CN111473471A - Multi-linkage energy consumption metering method and system - Google Patents
Multi-linkage energy consumption metering method and system Download PDFInfo
- Publication number
- CN111473471A CN111473471A CN202010213975.8A CN202010213975A CN111473471A CN 111473471 A CN111473471 A CN 111473471A CN 202010213975 A CN202010213975 A CN 202010213975A CN 111473471 A CN111473471 A CN 111473471A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- data
- neural network
- network model
- consumption data
- 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.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 210
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000003062 neural network model Methods 0.000 claims abstract description 111
- 238000010977 unit operation Methods 0.000 claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 abstract description 17
- 238000004378 air conditioning Methods 0.000 description 13
- 238000012937 correction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
- F24F11/47—Responding to energy costs
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/32—Responding to malfunctions or emergencies
- F24F11/38—Failure diagnosis
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
- F24F11/58—Remote control using Internet communication
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
- F24F11/77—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity by controlling the speed of ventilators
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
- F24F11/86—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling compressors within refrigeration or heat pump circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/88—Electrical aspects, e.g. circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/546—Message passing systems or structures, e.g. queues
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/547—Messaging middleware
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Human Computer Interaction (AREA)
- Fluid Mechanics (AREA)
- Thermal Sciences (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a multi-connected energy consumption metering method and a multi-connected energy consumption metering system. Wherein, the method comprises the following steps: receiving unit operation data uploaded by the multi-split air conditioner; calculating in real time according to the unit operation data to obtain first energy consumption data; and correcting the first energy consumption data by using a neural network model to obtain corrected energy consumption data. According to the method, the energy consumption of the multi-connected unit can be calculated on line in real time by receiving the unit operation data of the multi-connected unit, the calculated multi-connected unit energy consumption is corrected by using the neural network model obtained based on big data training, accurate measurement of the multi-connected unit energy consumption is realized, comprehensive measurement and statistics of a large number of multi-connected unit energy consumption are realized, a large amount of manpower is not required to be consumed, and the electricity meter is used for actual measurement, so that the method is convenient, accurate and efficient.
Description
Technical Field
The invention relates to the technical field of multi-online machines, in particular to a multi-online machine energy consumption metering method and system.
Background
The energy efficiency ratio (COP) of the air conditioner is the ratio of the refrigerating capacity of the air conditioner to the input power of the air conditioner, reflects the energy-saving level of the air conditioner, and aims to save energy and develop energy-saving and environment-friendly economy.
In recent years, the market influence of multi-online systems is getting larger and larger, the occupancy is improved year by year, and each manufacturer has high nominal energy efficiency, but the electricity utilization condition of the multi-online systems in the nationwide range cannot be directly obtained in practice, and the electricity meters need to be manually used for testing in person. The method for manually collecting data consumes a large amount of manpower and cost, has low efficiency, and cannot realize large data analysis.
The electric quantity and the refrigerating capacity are difficult to calculate through conventional parameters returned by the conventional air conditioner, and the calculating accuracy rate cannot meet the requirement at present. Different from a one-by-one household air conditioner, the multi-split air conditioner is a multi-element nonlinear system with a very complex state equation, and the system is difficult to be completely modeled by an accurate mathematical model.
Aiming at the problem of low accuracy of multi-split energy consumption measurement in the prior art, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a multi-linkage energy consumption metering method and system, and aims to solve the problem of low accuracy of multi-linkage energy consumption metering in the prior art.
In order to solve the technical problem, an embodiment of the present invention provides a method for measuring energy consumption of multiple servers, where the method is executed by a server and includes: receiving unit operation data uploaded by the multi-split air conditioner; calculating in real time according to the unit operation data to obtain first energy consumption data; and correcting the first energy consumption data by using a neural network model to obtain corrected energy consumption data.
Optionally, the obtaining of the first energy consumption data by real-time calculation according to the unit operation data includes: calculating to obtain real-time power and electric quantity according to the electricity utilization data in the unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in the unit operation data; calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio; wherein the first energy consumption data comprises: the electric quantity, the refrigerating capacity and the energy efficiency ratio.
Optionally, before obtaining the first energy consumption data by real-time calculation according to the unit operation data, the method further includes: acquiring the model information of the multi-split air conditioner; and determining an energy consumption algorithm corresponding to the model information according to prestored configuration information so as to calculate the first energy consumption data according to the energy consumption algorithm.
