CN117541438A - Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit - Google Patents
Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit Download PDFInfo
- Publication number
- CN117541438A CN117541438A CN202311244763.6A CN202311244763A CN117541438A CN 117541438 A CN117541438 A CN 117541438A CN 202311244763 A CN202311244763 A CN 202311244763A CN 117541438 A CN117541438 A CN 117541438A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- electric power
- condition
- power device
- power unit
- 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- Withdrawn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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 316
- 238000005457 optimization Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000006243 chemical reaction Methods 0.000 claims abstract description 21
- 238000012098 association analyses Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000003491 array Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000005057 refrigeration Methods 0.000 description 3
- 229910000838 Al alloy Inorganic materials 0.000 description 2
- 241000256626 Pterygota <winged insects> Species 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- 239000004411 aluminium Substances 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/163—Real estate management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/80—Homes; Buildings
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Accounting & Taxation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit, which belongs to the technical field of energy efficiency optimization and comprises the following steps: acquiring a historical operation log of a building electric unit, and acquiring all-condition operation data from the historical operation log; performing energy consumption association analysis on the data, determining energy consumption combinations of different power equipment in the building power unit in different running states at the same time, and constructing an energy consumption prediction model; acquiring operation information of each power device at the current moment, predicting current energy consumption, comparing the energy consumption, and determining an adjustable working condition of each power device according to an energy consumption optimal principle and a normal operation principle; based on the control box of the Internet of things, the working condition conversion is carried out, and the energy efficiency optimization is realized. The operation data of the building electric power unit is obtained by analyzing the historical operation log, the energy consumption prediction model is constructed through the operation data, the accuracy of the prediction data is guaranteed, and the energy efficiency optimization is effectively realized through the conversion of working conditions.
Description
Technical Field
The invention relates to the technical field of energy efficiency optimization, in particular to a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit.
Background
In order to realize energy conservation and environmental protection and reduce unnecessary energy consumption, intelligent monitoring and energy consumption data analysis are needed to be carried out on the energy consumption of a system of an electric power unit of a building, a multivariable model affecting the energy consumption is established, and energy efficiency optimization is further realized.
Therefore, the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit.
Disclosure of Invention
The invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method of a building electric power unit, which is used for constructing an energy consumption prediction model by carrying out energy consumption correlation analysis on data of a historical operation log, predicting the current energy consumption of the building electric power unit and the adjustable working condition of each electric power device through the energy consumption prediction model, and realizing energy efficiency optimization by adjusting the corresponding electric power device through an Internet of things control box.
The invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method of a building electric power unit, which comprises the following steps:
step 1: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
step 2: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
step 3: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
step 4: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
In one possible implementation manner, obtaining all-condition operation data of each electric device in the building electric power unit from the historical operation log includes:
based on the all-condition state of each power equipment, extracting data from the historical operation log;
and determining the operation data of each power equipment under different working conditions based on the extraction result to obtain the full-working-condition operation data.
In one possible implementation manner, performing energy consumption correlation analysis on the all-condition operation data to determine energy consumption combinations of different power devices in the building power unit in different operation states at the same time, where the method includes:
according to the full-working-condition operation data of each power device, determining a first working-condition array of the same power device at different moments, and performing energy consumption conversion on the first working-condition array to obtain a first energy consumption array;
performing time alignment processing on the first energy consumption arrays of different power equipment, constructing to obtain a first energy consumption matrix, and respectively extracting each column in the first energy consumption matrix as an initial combination;
calculating a first energy consumption value of each initial array, simultaneously, carrying out superposition classification on all initial arrays, and preprocessing all first energy consumption values under corresponding classification by combining the combination superposition degree corresponding to superposition classification to obtain a second energy consumption value, wherein the superposition classification refers to the consistency of operation setting parameters of the power equipment under different moments;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a corresponding second energy consumption value; />Representing the maximum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the minimum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the i1 first energy consumption value in the corresponding coincidence classification; n0 represents the initial combination number in the corresponding coincidence classification; />Representing the total number of initial combinations; />Representing the corresponding combination overlap ratio;
determining a standard energy consumption variance based on the second energy consumption value and all the first energy consumption values under the same coincidence classificationAnd combining standard loss factors corresponding to operation setting parameters under the same coincidence classification, and configuring a first energy consumption factor for each power equipment under the same coincidence classification to obtain an energy consumption combination under the same coincidence classification;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>The total number of rows of the first energy consumption matrix is represented and is consistent with the total number of elements contained in each column of the matrix; />Representing a standard loss factor of the j1 st power equipment in the same coincidence classification; />Representing the same coincidence classificationA first power consumption factor of the j1 st power device; />Representing the energy consumption value of the (1) th power equipment in the same coincidence classification based on the (1) th initial combination;
according to the operation setting array and the first energy consumption array of the non-coincident categorization, configuring a second energy consumption factor for each power equipment under the non-coincident categorization to obtain an energy consumption combination under the non-coincident categorization;
wherein (1)>Representing standard loss factors of corresponding power equipment under non-coincident classification; />A second loss factor representing the corresponding power device under the non-coincident categorization; />Representing the corresponding energy consumption variance under non-coincident categorization; />Representing the actual loss value of the j2 power equipment in the non-coincident classification; />And the standard loss value of the j2 power equipment in the non-coincident classification is represented.
