platform;
after the secondary building energy efficiency management platform analyzes the data, the received data is compared with first preset data in the platform, and when the data difference exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to user equipment;
and the secondary building energy efficiency management platform sends the data stored in the database to the primary building energy efficiency management platform through a network.
4. The building energy efficiency management method according to claim 3, wherein after the secondary building energy efficiency management platform analyzes the data, the received data is compared with preset data in the platform, and when the data differ by more than 5 units, the secondary building energy efficiency management platform sends alarm information to the user equipment, comprising:
the second-level building energy efficiency management platform compares the received data detected by the temperature, humidity and rainfall sensors deployed on the window with first preset data in the platform, if the detected data of the external environment is not different from the first preset data in the platform by more than three units, the data of the electric energy consumption of the air conditioner is checked, and if the air conditioner is in an open state at the moment, the door and window are controlled to be opened, and the air conditioner is closed;
the secondary building energy efficiency management platform receives data sent by an indoor brightness sensor, and if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in a 1/3 scene mode, the lamp is adjusted to be in the 1/3 scene mode;
the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
And the secondary building energy efficiency management platform compares the energy consumption data of each electric appliance with second preset data in the platform, and if the difference between the energy consumption data and the second preset data exceeds 5 units, the secondary building energy efficiency management platform sends alarm information to the user equipment.
5. The building energy efficiency management method according to claim 1, wherein the first-level building energy efficiency management platform receives the electric energy data, performs model training on the electric energy data through a deep learning algorithm, gives suggestions according to the trained model, and adjusts each device according to the suggestions, including:
after washing, missing value filling and normalization processing are carried out on the received electric energy data, time sequence cutting is carried out on the data to obtain a plurality of time sequence fragments, and each fragment comprises data of a plurality of time steps;
adopting a network structure based on alternating stacking of convolution layers and pooling layers, and carrying out feature extraction on each time sequence segment by using a convolution neural network, wherein the convolution neural network learns the fluctuation and trend in the time sequence segments;
model training is carried out on the extracted features by using a support vector regression algorithm, and the energy consumption of each electric appliance is predicted;
according to the trained model, corresponding advice and second preset data in the platform are given by combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice given by the model.
6. A building energy efficiency management system, the system comprising:
the system comprises a data acquisition module, an indoor and outdoor environment data acquisition module and an indoor and outdoor environment data acquisition module, wherein each electric energy acquisition node acquires electric energy consumed by each electric appliance, and the acquired electric energy data is sent to an indoor secondary building energy efficiency management platform through ZigBee;
the analysis data module is used for enabling the indoor secondary building energy efficiency management platform to analyze the indoor and outdoor environment data and the electric energy data and sending the indoor and outdoor environment data and the electric energy data to the primary building energy efficiency management platform through a network;
the model training module is used for receiving the electric energy data by the first-level building energy efficiency management platform, training the model by a deep learning algorithm, giving suggestions according to the trained model, and adjusting all the devices according to the suggestions.
7. The building energy efficiency management system of claim 6, wherein the collected data module comprises:
the detection module is used for detecting the temperature, the humidity and the rainfall of the external environment by using temperature, humidity and rainfall sensors arranged on windows, detecting indoor brightness, people, temperature and humidity by using indoor brightness sensors, infrared sensors, temperature sensors and humidity sensors respectively, and acquiring electric energy consumption of each electric appliance by using electric energy acquisition nodes arranged on air conditioners, lighting equipment and elevators;
All sensors collect data according to a sampling period standard, wherein the sampling period standard is as follows:
wherein count represents the total number of times the infrared sensor has detected a person in the last N detections, N i Indicating the number of times the infrared sensor detects the i-th person,
β＝2*α/(C*γ)
wherein beta represents the proportionality coefficient of the sampling period, alpha represents the standard deviation of temperature data, gamma represents the average value of all data, C is a constant for adjusting the relation between the sampling period and the fluctuation degree of environmental data, the value range is between 0.5 and 2,
T＝max(k'*β*α，T0)
wherein T0 represents a default sampling period, namely, a sampling period used when fluctuation of the environmental data is small, the value range is between [1,10] seconds, max represents the maximum value of the two, k' represents a proportionality coefficient calculated according to count,
k'＝(count/N)^e
wherein e is an index for controlling the relation between the proportional coefficient and the number of people, the value range is between [1,3],
and the communication module is used for transmitting the data acquired by each sensor and the electric energy data consumed by each electric appliance acquired by each electric energy acquisition node to the indoor secondary building energy efficiency management platform through ZigBee.
8. The building energy efficiency management system of claim 6, wherein the analysis data module comprises:
The indoor secondary building energy efficiency management platform receives the data acquired by the sensors and the electric energy data consumed by the electric appliances acquired by the electric energy acquisition nodes through ZigBee and stores the data in a database of the platform;
the comparison module is used for comparing the received data with first preset data in the platform after the data are analyzed by the secondary building energy efficiency management platform, and sending alarm information to the user equipment by the secondary building energy efficiency management platform when the data differ by more than 5 units;
the primary platform and secondary platform communication module is used for the secondary building energy efficiency management platform to send the data stored in the database to the primary building energy efficiency management platform through a network.