Optionally, the modifying the first energy consumption data by using a neural network model to obtain modified energy consumption data includes: and taking the first energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
Optionally, before the modifying the first energy consumption data by using the neural network model, the method further includes: building a neural network and initializing parameters of the neural network; obtaining sample data, wherein the sample data comprises: theoretical energy consumption data obtained by calculation aiming at least two multi-connected lines and corresponding actual measured real data; taking the theoretical energy consumption data as the input of the neural network to obtain the output of the neural network; judging whether the error between the output of the neural network and the real data is within a first preset error range or not; if so, determining that the training of the neural network model is finished; and if not, adjusting the parameters of the neural network, and returning to execute the step of taking the theoretical energy consumption data as the input of the neural network.
Optionally, after it is determined that training of the neural network model is completed, the method further includes: selecting updating data used for updating a model from the first energy consumption data calculated in real time for each multi-split air conditioner, and acquiring real data corresponding to the updating data; and updating the neural network model according to the updated data and the corresponding real data.
Optionally, after it is determined that training of the neural network model is completed, the method further includes: and sending the trained neural network model to each multi-split telephone so that each multi-split telephone stores the trained neural network model.
Optionally, after sending the trained neural network model to each of the multiple online units, the method further includes: receiving second energy consumption data uploaded by the multi-split air conditioner according to a preset period, wherein the second energy consumption data is energy consumption data obtained after a neural network model stored locally by the multi-split air conditioner is corrected for the last time; judging whether the error between the second energy consumption data and the corrected energy consumption data obtained by the server based on the same unit operation data and the current neural network model is within a second preset error range or not; and if not, sending the current neural network model to the multi-split air conditioner for local model updating.
Optionally, the method further includes: if the server side is detected to have the invalid session, determining that the server to which the session belongs has a fault, and transferring the application or service on the fault server to any target server in the server side so as to enable the target server to continuously execute the current task.
Optionally, after receiving the unit operation data uploaded by the multi-split air conditioner, the method further includes: extracting effective data in the unit operation data according to a preset rule; and storing the valid data into a message middleware in a queue form in real time, wherein the valid period of the data stored in the message middleware is preset duration.
Optionally, the method further includes: and at least storing the unit operation data, the first energy consumption data, the modified energy consumption data and the neural network model into a non-relational database.
The embodiment of the invention also provides a multi-split energy consumption metering method, which is executed by the multi-split machine, and comprises the following steps: acquiring unit operation data; calculating in real time according to the unit operation data to obtain energy consumption data; and correcting the calculated energy consumption data by using the locally stored neural network model to obtain the corrected energy consumption data.
Optionally, the method further includes: and if the preset period is reached, uploading the energy consumption data after the latest correction to a server side so that the server side judges whether the neural network model stored locally in the multi-split air conditioner needs to be updated or not.
Optionally, after the last modified energy consumption data is uploaded to the server, the method further includes: detecting whether a model updating signal is received; and if so, replacing the locally stored original neural network model with the received new neural network model.
Optionally, the obtaining of the energy consumption data by real-time calculation according to the unit operation data includes: calculating to obtain real-time power and electric quantity according to the electricity utilization data in the unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in the unit operation data; calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio; wherein the energy consumption data comprises: the electric quantity, the refrigerating capacity and the energy efficiency ratio.
Optionally, the modifying the calculated energy consumption data by using the locally stored neural network model to obtain modified energy consumption data includes: and taking the calculated energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
The embodiment of the invention also provides a multi-split energy consumption metering system, which comprises: the system comprises a server and at least two multi-connected lines; the server is used for receiving the unit operation data uploaded by the multi-online unit; calculating in real time according to the unit operation data to obtain first energy consumption data; and correcting the first energy consumption data by using a neural network model to obtain corrected energy consumption data.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method according to the embodiments of the present invention.
By applying the technical scheme of the invention, the energy consumption of the multi-split air conditioning unit can be calculated on line in real time by receiving the unit operation data of the multi-split air conditioning unit, the calculated multi-split air conditioning unit energy consumption is corrected by utilizing the neural network model obtained based on big data training, the accurate measurement of the energy consumption of the multi-split air conditioning unit is realized, the comprehensive measurement and statistics of a large amount of multi-split air conditioning unit energy consumption are realized, a large amount of manpower is not required to be consumed, the electric meter is used for actual measurement, and the.
Drawings
Fig. 1 is a flowchart of a multi-split energy consumption metering method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a neural network model training process according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a calculation process of the local and server sides according to an embodiment of the present invention;
FIG. 4 is an overall architecture diagram of a multi-couple energy consumption meter according to an embodiment of the present invention;
fig. 5 is a flowchart of a multi-split energy consumption metering method according to a second embodiment of the present invention;
fig. 6 is a block diagram of a multi-split energy consumption metering device according to a third embodiment of the present invention;
fig. 7 is a block diagram of a multi-split energy consumption metering device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment provides a multi-online energy consumption metering method, which is executed by a server and can accurately meter the energy consumption of the multi-online. Fig. 1 is a flowchart of a multi-energy consumption metering method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
and S101, receiving unit operation data uploaded by the multi-split air conditioner.