In one possible implementation, building an energy consumption prediction model includes:
inputting all the energy consumption combinations and the first operation setting states under the same coincidence classification into the neural network model for first main training, and simultaneously inputting the initial combinations consistent with all the coincidence classification into the neural network model for first auxiliary training;
inputting all the energy consumption combinations under the non-coincident classification and the second operation setting state into the neural network model for second main training, and simultaneously inputting the initial combination consistent with all the non-coincident classification into the neural network model for second auxiliary training;
and obtaining an energy consumption prediction model based on the training result.
In one possible implementation manner, the method for obtaining the operation information of each power device in the building power unit at the current moment, and sequentially inputting the operation information into the energy consumption prediction model to predict the current energy consumption of each power device includes:
real-time monitoring is carried out on the real-time operation state of each electric power device in the building electric power unit, and the operation information of each electric power device at the current moment is obtained based on the real-time monitoring result;
and carrying out information standardization on the running information at the current moment according to the input standard of the energy consumption prediction model, inputting the standardized information into the energy consumption prediction model to obtain the predicted energy consumption of each power device, and taking the predicted energy consumption as the current energy consumption of the corresponding power device.
In one possible implementation, the current integrated energy consumption is compared with the allowable maximum energy consumption, and the adjustable working condition of each power device is determined according to the energy consumption optimal principle and the normal operation principle, including:
superposing the current energy consumption of each power device to obtain the current comprehensive energy consumption, and obtaining the current allowable maximum energy consumption based on the preset energy consumption condition of each power device;
comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and if the current comprehensive energy consumption is smaller than or equal to the allowable maximum energy consumption, controlling each electric power device to continue to operate according to the current working condition;
if the current comprehensive energy consumption exceeds the allowable maximum energy consumption, the current working condition of each power device is adjusted;
and acquiring a set of to-be-adjusted working conditions of each electric device in the building electric power unit, which is consistent with the corresponding normal operation condition at the current moment, based on the normal operation principle, selecting from the set of to-be-adjusted working conditions of the corresponding electric devices based on the energy consumption optimal principle, and determining the adjustable working condition of each electric device.
In one possible implementation manner, based on the control box of the internet of things, controlling the corresponding power equipment to perform working condition conversion according to the adjustable working condition, so as to realize energy efficiency optimization, including:
comparing the current working condition of each power device with the corresponding adjustable working condition to obtain an adjustment strategy;
and carrying out working condition conversion on the working condition of each power device according to the adjustment strategy through the control box of the Internet of things, so as to realize energy efficiency optimization.
The invention provides a full-working-condition energy consumption prediction and energy efficiency optimization device of a building electric power unit, which comprises the following components:
and a data acquisition module: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
model construction module: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
the working condition determining module: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
and the working condition adjusting module is used for: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for predicting all-condition energy consumption and optimizing energy efficiency of a building electric power unit in an embodiment of the invention;
fig. 2 is a structural design diagram of a body of an internet of things control box in an embodiment of the invention;
fig. 3 is a control interface display diagram of an internet of things control box in an embodiment of the 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 embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method of a building electric power unit, which is shown in fig. 1 and comprises the following steps:
step 1: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
step 2: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
step 3: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
step 4: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
In this embodiment, the building power unit is composed of power equipment required for use in the process of building, such as air conditioning and heating equipment, elevators, water pumps, ventilators, etc.