9. The building energy efficiency management system of claim 8, wherein the comparison module comprises:
the air conditioner door and window linkage module is used for comparing the received data detected by the temperature, humidity and rainfall sensors deployed on the windows with first preset data in the platform by the two-stage building energy efficiency management platform, checking the air conditioner electric energy consumption data if the detected data of the external environment is not different from the first preset data in the platform by more than three units, and controlling to open the door and window and close the air conditioner if the air conditioner is in an open state at the moment;
The lighting system adjusting module is used for receiving data sent by the indoor brightness sensor by the secondary building energy efficiency management platform, and adjusting the lamp to be in a 1/3 scene mode if the sensor of the brightness sensor is found to display that the indoor brightness is in a 'bright' mode and the lamp is not in the 1/3 scene mode; the secondary building energy efficiency management platform receives data sent by the indoor brightness sensor and the infrared sensor, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'more' state, the lamp is adjusted to be in a 1 scene mode, if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/2 scene mode, and if the corridor brightness is found to be in a 'dark' mode and the data display personnel flow detected by the infrared sensor is in a 'less' mode, the lamp is adjusted to be in a 1/3 scene mode;
and the alarm module is used for comparing the energy consumption data of each electric appliance with second preset data in the platform by the two-stage building energy efficiency management platform, and sending alarm information to the user equipment if the difference of the data is found to be more than 5 units.
10. The building energy efficiency management system of claim 6, wherein the model training module comprises:
the data preprocessing module is used for carrying out time sequence cutting on the received electric energy data after washing, missing value filling and normalization processing to obtain a plurality of time sequence fragments, wherein each fragment comprises data of a plurality of time steps;
the feature extraction module adopts a network structure based on alternating stacking of a convolution layer and a pooling layer, and uses a convolution neural network to extract features of each time sequence segment, and the convolution neural network learns fluctuation and trend in the time sequence segments;
the prediction module is used for carrying out model training on the extracted characteristics and predicting the energy consumption of each electric appliance by using a support vector regression algorithm;
and the generation advice and second preset data module is used for providing corresponding advice and second preset data in the platform according to the trained model and combining building energy consumption data acquired in real time, and a user adjusts all equipment in the building according to the advice provided by the model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081785.5A CN117094468A (en) | 2023-08-25 | 2023-08-25 | Building energy efficiency management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311081785.5A CN117094468A (en) | 2023-08-25 | 2023-08-25 | Building energy efficiency management system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117094468A true CN117094468A (en) | 2023-11-21 |
Family
ID=88781079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311081785.5A Withdrawn CN117094468A (en) | 2023-08-25 | 2023-08-25 | Building energy efficiency management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094468A (en) |
-
2023
- 2023-08-25 CN CN202311081785.5A patent/CN117094468A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298487B (en) | Indoor temperature prediction method for meeting personalized demands of users | |
| CN107942960B (en) | A kind of intelligentized information processing system | |
| CN102779228B (en) | Method and system for online prediction on cooling load of central air conditioner in marketplace buildings | |
| CN107318534B (en) | Intelligent temperature control method and system of sunlight greenhouse curtain rolling machine with temperature prediction function | |
| CN111735178A (en) | Air conditioner energy-saving system based on elite meaning and SVR regression algorithm and optimization method | |
| CN112050397A (en) | Method and system for regulating and controlling temperature of machine room | |
| WO2011129025A1 (en) | Energy conservation unit and system of a building by way of interactive learning | |
| CN109799726B (en) | Smart home system combined with living environment detection | |
| CN111103220A (en) | Method and system for predicting and regulating concentration of atmospheric pollutants | |
| CN108534325A (en) | Indoor and outdoor surroundings parameter monitors regulating device and applies its unmanned convenience store automatically | |
| KR20220105704A (en) | Intelligent Building Energy Management System Through Complex Control of Sunshade device | |
| CN214619993U (en) | Intelligent control energy-saving system of air conditioner | |
| CN110332686A (en) | A kind of energy consumption of building control energy conserving system and its method | |
| CN117094468A (en) | Building energy efficiency management system and method | |
| CN112307675A (en) | Neural network-based temperature-sensitive load separation identification method and system | |
| CN201803430U (en) | Air-conditioning energy-saving controller in subway station | |
| CN204329251U (en) | A kind of hospital monomer air-conditioning joint control energy-saving management system | |
| CN115758680A (en) | Permanent magnet direct-drive low-speed large fan and central air conditioning system linkage regulation and control method and system | |
| CN103529771A (en) | Family intelligent energy consumption regulation and control system based on data analysis | |
| CN116105217A (en) | Low-energy-consumption building system for combined application of photovoltaic energy and air heat source pump | |
| CN109005092A (en) | Intelligent home control system based on internet of things | |
| CN114489200A (en) | Warmhouse booth environmental control system | |
| CN114548445A (en) | Building operation and maintenance management system based on real-time feedback | |
| CN114189970A (en) | Online learning-based intelligent lamp backup control method | |
| CN112462648A (en) | System for monitoring and predicting building comprehensive environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231121 |
|
| WW01 | Invention patent application withdrawn after publication |