And S102, calculating in real time according to the unit operation data to obtain first energy consumption data. Wherein the first energy consumption data comprises: electrical capacity, refrigeration capacity, and energy efficiency ratio (i.e., COP).
S103, modifying the first energy consumption data by using the neural network model to obtain modified energy consumption data.
Specifically, the step of correcting the first energy consumption data by using the neural network model to obtain the corrected energy consumption data includes: and taking the first energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the modified energy consumption data. The neural network model in this embodiment is an optimized model trained with the support of the mass data set, and the error between the theoretical predicted value (i.e., the corrected energy consumption data) output by the model and the measured value of the electricity meter is within an allowable error range, for example, 5%.
The online energy consumption real-time calculation multi-split air conditioning unit is characterized in that the unit operation data of the multi-split air conditioning unit is received, the energy consumption of the multi-split air conditioning unit can be calculated on line in real time, the calculated multi-split air conditioning unit energy consumption is corrected by utilizing a neural network model obtained based on big data training, accurate measurement of the energy consumption of the multi-split air conditioning unit is realized, comprehensive measurement and statistics of a large number of multi-split air conditioning unit energy consumption are realized, a large amount of manpower is not required to.
Specifically, the obtaining of the first energy consumption data by real-time calculation according to the unit operation data includes: calculating to obtain real-time power and electric quantity according to power utilization data in unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in unit operation data; and calculating according to the real-time power and the refrigerating capacity to obtain the energy efficiency ratio.
The first energy consumption data are obtained through calculation according to existing parameters acquired by the multi-connected unit. The unit operation data is the full-condition data of the multi-split air conditioner, such as the operation frequency of a compressor, the operation frequency of a fan, high and low voltages, voltage, current, the opening degree of an expansion valve, temperature and the like. The electricity consumption data includes: the compressor comprises a compressor, a current, a voltage, high and low pressure parameters and the like, wherein the high and low pressure parameters refer to pressures before and after compression of the compressor, specifically, the pressure before compression of the compressor is low pressure, and the pressure after compression of the compressor is high pressure. Fitting is carried out based on current, voltage, high-voltage and low-voltage parameters and the like to obtain real-time power of the multi-split air conditioner, and the power is integrated with time to obtain electric quantity. The specifying the location includes: compressor inlet and outlet and evaporimeter inlet and outlet, thermophysical properties data includes: temperature, pressure, density, enthalpy and entropy. The method specifically comprises the steps of detecting related numerical values through a temperature sensor and a pressure sensor on the multi-split air conditioner, calculating to obtain thermophysical property data of a specified position, and then obtaining refrigerating capacity through enthalpy difference of key points. The calculation of power, the calculation of thermophysical data and the calculation of refrigerating capacity through enthalpy difference all adopt the existing calculation formulas, which is not described in detail in this embodiment.
Considering that different machine types of the multi-split air conditioner have different energy consumption algorithms, the embodiment writes all known machine type information of the multi-split air conditioner and the corresponding energy consumption algorithms into the configuration file in advance, only needs to read the configuration file before operation, can dynamically bind the machine type and the corresponding algorithm during operation, and calculates the first energy consumption data by using a proper algorithm. Specifically, before obtaining the first energy consumption data by real-time calculation according to the unit operation data, the method further includes: acquiring model information of the multi-split air conditioner; and determining an energy consumption algorithm corresponding to the model information according to the pre-stored configuration information so as to calculate first energy consumption data according to the energy consumption algorithm.
Therefore, the operation data of the multi-split air conditioning unit is obtained, the data is extracted and analyzed, and the power, the electric quantity, the refrigerating capacity and the COP corresponding to various types of multi-split air conditioning units can be calculated according to the analyzed data and the matched energy consumption algorithm.
In an alternative embodiment, before the first energy consumption data is modified by the neural network model, the sample data is required to be trained to obtain the neural network model. Referring to fig. 2, the training process includes: building a neural network and initializing parameters of the neural network; acquiring sample data, wherein the sample data comprises: theoretical energy consumption data obtained by calculation aiming at least two multi-connected lines and corresponding actual measured real data; taking theoretical energy consumption data as input of a neural network to obtain output of the neural network; judging whether the error between the output of the neural network and the real data is within a first preset error range or not; if so, determining that the training of the neural network model is finished, wherein the model can be used for subsequent energy consumption data correction; if not, adjusting parameters of the neural network, returning to the step of executing the input of taking the theoretical energy consumption data as the neural network, and continuing to train by using the sample data. The actual data (may also be referred to as measured data) includes: the electric quantity, the refrigerating capacity and the COP can be directly measured through an ammeter, the refrigerating capacity can be reflected through indoor enthalpy change (obtained through temperature and pressure), and the COP can be calculated through the electric quantity and the refrigerating capacity.