In this embodiment, the full-working-condition operation data refers to all operation data of each electric device under different working conditions, such as operation data of an air conditioner under different refrigeration temperatures, where the operation data includes energy consumption data, operation state data, and the like.
In this embodiment, the energy consumption association analysis refers to associating working conditions of different power devices with energy consumption conditions to obtain energy consumption combinations of the power devices under the different working conditions, where the energy consumption combinations refer to energy consumption conditions of the different power devices under normal running states at the same time.
In this embodiment, the energy consumption prediction model refers to obtaining the current energy consumption of each electric device at this time through the operation setting parameters of each electric device.
In this embodiment, the operation information includes information about different working conditions of each electric device and specific setting information of a current working condition, such as a specific setting refrigeration temperature of the air conditioner under a refrigeration working condition.
In this embodiment, the current integrated energy consumption refers to the total value of the energy consumption of all the power devices at the present moment.
In this embodiment, the allowable maximum energy consumption refers to the maximum value of energy consumption, that is, the maximum allowable value of energy consumption of each power device in summary.
In the embodiment, the energy consumption optimization principle refers to ensuring that the total energy consumption of all the electric power equipment is the lowest in the operation process of the building electric power unit, and the normal operation principle refers to ensuring that all the electric power equipment can normally operate.
In this embodiment, the adjustable working condition refers to a range in which the operation working condition of each electric power device can be adjusted under the constraint of the energy consumption optimization principle and the normal operation principle.
In this embodiment, thing networking control box is the structure of full aluminium fuselage, and the frame of fuselage is full aluminium frame and uses aluminum alloy connecting piece and aluminum alloy stiffening rib, specifically as shown in fig. 2, and thing networking control box includes: the system comprises a power supply, an automatic manual alarm switching button, an emergency braking button, an automatic manual closing button, a frequency control button, a fault button, a starting closing button, a solar control button, each power equipment state lamp panel, a control screen and a running time display screen, and is particularly shown in fig. 3.
In this embodiment, energy efficiency optimization refers to achieving reduction of total energy consumption of the electric power unit under the condition that normal operation of the electric power unit is ensured.
The beneficial effects of the technical scheme are as follows: the method comprises the steps of obtaining a historical operation log, carrying out energy consumption association analysis on all-condition operation data in the historical operation log, constructing an energy consumption prediction model, guaranteeing the accuracy of energy consumption prediction, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, determining the adjustable condition of each power device according to the energy consumption optimal principle and the normal operation principle, adjusting the condition through an Internet of things control box, controlling the condition, and guaranteeing that each power device in the power unit effectively achieves energy consumption optimization under the normal operation condition.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method of a building electric power unit, which obtains full-working-condition operation data of each electric power device in the building electric power unit from a historical operation log, and comprises the following steps:
based on the all-condition state of each power equipment, extracting data from the historical operation log;
and determining the operation data of each power equipment under different working conditions based on the extraction result to obtain the full-working-condition operation data.
In this embodiment, the full-condition state refers to all condition states of each electric device, such as the full-condition state of the air conditioner including cooling, heating, humidifying, and the like.
In this embodiment, the extraction result refers to the operation data related to the all-condition state of each power device in the history operation log.