Specifically, a complex nonlinear system of a BP neural network expression multi-connected line can be established, the system is regarded as a black box, a neural network model is trained by adopting theories such as a Stochastic Gradient Descent (SGD) method and a Back Propagation (BP) method and the like for nonlinear regression, the fitting degree is higher than that of a least square method, and the error is smaller.
In the embodiment, the neural network is built, the calculated theoretical value is used as the input of the neural network, the actual value measured actually is used as the label to perform supervised learning, the reliable neural network model is obtained, and the real-time calculated energy consumption data is corrected by using the neural network model, so that the accuracy of energy consumption measurement is improved.
In order to further ensure the accuracy of energy consumption measurement, the trained neural network model can be updated in time. Specifically, after it is determined that training of the neural network model is completed, the method further includes: selecting update data for updating the model from the first energy consumption data calculated in real time for each multi-split air conditioner, and acquiring real data corresponding to the update data; and updating the neural network model according to the updated data and the corresponding real data. The process of updating the model is similar to the process of training the model, the updated data is used as the input of the neural network model, whether the error between the output of the neural network model and the corresponding real data is within a first preset error range or not is judged, if yes, updating is not needed, and if not, the parameters of the neural network are adjusted, and training is continued.
According to the embodiment, the corresponding real data is obtained only aiming at the selected updating data, not aiming at all energy consumption data, and the model can be updated in time without consuming too much manpower.
In order to relieve the pressure of the server, after the neural network model of the server is complete, the neural network model trained by the server can be synchronously updated to the local of the multi-split air conditioner, so that the multi-split air conditioner has the capability of correcting parameters. If the network is not connected, the multi-online local computing can replace the computing of the remote server, so that the accurate energy consumption prediction and metering are realized, the local metering efficiency is high, and the user experience is good.
Specifically, after it is determined that training of the neural network model is completed, the method further includes: and sending the neural network model obtained by training to each multi-split air conditioner so that each multi-split air conditioner stores the neural network model obtained by training.
Considering that the neural network model of the server can be updated in real time according to data, the difference of the tuning errors of the local multi-online system and the server can occur, if the error is too large, the neural network model of the server is sent to the multi-online system to update the local model in time, and the accuracy and reliability of a local correction result are ensured. Specifically, referring to fig. 3, after the trained neural network model is sent to each multi-split air conditioner, the method further includes: receiving second energy consumption data uploaded by the multi-online unit according to a preset period, wherein the second energy consumption data is energy consumption data obtained after a neural network model stored locally by the multi-online unit is corrected for the last time; judging whether the error between the second energy consumption data and the corrected energy consumption data obtained by the server based on the same unit operation data and the current neural network model is within a second preset error range or not; and if not, sending the current neural network model to the multi-connected line for local model updating.
The preset period refers to a preset sampling period, and when the period arrives, data needs to be sampled to judge whether the neural network model stored locally in the multi-split air conditioner needs to be updated or not. The transmission of the neural network model can be realized according to the multi-split communication address. Preferably, the second predetermined error range is smaller than the first predetermined error range.
According to the embodiment, the correction results of the local multi-split air conditioner and the server are sampled and compared at regular time, the local neural network model of the multi-split air conditioner is updated in time, the accuracy and the reliability of the local correction results are guaranteed, a stable system with closed-loop feedback is realized, and the system is stable and reliable.
The server of this embodiment may include at least one server, that is, a server cluster is formed, and each server may provide the same service. In an optional implementation manner, if it is detected that a failed session exists at a server, it is determined that a server to which the session belongs is failed, and an application or service on the failed server is transferred to any target server in the server, so that the target server continues to execute a current task. In practical use, if a server is unexpectedly suspended, a session cannot be maintained, so that the session fails over time, the whole cluster can quickly detect the failure and immediately automatically transfer an application or service on the server to other servers, and the failover is realized through a session mechanism. In formal computing, the cluster can be expanded online (i.e. servers are added) or the parallelism of the program can be adjusted to optimize performance. Meanwhile, in order to enable the cluster to have better load balance, an intelligent main server election algorithm is used, and if a certain working node is down, the node is automatically tried to be restarted. In this embodiment, distributed computing is implemented by using a server cluster, which may expand the capacity and improve the performance and the computing efficiency.
In addition, the embodiment combines big data to realize the accurate measurement of the energy consumption of the multi-split air conditioner, and the persistence of the big data is realized through the following two points:
(1) message middleware
After receiving the unit operation data uploaded by the multi-split air conditioner, the method further comprises the following steps: extracting effective data in the unit operation data according to a preset rule; and storing the valid data into the message middleware in a queue form in real time, wherein the valid period of the data stored in the message middleware is preset duration.
Since the multi-split-line real-time uploads the data to the server, the data uploaded each time may have duplicate data, and therefore valid data in the data can be extracted according to a preset rule for storage, so as to prevent unnecessary storage space occupation, for example, the preset rule may be that data is extracted once at intervals of a preset time. The preset time duration can be set according to actual requirements, for example, 7 days, 30 days, and the like, that is, valid data of the last 7 days is stored in the message middleware. The effective data is stored in a queue form, and the corresponding effective data can be read in combination with a publish-subscribe mode when in subsequent needs, so that the data can be recycled. By combining the queue mode and the publish-subscribe mode, the multi-online data in a configurable time period can be reused, reusability is improved, high throughput can be guaranteed on the premise of low delay, and performance cannot be affected due to persistent massive data.
(2) Non-relational database
The method further comprises the following steps: and at least storing the unit operation data, the first energy consumption data, the corrected energy consumption data and the neural network model into a non-relational database. All information and data in the process of multi-online energy consumption metering can be stored in a non-relational database.
The data is persisted by adopting the message middleware and the non-relational database, so that the coupling degree of a data storage party and a data use party is lower, the working efficiency is improved, and the time and labor cost for maintaining the system in the future are reduced.
Referring to fig. 4, as an overall architecture diagram, a server may obtain real-time data of all operating conditions of a multi-split unit across the country through a multi-split communication module (in a wireless or wired manner), persist the data into a message middleware, obtain energy consumption data through calculation using a big data stream type calculation platform, and correct the calculated energy consumption data through a neural network model, thereby achieving accurate energy consumption metering. It should be noted that this example is only for better illustrating the present application and should not be construed as an undue limitation to the present application.
Example two
The embodiment provides a multi-split energy consumption metering method, which is executed by multi-split machines and can accurately meter the energy consumption of the multi-split machines. The same or corresponding terms as those of the above-described embodiments are explained, and the description of the present embodiment is omitted.
Fig. 5 is a flowchart of a multi-energy consumption metering method according to a second embodiment of the present invention, and as shown in fig. 5, the method includes the following steps:
s501, acquiring unit operation data.
And S502, calculating in real time according to the unit operation data to obtain energy consumption data.
And S503, correcting the calculated energy consumption data by using the locally stored neural network model to obtain the corrected energy consumption data.
Specifically, the method for correcting the calculated energy consumption data by using the locally stored neural network model to obtain the corrected energy consumption data includes: and taking the calculated energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
In the embodiment, the multi-split air conditioner can calculate the energy consumption of the multi-split air conditioner in real time on line by acquiring the running data of the unit, and the calculated energy consumption is corrected by using the neural network model stored locally, so that the accurate measurement of the energy consumption of the multi-split air conditioner is realized, the local measurement efficiency is high, and the user experience is good.
And if the preset period is reached, uploading the energy consumption data after the last correction to the server side so that the server side can judge whether the neural network model stored locally in the multi-split air conditioner needs to be updated or not.
Further, after the last modified energy consumption data is uploaded to the server, the method further includes: detecting whether a model updating signal is received; and if so, replacing the locally stored original neural network model with the received new neural network model. And the local model is updated in time, and the accuracy and reliability of the local correction result are ensured.
Specifically, the energy consumption data is obtained by real-time calculation according to the unit operation data, and the method comprises the following steps: calculating to obtain real-time power and electric quantity according to power utilization data in unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in unit operation data; calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio; wherein the energy consumption data comprises: electric quantity, refrigerating capacity and energy efficiency ratio.
EXAMPLE III
Based on the same inventive concept, the embodiment provides a multi-connected energy consumption metering device, which is applied to a server, and can be used for implementing the multi-connected energy consumption metering method described in the first embodiment, and the device can be implemented by software and/or hardware.
Fig. 6 is a block diagram of a multi-connected energy consumption metering device according to a third embodiment of the present invention, and as shown in fig. 6, the device includes:
the receiving module 61 is used for receiving the unit operation data uploaded by the multi-online unit;
the first calculation module 62 is configured to calculate in real time according to the unit operation data to obtain first energy consumption data;
and a first correcting module 63, configured to correct the first energy consumption data by using a neural network model, so as to obtain corrected energy consumption data.
Optionally, the first calculating module 62 is specifically configured to: calculating to obtain real-time power and electric quantity according to the electricity utilization data in the unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in the unit operation data; calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio; wherein the first energy consumption data comprises: the electric quantity, the refrigerating capacity and the energy efficiency ratio.