The beneficial effects of the technical scheme are as follows: the data is extracted from the historical operation data, the full-working-condition operation data of each power device is determined from the extraction, powerful data support is provided for subsequent energy consumption correlation analysis, and the reliability of data sources is guaranteed.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method of a building electric power unit, which is used for carrying out energy consumption correlation analysis on full-working-condition operation data to determine energy consumption combinations of different electric power equipment in the building electric power unit in different operation states at the same time, and comprises the following steps:
according to the full-working-condition operation data of each power device, determining a first working-condition array of the same power device at different moments, and performing energy consumption conversion on the first working-condition array to obtain a first energy consumption array;
performing time alignment processing on the first energy consumption arrays of different power equipment, constructing to obtain a first energy consumption matrix, and respectively extracting each column in the first energy consumption matrix as an initial combination;
calculating a first energy consumption value of each initial array, simultaneously, carrying out superposition classification on all initial arrays, and preprocessing all first energy consumption values under corresponding classification by combining the combination superposition degree corresponding to superposition classification to obtain a second energy consumption value, wherein the superposition classification refers to the consistency of operation setting parameters of the power equipment under different moments;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a corresponding second energy consumption value; />Representing the maximum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the minimum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the i1 first energy consumption value in the corresponding coincidence classification; n0 represents the initial combination number in the corresponding coincidence classification; />Representing the total number of initial combinations; />Representing the corresponding combination overlap ratio;
determining a standard energy consumption variance based on the second energy consumption value and all the first energy consumption values under the same coincidence classificationAnd combining standard loss factors corresponding to operation setting parameters under the same coincidence classification, and configuring a first energy consumption factor for each power equipment under the same coincidence classification to obtain an energy consumption combination under the same coincidence classification;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>The total number of rows of the first energy consumption matrix is represented and is consistent with the total number of elements contained in each column of the matrix; />Representing a standard loss factor of the j1 st power equipment in the same coincidence classification; />A first energy consumption factor representing the j1 st power device in the same coincidence classification;representing the energy consumption value of the (1) th power equipment in the same coincidence classification based on the (1) th initial combination;
according to the operation setting array and the first energy consumption array of the non-coincident categorization, configuring a second energy consumption factor for each power equipment under the non-coincident categorization to obtain an energy consumption combination under the non-coincident categorization;
wherein (1)>Representing standard loss factors of corresponding power equipment under non-coincident classification; />A second loss factor representing the corresponding power device under the non-coincident categorization;representing the corresponding energy consumption variance under non-coincident categorization; />Representing the actual loss value of the j2 power equipment in the non-coincident classification; />And the standard loss value of the j2 power equipment in the non-coincident classification is represented.
In this embodiment, the first working condition array refers to a specific operation working condition array of the same power device at different moments, that is, specific operation data, and the operation conditions corresponding to the working conditions under different conditions may be different.
In this embodiment, the energy consumption conversion is to perform matching conversion on the working condition data related to the working condition array, and the obtained energy consumption data is obtained based on a working condition-energy consumption mapping table, where the working condition-energy consumption mapping table includes different working condition data and energy consumption matched with the working condition data, for example, the working condition is a third gear of operation, and at this time, the corresponding energy consumption is matched to 100J.
In this embodiment, the first operating condition array of the electrical device 1 is [ operating condition data of operating condition data time 2 of time 1, operating condition data of time 3 ].
In this embodiment, the first energy consumption array is [ energy consumption of energy consumption time 3 of energy consumption time 2 of time 1.], and n2 elements are included in the first energy consumption array.
In this embodiment, the first energy consumption matrix =。
In this embodiment, the initial array is such as: energy consumption of device 1 at time 1.
In this embodiment, the first energy consumption value = the sum of all energy consumption in the corresponding column.
In this embodiment, the combination classification refers to that the operation setting parameters of the electric devices at the corresponding time are consistent, for example, n2 times exist, and the operation setting parameters of the devices at times 1, 3, 4, and 5 are consistent, at this time, the times corresponding to the consistent operation setting parameters are grouped into a group, because, in the actual operation process of the devices, due to errors of the devices themselves or errors of the systems themselves, and the like, a certain difference exists between the actual operation parameters and the operation setting parameters at different times.
In this embodiment, the energy consumption is combined: first energy consumption factor of device 1 first energy consumption factor of device 2.
The beneficial effects of the technical scheme are as follows: the data analysis is carried out on the all-condition operation data of each power device, and all energy consumption combinations of each power device under different conditions are obtained through energy consumption conversion, so that the comprehensiveness of the energy consumption combinations is ensured, and convenience is provided for the follow-up construction of the energy consumption prediction model.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit, which comprises the following steps of:
inputting all the energy consumption combinations and the first operation setting states under the same coincidence classification into the neural network model for first main training, and simultaneously inputting the initial combinations consistent with all the coincidence classification into the neural network model for first auxiliary training;
inputting all the energy consumption combinations under the non-coincident classification and the second operation setting state into the neural network model for second main training, and simultaneously inputting the initial combination consistent with all the non-coincident classification into the neural network model for second auxiliary training;
and obtaining an energy consumption prediction model based on the training result.
In this embodiment, the first operation setting state refers to an operation setting state when the operation parameters of the electric device are the same at different times.
In this embodiment, the first main training refers to a process of training the energy consumption combination and the first operation setting state under the same superposition classification to obtain the energy consumption of the power equipment conforming to the first operation setting state, and the accuracy of the training result is improved by performing auxiliary training on the initial combination consistent with the same superposition classification.
In this embodiment, the second operation setting state refers to an operation setting state reflecting the operation parameters of the electric power equipment at different times.
In this embodiment, the second main training refers to a process of training all the non-coincident classified energy consumption combinations and the second operation setting state to obtain the energy consumption of the electric power equipment conforming to the second operation setting state, and improves the accuracy of the training result by performing auxiliary training on the winged insects and the classified initial combination.
The beneficial effects of the technical scheme are as follows: the known energy consumption combinations, running setting states and corresponding initial combinations under the same coincidence classification are trained through the neural network model to obtain the energy consumption situation of the combinations conforming to the coincidence classification, the accuracy of data is guaranteed, the energy consumption situation of the winged insects and the classification combinations is obtained through training the energy consumption combinations, the running setting states and the corresponding initial combinations under the non-coincidence classification, the comprehensiveness of the data is guaranteed, and powerful guarantee is provided for obtaining accurate data through energy consumption prediction through an energy consumption prediction model.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit, which is used for acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into an energy consumption prediction model and predicting the current energy consumption of each electric power device, and comprises the following steps:
real-time monitoring is carried out on the real-time operation state of each electric power device in the building electric power unit, and the operation information of each electric power device at the current moment is obtained based on the real-time monitoring result;
and carrying out information standardization on the running information at the current moment according to the input standard of the energy consumption prediction model, inputting the standardized information into the energy consumption prediction model to obtain the predicted energy consumption of each power device, and taking the predicted energy consumption as the current energy consumption of the corresponding power device.
In this embodiment, the input standard of the energy consumption prediction model refers to an input standard capable of reflecting the corresponding energy consumption situation in the energy consumption prediction model.
In this embodiment, the information normalization is a process of extracting information by which the operation information at the present time is subjected to information extraction in accordance with the input standard, to obtain information conforming to the input standard.
In this embodiment, the predicted energy consumption refers to energy consumption predicted by corresponding standardized information.
The beneficial effects of the technical scheme are as follows: the effectiveness of energy consumption prediction is guaranteed by carrying out information standardization on the current time operation information of each power device, the efficiency of energy consumption prediction is improved, and convenience is provided for subsequent determination of adjustable working conditions.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit, which compares the current comprehensive energy consumption with the allowable maximum energy consumption, determines the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal operation principle, and comprises the following steps:
superposing the current energy consumption of each power device to obtain the current comprehensive energy consumption, and obtaining the current allowable maximum energy consumption based on the preset energy consumption condition of each power device;
comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and if the current comprehensive energy consumption is smaller than or equal to the allowable maximum energy consumption, controlling each electric power device to continue to operate according to the current working condition;
if the current comprehensive energy consumption exceeds the allowable maximum energy consumption, the current working condition of each power device is adjusted;
and acquiring a set of to-be-adjusted working conditions of each electric device in the building electric power unit, which is consistent with the corresponding normal operation condition at the current moment, based on the normal operation principle, selecting from the set of to-be-adjusted working conditions of the corresponding electric devices based on the energy consumption optimal principle, and determining the adjustable working condition of each electric device.
In this embodiment, the preset energy consumption condition of each electric device refers to the maximum allowable energy consumption of each electric device under the current operating condition, and is determined by the device condition of each electric device and the total energy consumption condition of the electric power unit.
In this embodiment, the set of conditions to be adjusted includes all of the adjustable conditions for each electrical device.
The beneficial effects of the technical scheme are as follows: the comparison of the comprehensive energy consumption and the allowable maximum energy consumption is used for determining whether the working condition adjustment is needed, so that the efficiency of energy efficiency optimization is improved, the adjustable working condition of each power device is determined through the normal operation principle and the energy consumption optimization principle, and the energy efficiency optimization is realized while each power device is in normal operation.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization method for a building electric power unit, which is based on an internet of things control box to control corresponding electric power equipment to perform working condition conversion according to the adjustable working condition, and realizes energy efficiency optimization, and comprises the following steps:
comparing the current working condition of each power device with the corresponding adjustable working condition to obtain an adjustment strategy;
and carrying out working condition conversion on the working condition of each power device according to the adjustment strategy through the control box of the Internet of things, so as to realize energy efficiency optimization.
In this embodiment, the adjustment strategy includes an adjustment process for each electrical device by which the operating condition of each electrical device can be made consistent with the adjustable operating condition.
The beneficial effects of the technical scheme are as follows: the accuracy of the working condition conversion is improved by comparing the current working condition with the adjustable working condition to obtain the adjustment strategy, and the working condition of the building electric unit is adjusted by the control box of the Internet of things, so that the working condition adjustment process is simple and convenient.
The embodiment of the invention provides a full-working-condition energy consumption prediction and energy efficiency optimization device of a building electric power unit, which comprises the following components:
and a data acquisition module: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
model construction module: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
the working condition determining module: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
and the working condition adjusting module is used for: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
The beneficial effects of the technical scheme are as follows: the method comprises the steps of obtaining a historical operation log, carrying out energy consumption association analysis on all-condition operation data in the historical operation log, constructing an energy consumption prediction model, guaranteeing the accuracy of energy consumption prediction, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, determining the adjustable condition of each power device according to the energy consumption optimal principle and the normal operation principle, adjusting the condition through an Internet of things control box, controlling the condition, and guaranteeing that each power device in the power unit effectively achieves energy consumption optimization under the normal operation condition.
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 (8)
1. The full-working-condition energy consumption prediction and energy efficiency optimization method for the building electric power unit is characterized by comprising the following steps of:
step 1: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
step 2: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
step 3: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
step 4: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
2. The method for predicting and optimizing all-condition energy consumption and energy efficiency of a building power unit according to claim 1, wherein obtaining all-condition operation data of each power device in the building power unit from the historical operation log comprises:
based on the all-condition state of each power equipment, extracting data from the historical operation log;
and determining the operation data of each power equipment under different working conditions based on the extraction result to obtain the full-working-condition operation data.
3. The method for predicting energy consumption and optimizing energy efficiency under all working conditions of a building electric power unit according to claim 1, wherein the energy consumption correlation analysis is performed on the all working condition operation data, and determining energy consumption combinations of different electric power devices in the building electric power unit under different operation states at the same time comprises the following steps:
according to the full-working-condition operation data of each power device, determining a first working-condition array of the same power device at different moments, and performing energy consumption conversion on the first working-condition array to obtain a first energy consumption array;
performing time alignment processing on the first energy consumption arrays of different power equipment, constructing to obtain a first energy consumption matrix, and respectively extracting each column in the first energy consumption matrix as an initial combination;
calculating a first energy consumption value of each initial array, simultaneously, carrying out superposition classification on all initial arrays, and preprocessing all first energy consumption values under corresponding classification by combining the combination superposition degree corresponding to superposition classification to obtain a second energy consumption value, wherein the superposition classification refers to the consistency of operation setting parameters of the power equipment under different moments;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing a corresponding second energy consumption value; />Representing the maximum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the minimum value of all the first energy consumption values in the corresponding coincidence classification; />Representing the i1 first energy consumption value in the corresponding coincidence classification; n0 represents the initial combination number in the corresponding coincidence classification;/>representing the total number of initial combinations; />Representing the corresponding combination overlap ratio;
determining a standard energy consumption variance based on the second energy consumption value and all the first energy consumption values under the same coincidence classificationAnd combining standard loss factors corresponding to operation setting parameters under the same coincidence classification, and configuring a first energy consumption factor for each power equipment under the same coincidence classification to obtain an energy consumption combination under the same coincidence classification;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>The total number of rows of the first energy consumption matrix is represented and is consistent with the total number of elements contained in each column of the matrix; />Representing a standard loss factor of the j1 st power equipment in the same coincidence classification; />A first energy consumption factor representing the j1 st power device in the same coincidence classification; />Representing the energy consumption value of the (1) th power equipment in the same coincidence classification based on the (1) th initial combination;
according to the operation setting array and the first energy consumption array of the non-coincident categorization, configuring a second energy consumption factor for each power equipment under the non-coincident categorization to obtain an energy consumption combination under the non-coincident categorization;
wherein (1)>Representing standard loss factors of corresponding power equipment under non-coincident classification; />A second loss factor representing the corresponding power device under the non-coincident categorization; />Representing the corresponding energy consumption variance under non-coincident categorization; />Representing the actual loss value of the j2 power equipment in the non-coincident classification; />And the standard loss value of the j2 power equipment in the non-coincident classification is represented.
4. The method for predicting energy consumption and optimizing energy efficiency under all working conditions of a building electric power unit according to claim 3, wherein in step 2, constructing an energy consumption prediction model comprises the following steps:
inputting all the energy consumption combinations and the first operation setting states under the same coincidence classification into the neural network model for first main training, and simultaneously inputting the initial combinations consistent with all the coincidence classification into the neural network model for first auxiliary training;
inputting all the energy consumption combinations under the non-coincident classification and the second operation setting state into the neural network model for second main training, and simultaneously inputting the initial combination consistent with all the non-coincident classification into the neural network model for second auxiliary training;
and obtaining an energy consumption prediction model based on the training result.
5. The method for predicting and optimizing energy consumption under all conditions of a building electric power unit according to claim 1, wherein the method for obtaining the operation information of each electric power device in the building electric power unit at the current moment, and sequentially inputting the operation information into the energy consumption prediction model to predict the current energy consumption of each electric power device comprises the following steps:
real-time monitoring is carried out on the real-time operation state of each electric power device in the building electric power unit, and the operation information of each electric power device at the current moment is obtained based on the real-time monitoring result;
and carrying out information standardization on the running information at the current moment according to the input standard of the energy consumption prediction model, inputting the standardized information into the energy consumption prediction model to obtain the predicted energy consumption of each power device, and taking the predicted energy consumption as the current energy consumption of the corresponding power device.
6. The method for predicting and optimizing energy consumption under all operating conditions of a building electric power unit according to claim 1, wherein comparing the current integrated energy consumption with the allowable maximum energy consumption and determining the adjustable operating condition of each electric power device according to the energy consumption optimization principle and the normal operation principle comprises:
superposing the current energy consumption of each power device to obtain the current comprehensive energy consumption, and obtaining the current allowable maximum energy consumption based on the preset energy consumption condition of each power device;
comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and if the current comprehensive energy consumption is smaller than or equal to the allowable maximum energy consumption, controlling each electric power device to continue to operate according to the current working condition;
if the current comprehensive energy consumption exceeds the allowable maximum energy consumption, the current working condition of each power device is adjusted;
and acquiring a set of to-be-adjusted working conditions of each electric device in the building electric power unit, which is consistent with the corresponding normal operation condition at the current moment, based on the normal operation principle, selecting from the set of to-be-adjusted working conditions of the corresponding electric devices based on the energy consumption optimal principle, and determining the adjustable working condition of each electric device.
7. The method for predicting all-condition energy consumption and optimizing energy efficiency of a building electric power unit according to claim 1, wherein the method for optimizing energy efficiency is characterized by controlling corresponding electric power equipment to perform condition conversion according to the adjustable condition based on an internet of things control box, and comprises the following steps:
comparing the current working condition of each power device with the corresponding adjustable working condition to obtain an adjustment strategy;
and carrying out working condition conversion on the working condition of each power device according to the adjustment strategy through the control box of the Internet of things, so as to realize energy efficiency optimization.
8. All-condition energy consumption prediction and energy efficiency optimization device of building electric power unit, characterized by comprising:
and a data acquisition module: acquiring a historical operation log of a building electric power unit, and acquiring all-condition operation data of each electric power device in the building electric power unit from the historical operation log;
model construction module: performing energy consumption association analysis on the all-condition operation data, determining energy consumption combinations of different power equipment in the building power unit in different operation states at the same time, and constructing an energy consumption prediction model;
the working condition determining module: acquiring running information of each electric power device in the building electric power unit at the current moment, sequentially inputting the running information into the energy consumption prediction model, predicting the current energy consumption of each electric power device, comparing the current comprehensive energy consumption with the allowable maximum energy consumption, and determining the adjustable working condition of each electric power device according to the energy consumption optimal principle and the normal running principle;
and the working condition adjusting module is used for: and controlling corresponding power equipment to perform working condition conversion according to the adjustable working conditions based on the control box of the Internet of things, so as to realize energy efficiency optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311244763.6A CN117541438A (en) | 2023-09-26 | 2023-09-26 | Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311244763.6A CN117541438A (en) | 2023-09-26 | 2023-09-26 | Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117541438A true CN117541438A (en) | 2024-02-09 |
Family
ID=89784863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311244763.6A Withdrawn CN117541438A (en) | 2023-09-26 | 2023-09-26 | Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541438A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014318A (en) * | 2024-04-09 | 2024-05-10 | 国网浙江省电力有限公司宁波供电公司 | Dynamic management method and device for electric power energy demand based on multi-energy system |
| CN118094232A (en) * | 2024-04-25 | 2024-05-28 | 广东欢联电子科技有限公司 | Dynamic monitoring production energy consumption control system and method |
-
2023
- 2023-09-26 CN CN202311244763.6A patent/CN117541438A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014318A (en) * | 2024-04-09 | 2024-05-10 | 国网浙江省电力有限公司宁波供电公司 | Dynamic management method and device for electric power energy demand based on multi-energy system |
| CN118094232A (en) * | 2024-04-25 | 2024-05-28 | 广东欢联电子科技有限公司 | Dynamic monitoring production energy consumption control system and method |
| CN118094232B (en) * | 2024-04-25 | 2024-07-19 | 广东欢联电子科技有限公司 | Dynamic monitoring production energy consumption control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110392515B (en) | Historical data-based cold and heat source machine room energy-saving control method and system | |
| EP3483517B1 (en) | System and method for predicting load of and controlling subway heating, ventilation, and air conditioning system | |
| CN112577161B (en) | Air conditioner energy consumption model training method and air conditioner system control method | |
| CN110410942B (en) | Energy-saving optimization control method and system for cold and heat source machine room | |
| CN107143981B (en) | A kind of controlling system of central air conditioner and method | |
| CN110458340B (en) | Building air conditioner cold load autoregressive prediction method based on mode classification | |
| CN117541438A (en) | Full-working-condition energy consumption prediction and energy efficiency optimization method for building electric power unit | |
| CN102721156A (en) | Central air-conditioning self-optimization intelligent fuzzy control device and control method thereof | |
| EP2881583A1 (en) | Method and device for optimizing operational control of compressors in multi-couple unit air-conditioning system | |
| CN114383299B (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN112097365A (en) | Air conditioner fault detection and identification method and device based on prediction and classification model | |
| CN108491580A (en) | A kind of equipment fault diagnosis apparatus and system | |
| EP3996178B1 (en) | Optimization of thermal management control of lithium-ion battery system | |
| CN106885350A (en) | A kind of air conditioner energy conservation control system | |
| CN111664550A (en) | Energy efficiency optimization method and system based on prediction model and optimization algorithm | |
| CN112614013A (en) | Multi-energy coupling scheduling system and method for multi-station fusion type distributed energy station | |
| CN115183421A (en) | Energy-saving control method, system and equipment for central air-conditioning water cooling unit | |
| CN110895029A (en) | Building load prediction method based on temperature of chilled water | |
| CN111594984A (en) | Central air conditioner full-link coordination control system and control method | |
| CN115081220A (en) | Adjusting method and system for high-energy-efficiency central air-conditioning system | |
| Deng et al. | Optimal control of chilled water system with ensemble learning and cloud edge terminal implementation | |
| CN102679649B (en) | Energy conservation control device and energy conservation control method of refrigerating system | |
| CN114609978A (en) | Flat control method and control system for air cooling data center | |
| CN114636212B (en) | GRNN-based running control method for multiple water chilling unit systems | |
| CN113757922A (en) | Deep learning-based air conditioning system energy-saving control method, device and equipment and computer medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240209 |
|
| WW01 | Invention patent application withdrawn after publication |