Optionally, the apparatus further comprises:
the information acquisition module is used for acquiring the model information of the multi-split air conditioner before first energy consumption data is obtained through real-time calculation according to the unit operation data;
and the determining module is used for determining an energy consumption algorithm corresponding to the model information according to prestored configuration information so as to calculate the first energy consumption data according to the energy consumption algorithm.
Optionally, the first modification module 63 is specifically configured to: and taking the first energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
Optionally, the apparatus further comprises:
the building module is used for building a neural network before the first energy consumption data is corrected by using a neural network model, and initializing parameters of the neural network;
a data obtaining module, configured to obtain sample data, where the sample data includes: theoretical energy consumption data obtained by calculation aiming at least two multi-connected lines and corresponding actual measured real data;
the input module is used for taking the theoretical energy consumption data as the input of the neural network to obtain the output of the neural network;
the first judgment module is used for judging whether the error between the output of the neural network and the real data is within a first preset error range or not;
the processing module is used for determining that the training of the neural network model is finished if the neural network model is in the normal state; and if not, adjusting the parameters of the neural network, and returning to execute the step of taking the theoretical energy consumption data as the input of the neural network.
Optionally, the apparatus further comprises: the first updating module is used for selecting updating data used for updating the model from the first energy consumption data calculated in real time aiming at each multi-split system after the training of the neural network model is determined to be completed, and acquiring real data corresponding to the updating data; and updating the neural network model according to the updated data and the corresponding real data.
Optionally, the apparatus further comprises: and the sending module is used for sending the trained neural network model to each multi-split telephone after the training of the neural network model is determined to be completed, so that each multi-split telephone stores the trained neural network model.
Optionally, the receiving module 61 is further configured to receive second energy consumption data uploaded by the multi-split air conditioner according to a preset period after the trained neural network model is sent to each multi-split air conditioner, where the second energy consumption data is energy consumption data obtained after the neural network model stored locally in the multi-split air conditioner is modified last time;
the device further comprises: the second judging module is used for judging whether the error between the second energy consumption data and the corrected energy consumption data obtained by the server based on the same unit operation data and the current neural network model is within a second preset error range or not;
and the sending module is further used for sending the current neural network model to the multi-split air conditioner for local model updating if the neural network model is not the current neural network model.
Optionally, the apparatus further comprises: and the failure processing module is used for determining that the server to which the session belongs fails if the server is detected to have a failed session, and transferring the application or service on the failed server to any target server in the server so that the target server continues to execute the current task.
Optionally, the apparatus further comprises: the first storage module is used for extracting effective data in the unit operation data according to a preset rule after receiving the unit operation data uploaded by the multi-online unit; and storing the effective data into a message middleware in a queue form in real time, wherein the effective period of the data stored in the message middleware is preset duration.
Optionally, the apparatus further comprises: and the second storage module is used for storing at least the unit operation data, the first energy consumption data, the corrected energy consumption data and the neural network model into a non-relational database.
The device can execute the method provided by the first embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided in the first embodiment of the present invention.
Example four
Based on the same inventive concept, this embodiment provides a multi-split energy consumption metering device, which is applied to a multi-split air conditioner, and can be used to implement the multi-split energy consumption metering method described in the second embodiment above, and the device can be implemented by software and/or hardware.
Fig. 7 is a block diagram of a multi-couple energy consumption metering device according to a fourth embodiment of the present invention, and as shown in fig. 7, the device includes:
the acquisition module 71 is used for acquiring unit operation data;
the second calculation module 72 is used for calculating in real time according to the unit operation data to obtain energy consumption data;
and the second correcting module 73 is configured to correct the calculated energy consumption data by using the locally stored neural network model, so as to obtain corrected energy consumption data.
Optionally, the apparatus further comprises: and the uploading module is used for uploading the energy consumption data which is corrected for the last time to the server side if the preset period is reached, so that the server side judges whether the neural network model stored locally in the multi-split air conditioner needs to be updated or not.
Optionally, the apparatus further comprises: the second updating module is used for detecting whether a model updating signal is received or not after the energy consumption data which is corrected for the last time is uploaded to the server; and if so, replacing the locally stored original neural network model with the received new neural network model.
Optionally, the second calculating module 72 is specifically configured to: calculating to obtain real-time power and electric quantity according to the electricity utilization data in the unit operation data; calculating to obtain refrigerating capacity according to thermophysical data of a specified position in the unit operation data; calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio; wherein the energy consumption data comprises: the electric quantity, the refrigerating capacity and the energy efficiency ratio.
Optionally, the second modification module 73 is specifically configured to: and taking the calculated energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
The device can execute the method provided by the second embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. For details of the technique not described in detail in this embodiment, reference may be made to the method provided in the second embodiment of the present invention.
EXAMPLE five
The present embodiment provides a multi-split energy consumption metering system, including: the system comprises a server and at least two multi-connected lines. The server is used for receiving the unit operation data uploaded by the multi-online unit; calculating in real time according to the unit operation data to obtain first energy consumption data; and correcting the first energy consumption data by using the neural network model to obtain the corrected energy consumption data. Specifically, the server includes the multi-split energy consumption metering device in the third embodiment of the present invention; the multi-split air conditioner comprises the multi-split air conditioner energy consumption metering device in the fourth embodiment of the invention.
The server side can comprise at least one server, namely a server cluster is formed, and each server can provide the same service.
The embodiment can calculate the energy consumption of the multi-split air conditioner on line in real time, and the calculated multi-split air conditioner energy consumption is corrected by utilizing the neural network model obtained based on big data training, so that the accurate measurement of the energy consumption of the multi-split air conditioner is realized, the comprehensive measurement and statistics of a large number of multi-split air conditioner energy consumption are realized, a large amount of manpower is not required to be consumed, and an ammeter is used for actual measurement, so that the multi-split air conditioner energy consumption.
EXAMPLE six
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements a multi-session energy consumption metering method of a server side according to the first embodiment of the present invention, or implements a multi-session energy consumption metering method of a multi-session side according to the second embodiment of the present invention.
EXAMPLE seven
The present embodiment provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, implement the method for measuring consumption of multiple machines on a server side according to the first embodiment of the present invention, or implement the method for measuring consumption of multiple machines on a multiple machine side according to the second embodiment of the present invention.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A multi-player energy consumption metering method, wherein the method is executed by a server, and the method comprises the following steps:
receiving unit operation data uploaded by the multi-split air conditioner;
calculating in real time according to the unit operation data to obtain first energy consumption data;
and correcting the first energy consumption data by using a neural network model to obtain corrected energy consumption data.
2. The method of claim 1, wherein calculating the first energy consumption data in real time from the unit operational data comprises:
calculating to obtain real-time power and electric quantity according to the electricity utilization data in the unit operation data;
calculating to obtain refrigerating capacity according to thermophysical data of a specified position in the unit operation data;
calculating according to the real-time power and the refrigerating capacity to obtain an energy efficiency ratio;
wherein the first energy consumption data comprises: the electric quantity, the refrigerating capacity and the energy efficiency ratio.
3. The method of claim 1, further comprising, prior to calculating the first energy consumption data in real time from the unit operational data:
acquiring the model information of the multi-split air conditioner;
and determining an energy consumption algorithm corresponding to the model information according to prestored configuration information so as to calculate the first energy consumption data according to the energy consumption algorithm.
4. The method of claim 1, wherein modifying the first energy consumption data using a neural network model to obtain modified energy consumption data comprises:
and taking the first energy consumption data as the input of the neural network model to obtain the output of the neural network model, and taking the output as the corrected energy consumption data.
5. The method of claim 1, further comprising, prior to modifying the first energy consumption data using a neural network model:
building a neural network and initializing parameters of the neural network;
obtaining sample data, wherein the sample data comprises: theoretical energy consumption data obtained by calculation aiming at least two multi-connected lines and corresponding actual measured real data;
taking the theoretical energy consumption data as the input of the neural network to obtain the output of the neural network;
judging whether the error between the output of the neural network and the real data is within a first preset error range or not;
if so, determining that the training of the neural network model is finished;
and if not, adjusting the parameters of the neural network, and returning to execute the step of taking the theoretical energy consumption data as the input of the neural network.
6. The method of claim 5, after determining that training of the neural network model is complete, further comprising:
selecting updating data used for updating a model from the first energy consumption data calculated in real time for each multi-split air conditioner, and acquiring real data corresponding to the updating data;
and updating the neural network model according to the updated data and the corresponding real data.
7. The method of claim 5, after determining that training of the neural network model is complete, further comprising:
and sending the trained neural network model to each multi-split telephone so that each multi-split telephone stores the trained neural network model.
8. The method of claim 7, after sending the trained neural network model to each of the plurality of online machines, further comprising:
receiving second energy consumption data uploaded by the multi-split air conditioner according to a preset period, wherein the second energy consumption data is energy consumption data obtained after a neural network model stored locally by the multi-split air conditioner is corrected for the last time;
judging whether the error between the second energy consumption data and the corrected energy consumption data obtained by the server based on the same unit operation data and the current neural network model is within a second preset error range or not;
and if not, sending the current neural network model to the multi-split air conditioner for local model updating.
9. A multi-split energy consumption metering system, comprising: the system comprises a server and at least two multi-connected lines;
the server is used for receiving the unit operation data uploaded by the multi-online unit; calculating in real time according to the unit operation data to obtain first energy consumption data; and correcting the first energy consumption data by using a neural network model to obtain corrected energy consumption data.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010213975.8A CN111473471A (en) | 2020-03-24 | 2020-03-24 | Multi-linkage energy consumption metering method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010213975.8A CN111473471A (en) | 2020-03-24 | 2020-03-24 | Multi-linkage energy consumption metering method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111473471A true CN111473471A (en) | 2020-07-31 |
Family
ID=71747704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010213975.8A Pending CN111473471A (en) | 2020-03-24 | 2020-03-24 | Multi-linkage energy consumption metering method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111473471A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111964217A (en) * | 2020-08-26 | 2020-11-20 | 特灵空调***(中国)有限公司 | Air conditioner control method, system and storage medium |
| CN112364563A (en) * | 2020-11-11 | 2021-02-12 | 清华大学 | Household metering and charging method and device for multi-split air conditioner |
| WO2023090144A1 (en) * | 2021-11-18 | 2023-05-25 | アズビル株式会社 | Information processing device, information processing method, and information processing program |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN110749028A (en) * | 2019-10-29 | 2020-02-04 | 珠海格力电器股份有限公司 | Method, system and device for determining air conditioner operation power |
-
2020
- 2020-03-24 CN CN202010213975.8A patent/CN111473471A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446139A (en) * | 2015-12-18 | 2016-03-30 | 华南理工大学 | Construction energy consumption analysis method and construction energy consumption analysis system based on BP neural network |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN110749028A (en) * | 2019-10-29 | 2020-02-04 | 珠海格力电器股份有限公司 | Method, system and device for determining air conditioner operation power |
Non-Patent Citations (1)
| Title |
|---|
| 邓钊鹏: "一种基于BP神经网络的建筑能耗分析模型的研究与实现", 一种基于BP神经网络的建筑能耗分析模型的研究与实现, pages 7 - 35 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111964217A (en) * | 2020-08-26 | 2020-11-20 | 特灵空调***(中国)有限公司 | Air conditioner control method, system and storage medium |
| CN112364563A (en) * | 2020-11-11 | 2021-02-12 | 清华大学 | Household metering and charging method and device for multi-split air conditioner |
| WO2023090144A1 (en) * | 2021-11-18 | 2023-05-25 | アズビル株式会社 | Information processing device, information processing method, and information processing program |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111473471A (en) | Multi-linkage energy consumption metering method and system | |
| CN109937331B (en) | Air conditioner and air conditioning system | |
| CN106326990A (en) | Intelligent refrigerator remote fault diagnosis and service system and method thereof | |
| CN107062559B (en) | A kind of air conditioner lacks fluorine detection method, device and air-conditioning system | |
| US20170356665A1 (en) | Method and apparatus for providing equipment maintenance via a network | |
| US20200379423A1 (en) | Systems and methods for detecting changes in energy usage in a building | |
| CN111830350B (en) | Energy consumption metering method and device and electric appliance | |
| CN111999692B (en) | Multi-table error calibration method and device | |
| Wang et al. | A load modeling algorithm for distribution system state estimation | |
| CN112462135B (en) | Electric quantity determination method based on household charging system and air conditioning unit | |
| CN113009406A (en) | Electric quantity measurement correction method and device and air conditioning system | |
| CN107121943B (en) | Method and device for obtaining health prediction information of intelligent instrument | |
| CN114168444A (en) | Dynamic operation and maintenance repair reporting model based on monitoring big data | |
| CN116154765A (en) | Power topological relation identification method and device, computer equipment and storage medium | |
| CN114135984A (en) | Simulation control system of air conditioner | |
| CN115493248A (en) | Intelligent diagnosis method and system for full life cycle of central air-conditioning system | |
| CN111999691A (en) | Error calibration method and error calibration device for metering sensor device | |
| WO2016136391A1 (en) | Fault point locating device and method, electric power system monitoring system, and facility planning support system | |
| CN117291576A (en) | Industrial scene data trend prediction-based method, system, computer equipment and storage medium | |
| KR102432287B1 (en) | Method and apparatus for real-time remote meter reading | |
| CN113566374A (en) | Building load determination method and system | |
| CN114089260A (en) | Electric quantity measurement correction method and device and micro-grid system | |
| TWI748672B (en) | Automatic meter reading abnormality analysis system and method thereof | |
| CN114897196B (en) | Operation management method, equipment and medium for office building water supply network | |
| CN118034990B (en) | Concentrator verification method and system based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |