Comprehensive energy-saving control device for power utilization of commercial building

Abstract

The invention discloses a commercial building electricity comprehensive energy-saving control device, and relates to the technical field of building energy management, the commercial building electricity comprehensive energy-saving control device comprises a comprehensive energy service cloud platform, an air conditioner energy router and an intelligent terminal, the comprehensive energy service cloud platform is in signal connection with the intelligent terminal through the air conditioner energy router; the integrated energy service cloud platform is communicated with the air conditioner energy router through the Ethernet, 4G and NBIOT; the air conditioner energy router is used for providing a traditional gateway data forwarding function and undertaking local data storage, fusion and terminal equipment management. From the perspective of energy efficiency, firstly, a perfect energy efficiency index of the central air-conditioning system is put forward, on this basis, a specific energy consumption optimization strategy is researched from links such as a cold and heat source system, a water system and a terminal system, and finally, from the whole building, operation mode adjustment based on self-learning optimization is achieved in combination with a load prediction model. And comprehensive energy-saving control of electricity utilization of commercial buildings is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy management, and in particular to a comprehensive energy-saving control device for commercial building electricity consumption. Background Art

[0002] Building electricity consumption accounts for 40% of the global total energy consumption, and this proportion is still increasing, especially in developing countries. Building load forecasting is an important basis for building energy efficiency management systems, evaluation and diagnosis of each energy-consuming subsystem in the building, optimized control of electricity consumption, and scheduling planning. Combining accurate load forecasting, the peak of the building load curve and the energy-saving potential of controllable loads can be analyzed, providing support for formulating a flexible load control mechanism based on demand response.

[0003] Intelligent power consumption is the basis and an important link in planning the smart grid. Accurate prediction of commercial building energy consumption can help the power grid system to conduct efficient management and reasonable allocation of electric energy resources, which is of great significance for carrying out intelligent power consumption services. Commercial building energy consumption managers (such as building owners or engineers) need to accurately predict energy demand in the near future or one day in advance so as to be able to better manage energy use.

[0004] 1. In the selection of electrical equipment and air-conditioning equipment in commercial buildings, due to the lack of necessary accurate data support, the design loads of power equipment and air-conditioning units are generally too large, and in actual operation, the phenomenon of using a big horse to pull a small cart often occurs, resulting in the system deviating from the optimal working state point during operation, the energy efficiency ratio of energy-consuming equipment decreasing, the operating efficiency of the system dropping, and increasing unnecessary energy consumption losses; 2. The operation managers of commercial buildings lack necessary skills, and the formulated energy-saving rules and regulations for commercial buildings are fragmented and lack scientificity. Energy-saving measures and energy-saving transformations mainly start from restricting energy use, with the idea of "energy conservation means not using energy", ignoring the user's demand for environmental quality, and achieving energy conservation at the cost of sacrificing the indoor environment, resulting in difficulties in actual implementation; 3. There is a lack of scientific energy consumption diagnosis indicators and evaluation criteria. Through research, it is found that the air-conditioning system accounts for about 30% - 40% of the total energy consumption of commercial buildings. And what are the indicators that affect the energy consumption level of the air-conditioning system? Although the existing energy consumption diagnosis methods for commercial buildings form their own systems, they are still limited to the overall level and have not been able to form a detailed energy-saving diagnosis method for the air-conditioning system. Summary of the Invention

[0005] The purpose of the present invention is to provide a comprehensive energy-saving control device for commercial building electricity consumption to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A comprehensive energy-saving control device for commercial buildings, including a comprehensive energy service cloud platform, an air-conditioning energy router, and intelligent terminals. The comprehensive energy service cloud platform is signal-connected to the intelligent terminals through the air-conditioning energy router. The comprehensive energy service cloud platform and the air-conditioning energy router are connected through Ethernet, 4G, and NBIoT. The air-conditioning energy router is used to provide the data forwarding function of a traditional gateway and undertake local data storage, fusion, terminal device management, refined energy diagnosis, and edge computing functions of demand response rules. Through the 485 / M-bus interface and the LoRa wireless network, the air-conditioning energy router respectively completes the collection of water, electricity, gas, and heating meters and the information collection / control of intelligent terminals. The air-conditioning energy router includes a local data processing module, a protocol parsing and adaptation module, a control strategy distribution and execution module, and a local alarm and energy monitoring module.

[0007] Preferably, the comprehensive energy service cloud platform includes a database module, a visualization module, and a microservice module. The database module is used to establish a MySQL relational database to store data, and its database model shows the relationship between data based on entity-relationship. The visualization module uses the Web side under the B / S structure for the visualization display of the system. The microservice module is used to provide dynamic online monitoring of energy consumption, statistical analysis of energy consumption data, energy efficiency analysis and comparison, energy-saving strategy management, demand response, and intelligent operation and maintenance.

[0008] Preferably, the local data processing module is used to access energy consumption monitoring data, energy consumption system control data, and archive data. The energy consumption monitoring data includes basic data, device-level data, branch data, gateway data, and industry statistical data. The energy consumption system control data includes load data, response capacity data, and control strategy data. The archive data refers to the archive data of various monitoring devices on the user side, including the name, status, specification model, manufacturer, rated voltage, and power of the devices.

[0009] Preferably, the protocol parsing and adaptation module is used to parse devices with different communication protocols, support multiple communication protocols, convert different protocols into a unified data format, and enable various devices to communicate and cooperate with each other.

[0010] Preferably, the control strategy distribution and execution module is used to provide a comprehensive energy efficiency improvement control strategy for the air-conditioning system of commercial buildings and execute strategy measures, including an air-conditioning system energy efficiency index module, a chiller energy efficiency optimization control strategy module, a terminal system control strategy module, an energy consumption optimization module for the central air-conditioning water circulation system, an artificial intelligence control strategy module, and a power demand response strategy. The energy efficiency index module of the air conditioning system compares and analyzes the operating energy efficiency of the central air conditioning in commercial buildings with the national energy efficiency grade, including the air conditioning energy consumption per unit area, the cooling capacity consumption per unit air conditioning area, the energy efficiency ratio of the air conditioning system, the energy efficiency ratio of the refrigeration system, the chilled water transmission coefficient, the energy efficiency ratio of the air conditioning terminal, the operating efficiency of the chiller, and the cooling water transmission coefficient; The energy efficiency optimization control strategy module of the chiller issues control strategies to the local execution of the regulation terminals converted by the control cabinets of the chilled water circulation subsystem, the cooling water circulation subsystem, and the air handling unit control cabinet respectively through the energy routing controller; The terminal system control strategy module includes the geothermal coil control strategy and the fan coil system control strategy. The geothermal coil control strategy uses intermittent heating and MRT control methods to control the heating condition. The start and stop of the geothermal coil heating system are controlled by the change of the indoor average radiation temperature. The fan coil system control strategy uses intermittent heating and variable air volume and variable water volume control methods, and the start and stop of the fan coil are controlled by the change of the indoor temperature; The energy consumption optimization module of the central air conditioning water circulation system is used to optimize the energy consumption of the central air conditioning water system. The total energy consumption of the central air conditioning water system includes the energy consumption of the chiller, the primary chilled water pump, and the secondary chilled water pump. Their constraint conditions are mutually coupled. This multi-dimensional non-linear constrained optimization problem is expressed by a mathematical expression and decoupled and analyzed for optimization; The artificial intelligence control strategy module uses the offline dynamic load prediction mathematical model and simulation database, analyzes the uncertainty and dynamic discrete characteristics of the supply-demand matching on the user side and source side of the coupled system by using the random forest feature method, and forms the basis for offline feature location prediction; combined with the online data deep learning method calculated by the long short-term memory neural network, a dynamic demand prediction optimization method integrating feature location and deep learning theory is proposed to realize the demand prediction applicable to the dynamic scenario of the coupled system; The power demand response strategy is used to formulate the operation strategy with the lowest economic cost according to the time-of-use electricity price conditions of the project. At the same time, combined with the differences in usage habits between working days and holidays of the building, as well as different demands such as comfort mode, health mode, epidemic prevention mode, and safety mode, the operation strategy of the energy system in different modes is formulated, and it can self-learn according to the actual usage situation to achieve flexible switching.

[0011] Preferably, the load prediction process in the artificial intelligence control strategy module is as follows: ① Simulate and calculate the system demand in a dynamic simulation manner, combine the load database of similar projects in typical cities, extract relevant load data characteristics, and form an offline load prediction result; ② Obtain historical air conditioning load data and preprocess the load data; ③ Divide the data samples, and perform model training and model optimization; ④ Input the test set data into the determined prediction model. The output results of the prediction model need to be de-normalized, and corresponding processing should be carried out for unreasonable results to obtain the final prediction results; ⑤ Integrate the online prediction results and the offline results, each with a weight ratio of 50%. The weight of the offline load prediction algorithm gradually decreases until the online prediction algorithm results are fully adopted.

[0012] Preferably, the local alarm and energy monitoring module is used to monitor the energy consumption of commercial buildings, real-time monitor various energy data, and set alarm rules to send an alarm when the energy consumption exceeds the set threshold, reminding relevant personnel to take corresponding energy-saving measures.

[0013] Preferably, the local alarm and energy monitoring module includes a building load data monitoring module and a threshold alarm module; The building load data monitoring module is used to real-time monitor the commercial building load data, and the commercial building load includes the air conditioning system, lighting socket system, power system, and special electricity consumption; The threshold alarm module is used to set the threshold of energy consumption and send an alarm when it exceeds the threshold.

[0014] Preferably, the local alarm and energy monitoring module further includes a data analysis module and a remote monitoring module; The data analysis module is used to analyze the monitored energy data and generate a report to help the building manager understand the energy consumption situation; The remote monitoring module supports remote monitoring functions, can monitor energy data anytime and anywhere, and perform real-time energy management.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. In the present invention, starting from the perspective of energy efficiency, a complete energy efficiency index for the central air conditioning system is first proposed. On this basis, specific energy consumption optimization strategies are studied from links such as the cold and heat source system, water system, and terminal system. Finally, starting from the overall building, combined with the load prediction model, the operation mode adjustment based on self-learning optimization is realized, and the comprehensive energy-saving control of electricity consumption in commercial buildings is achieved.

[0016] 2. In the present invention, based on the large amount of data analysis results of the upper computer, the system can formulate the operation strategy with the lowest economic cost according to the time-of-use electricity price conditions of the project. At the same time, combined with the differences in usage habits between working days and holidays in the building, and different needs such as comfort mode, health mode, epidemic prevention mode, and safety mode, the operation strategy of the energy system in different modes is formulated, and it can self-learn according to the actual usage situation to achieve flexible switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is the system block diagram of a comprehensive energy-saving control device for commercial building electricity consumption according to the present invention; Figure 2 This is the power load prediction flow chart of a comprehensive energy-saving control device for commercial building electricity consumption according to the present invention; Figure 3 This is the load distribution decision-making flow chart of a comprehensive energy-saving control device for commercial building electricity consumption according to the present invention.

[0018] In the figure: 1. Comprehensive energy service cloud platform; 11. Database module; 12. Visualization module; 13. Microservice module; 2. Air-conditioning energy router; 21. Local data processing module; 22. Protocol parsing and adaptation module; 23. Control strategy distribution and execution module; 231. Air-conditioning system energy efficiency index module; 232. Chiller energy efficiency optimization control strategy module; 233. Terminal system control strategy module; 234. Energy consumption optimization module for central air-conditioning water circulation system; 235. Artificial intelligence control strategy module; 236. Power demand response strategy; 24. Local alarm and energy monitoring module; 241. Building load data monitoring module; 242. Threshold alarm module; 243. Data analysis module; 244. Remote monitoring module; 3. Intelligent terminal. Specific implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Refer to Figures 1-3 As shown: A comprehensive energy-saving control device for commercial building electricity consumption includes a comprehensive energy service cloud platform 1, an air-conditioning energy router 2, and an intelligent terminal 3. The comprehensive energy service cloud platform 1 is signal-connected to the intelligent terminal 3 through the air-conditioning energy router 2, and the comprehensive energy service cloud platform 1 and the air-conditioning energy router 2 are connected through Ethernet, 4G, and NBIoT; Among them, the comprehensive energy service cloud platform 1 includes a database module 11, a visualization module 12, and a microservice module 13; The database module 11 is used to establish a MySQL relational database to store data, and its database model shows the relationship between data based on entity-relationship; The visualization module 12 uses a Web end under the B / S structure for the visualization display of the system; The microservice module 13 is used to provide dynamic online monitoring of energy consumption, statistical analysis of energy consumption data, energy efficiency analysis and comparison, energy-saving strategy management, demand response, and intelligent operation and maintenance; The air-conditioning energy router 2 is used to provide the traditional gateway data forwarding function and undertake the edge computing functions of local data storage, fusion, terminal device management, refined energy diagnosis, and demand-side response rules. Through the 485 / M-bus interface and the LoRa wireless network, it respectively completes the centralized meter reading function of water, electricity, gas, and heating meters and the information collection / control of the intelligent terminal 3. The air-conditioning energy router 2 includes a local data processing module 21, a protocol parsing and adaptation module 22, a control strategy distribution and execution module 23, and a local alarm and energy monitoring module 24; Among them, the local data processing module 21 is used to access energy consumption monitoring data, energy consumption system control data, and archive data; the energy consumption monitoring data includes basic data, equipment-level data, branch data, gateway data, and industry statistical data; the energy consumption system control data includes load data, response capacity data, and control strategy data; the archive data refers to various monitoring device archive data on the user side, including the name, status, specification model, manufacturer, rated voltage, and power of the equipment; Among them, the protocol parsing and adaptation module 22 is used to parse devices with different communication protocols, support multiple communication protocols, convert different protocols into a unified data format, and enable various devices to communicate and cooperate with each other; Among them, the control strategy distribution and execution module 23 is used to provide and execute the control strategy for improving the comprehensive energy efficiency of the air-conditioning system in commercial buildings, including an air-conditioning system energy efficiency index module 231, a chiller energy efficiency optimization control strategy module 232, a terminal system control strategy module 233, an energy optimization module 234 for the central air-conditioning water circulation system, and an artificial intelligence control strategy module 235; The air-conditioning system energy efficiency index module 231 conducts a comparative analysis of the operating energy efficiency of the central air-conditioning in commercial buildings with the national energy efficiency grade, including the air-conditioning energy consumption per unit area, the cooling capacity consumption per unit air-conditioning area, the energy efficiency ratio of the air-conditioning system, the energy efficiency ratio of the refrigeration system, the chilled water transportation coefficient, the energy efficiency ratio of the air-conditioning terminal, the operating efficiency of the chiller, and the cooling water transportation coefficient; The chiller energy efficiency optimization control strategy module 232 respectively issues the control terminals converted by the chilled water circulation subsystem control cabinet, the cooling water circulation subsystem control cabinet, and the air handling unit control cabinet through the energy router controller for local execution of the strategy; The terminal system control strategy module 233 includes a geothermal coil control strategy and a fan coil system control strategy. The geothermal coil control strategy uses intermittent heating and MRT control methods to control the heating condition, and controls the start and stop of the geothermal coil heating system through the change of the indoor average radiant temperature. The fan coil system control strategy uses intermittent heating and variable air volume and variable water volume control methods, and controls the start and stop of the fan coil through the change of the indoor temperature; The energy optimization module 234 for the central air-conditioning water circulation system is used to optimize the energy consumption of the central air-conditioning water system. The total energy consumption of the central air-conditioning water system includes the energy consumption of the chiller, the primary chilled water pump, and the secondary chilled water pump. Their constraint conditions are mutually coupled. For this multi-dimensional non-linear constrained optimization problem, it is expressed by a mathematical expression and decoupled and analyzed for optimization; As Figure 2 shown, the artificial intelligence control strategy module 235 uses the offline dynamic load prediction mathematical model and the simulation database, analyzes the uncertainty and dynamic discrete characteristics of the supply-demand matching on the user side and the source side of the coupled system by using the random forest feature method, and forms the basis for offline feature location prediction; and combines the online data deep learning method calculated by the long short-term memory neural network to propose a dynamic demand prediction optimization method that combines feature location and deep learning theory to achieve demand prediction applicable to the dynamic scenario of the coupled system. The load prediction process is as follows: ① Use dynamic simulation to simulate and calculate the system demand, combine the load database of similar projects in typical cities, extract relevant load data characteristics, and form an offline load prediction result; ② Obtain historical air-conditioning load data and preprocess the load data; ③ Divide the data samples, perform model training and model optimization; ④ Input the test set data into the determined prediction model. The output result of the prediction model needs to be de-normalized and the unreasonable results need to be processed accordingly to obtain the final prediction result; ⑤ Fuse the online prediction result and the offline result, each with a weight ratio of 50%. The weight of the offline load prediction algorithm gradually decreases until the online prediction algorithm result is completely adopted; The power demand response strategy 236 is used to formulate the operation strategy with the lowest economic cost according to the time-of-use electricity price conditions of the project, and at the same time, combined with the differences in usage habits between weekdays and holidays of the building, and different demands such as comfort mode, health mode, epidemic prevention mode, and safety mode, formulate the operation strategy of the energy system under different modes, and can self-learn according to the actual usage situation to achieve flexible switching; Specifically, it includes dynamic priority and decision-making scheme. The dynamic priority mainly reflects the user's electricity demand for the load within the response time. The electricity demand is calculated as follows: ; ; In the formula: is the electricity demand of load i; D is the dynamic priority sequence; is the sorting function.

[0021] Calculate the comfort loss of different loads according to different priorities, as follows: As can be seen from the above formula, the greater the electricity demand of a load, the higher its priority, and the smaller the comfort loss when participating in load regulation. Further, the corresponding load status can be obtained according to the comfort loss: S dr,i = S r,i (E p,i - 1) + S h,i ; P i (S dr,i ) = |S dr,i |; Finally, according to S dr,i the load amount P i (S dr,i ) of the corresponding priority load can be determined, and |S dr,i | is the ceiling of the minimum power supply unit of the load. When S dr,i is the air-conditioning load status, it represents the indoor set temperature. When S dr,i is the load status of other rigid regulation methods, it can be seen from the formula that P i (S dr,i ) is the same as S dr,i ; As Figure 3 shown, the decision-making scheme preferentially allocates low-participation loads, then solves the load comfort loss based on dynamic priorities, and finally completes the decision-making process of load allocation in the order from high to low priority. The entire decision-making process is as follows: Step1: Receive the demand response instruction from the grid side, retrieve the historical load data, and calculate the allocable load for this demand response

[0022] Step2: Calculate the normal load demand of low-participation loads during the response time , if holds, it means that there is remaining load that can be allocated to high-participation loads on the basis of the normal operation of low-participation loads, and go to Step4; otherwise, is preferentially allocated to low-participation loads and go to Step3.

[0023] Step3: Calculate the electricity demand of each low-participation load during the response time , generate the dynamic priority sequence of low-participation loads, find out the corresponding comfort loss sequence , and then perform load allocation in the order from high to low priority.

[0024] Step4: Calculate the electricity demand of each high-participation load during the response time , generating a dynamic priority sequence of low participation loads , find the corresponding comfort loss sequence , and then the load is distributed in descending order of priority. The high participation distribution load at this time is .

[0025] Step 5: Output the allocated load of each response strategy and generate control instructions.

[0026] The local alarm and energy monitoring module 24 is used to monitor the energy consumption of commercial buildings and monitor various energy data in real time. At the same time, alarm rules are set to issue an alarm when energy consumption exceeds a set threshold, reminding relevant personnel to take corresponding energy-saving measures; specifically, it includes a building load data monitoring module 241, a threshold alarm module 242, a data analysis module 243 and a remote monitoring module 244; The building load data monitoring module 241 is used to monitor the commercial building load data in real time. The commercial building load includes air conditioning system, lighting socket system, power system and special electricity consumption; the threshold alarm module 242 is used to set the threshold of energy consumption and issue an alarm when the threshold is exceeded; the data analysis module 243 is used to analyze the monitored energy data and generate reports to help building managers understand energy consumption; the remote monitoring module 244 supports remote monitoring function, which can monitor energy data anytime and anywhere and perform real-time energy management.

[0027] The present invention aims at the problem of optimizing air conditioning energy consumption in large commercial buildings, develops an air conditioning energy router for commercial buildings, connects protocols between different manufacturers and different equipment, and realizes ubiquitous interconnection. On this basis, with the help of energy system big data, vigorously promote services such as air conditioning system optimization control, power demand response, and power market transactions. Through energy efficiency monitoring and analysis, provide customers with comprehensive energy efficiency improvement services such as equipment parameter matching, pipe network operation optimization, and terminal real-time control, and promote the coordinated balance of air conditioning system energy load and power grid supply capacity. By establishing typical buildings and equipment energy consumption models of different forms, the visualization of building energy systems is realized, and standardized building energy efficiency monitoring products and overall solutions suitable for different application scenarios and different energy categories are established to meet the plug-and-play requirements of various terminal devices in the energy control system, and realize multi-objective automatic regulation of building energy systems; By solving the problem of efficient access to energy consumption data, environmental data, equipment operation and status data of the smart energy system, and accurate issuance of information system instruction strategies, an overall solution and idea of ​​equipment modeling, collection point code preset and communication protocol standardization was proposed, and an energy controller was developed to ensure the integration of the energy Internet industrial control system and the information system, solving the urgent demand for data in the energy information system and laying the foundation for realizing diversified energy services in the information system; Based on the analysis of the electricity load of commercial buildings, an energy optimization control strategy for commercial buildings is proposed. From the perspective of energy efficiency, first, a complete energy efficiency index for the central air-conditioning system is proposed. On this basis, specific energy optimization strategies are studied from aspects such as the cold and heat source system, water system, and terminal system. Finally, starting from the overall building, the operation mode adjustment based on self-learning optimization is realized by combining the load prediction model. Based on the large amount of data analysis results of the upper computer, the system can formulate the operation strategy with the lowest economic cost according to the time-of-use electricity price conditions of the project. At the same time, considering the differences in usage habits between working days and holidays of the building, as well as different needs such as comfort mode, health mode, epidemic prevention mode, and safety mode, the operation strategies of the energy system under different modes are formulated, and it can learn from the actual usage situation and achieve flexible switching.

[0028] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An integrated energy-saving control device for electricity consumption in commercial buildings, characterized in that: It includes an integrated energy service cloud platform (1), an air-conditioning energy router (2), and intelligent terminals (3). The integrated energy service cloud platform (1) is signal-connected to the intelligent terminals (3) through the air-conditioning energy router (2). The integrated energy service cloud platform (1) and the air-conditioning energy router (2) are connected through Ethernet, 4G, and NBIoT. The air-conditioning energy router (2) is used to provide the data forwarding function of a traditional gateway and undertake local data storage, fusion, terminal device management, refined energy diagnosis, and edge computing functions of demand response rules. Through the 485 / M-bus interface and the LoRa wireless network, it respectively completes the collection of water, electricity, gas, and heating meters and the information collection / control of the intelligent terminals (3). The air-conditioning energy router (2) includes a local data processing module (21), a protocol parsing and adaptation module (22), a control strategy distribution and execution module (23), and a local alarm and energy monitoring module (24).

2. The integrated energy-saving control device for electricity consumption in commercial buildings according to claim 1, wherein: The integrated energy service cloud platform (1) includes a database module (11), a visualization module (12), and a microservice module (13). The database module (11) is used to establish a MySQL relational database to store data, and its database model shows the relationship between data based on entity-relationship. The visualization module (12) uses the Web side under the B / S structure for the visualization display of the system. The microservice module (13) is used to provide dynamic online monitoring of energy consumption, statistical analysis of energy consumption data, energy efficiency analysis and comparison, energy-saving strategy management, demand response, and intelligent operation and maintenance.

3. The integrated energy-saving control device for commercial building electricity consumption according to claim 1, characterized in that: The local data processing module (21) is used to access energy consumption monitoring data, energy consumption system control data, and archive data. The energy consumption monitoring data includes basic data, equipment-level data, branch data, gateway data, and industry statistical data. The energy consumption system control data includes load data, response capacity data, and control strategy data. The archive data refers to the archive data of various monitoring devices on the user side, including the name, status, specification model, manufacturer, rated voltage, and power of the equipment.

4. The integrated power consumption energy-saving control device for commercial buildings according to claim 3, characterized in that: The protocol parsing and adaptation module (22) is used to parse devices with different communication protocols, support multiple communication protocols, convert different protocols into a unified data format, and enable various devices to communicate and cooperate with each other.

5. An integrated energy-saving control device for commercial building electricity consumption according to claim 4, characterized in that: The control strategy distribution and execution module (23) is used to provide control strategies for improving the comprehensive energy efficiency of the air-conditioning system in commercial buildings and execute strategy measures, including an air-conditioning system energy efficiency index module (231), a chiller energy efficiency optimization control strategy module (232), an end-system control strategy module (233), an energy consumption optimization module for the central air-conditioning water circulation system (234), an artificial intelligence control strategy module (235), and a power demand response strategy (236). The air-conditioning system energy efficiency index module (231) conducts a comparative analysis of the operating energy efficiency of the central air-conditioning in commercial buildings and the national energy efficiency grade, including the air-conditioning energy consumption per unit area, the cooling capacity per unit air-conditioning area, the energy efficiency ratio of the air-conditioning system, the energy efficiency ratio of the refrigeration system, the chilled water transmission coefficient, the energy efficiency ratio of the air-conditioning terminal, the operating efficiency of the chiller, and the cooling water transmission coefficient. The energy efficiency optimization control strategy module (232) of the chiller issues control commands to the regulation terminals converted by the control cabinets of the chilled water circulation subsystem, the cooling water circulation subsystem, and the air handling unit control cabinet respectively through the energy routing controller for local execution of the strategy. The terminal system control strategy module (233) includes the geothermal coil control strategy and the fan coil system control strategy. The geothermal coil control strategy uses the intermittent heating and MRT control methods to control the heating condition. The start and stop of the geothermal coil heating system are controlled by the change of the indoor average radiant temperature. The fan coil system control strategy uses the intermittent heating and variable air volume and variable water volume control methods, and the start and stop of the fan coil are controlled by the change of the indoor temperature. The energy consumption optimization module (234) of the central air-conditioning water circulation system is used to optimize the energy consumption of the central air-conditioning water system. The total energy consumption of the central air-conditioning water system includes the energy consumption of the chiller, the primary chilled water pump, and the secondary chilled water pump. Their constraint conditions are mutually coupled. This multi-dimensional non-linear constrained optimization problem is expressed by a mathematical expression and decoupled and analyzed for optimization. The artificial intelligence control strategy module (235) uses the offline dynamic load prediction mathematical model and the simulation database, and uses the random forest feature method to analyze the uncertainty and dynamic discrete characteristics of the supply-demand matching on the user side and the source side of the coupled system, forming the basis for offline feature location prediction; and combining the online data deep learning method calculated by the long short-term memory neural network, a dynamic demand prediction optimization method integrating feature location and deep learning theory is proposed to realize the demand prediction applicable to the dynamic scenario of the coupled system. The power demand response strategy (236) is used to formulate the operation strategy with the lowest economic cost according to the time-of-use electricity price conditions of the project, and at the same time, combined with the differences in the usage habits of weekdays and holidays in the building, different demands such as comfort mode, health mode, epidemic prevention mode, and safety mode, to formulate the operation strategy of the energy system under different modes, and can self-learn according to the actual usage situation to achieve flexible switching.

6. The integrated energy-saving control device for electricity consumption in commercial buildings according to claim 5, characterized in that: The load prediction process in the artificial intelligence control strategy module (235) is as follows: ① Simulate and calculate the system demand in a dynamic simulation manner, combine the load database of similar projects in typical cities, extract relevant load data characteristics, and form an offline load prediction result. ② Obtain historical air-conditioning load data and preprocess the load data. ③ Divide the data samples, perform model training and model optimization. ④ Input the test set data into the determined prediction model. The output result of the prediction model needs to be de-normalized and the unreasonable results need to be processed accordingly to obtain the final prediction result. ⑤ Fuse the online prediction result and the offline result, each with a weight ratio of 50%. The weight of the offline load prediction algorithm gradually decreases until the online prediction algorithm result is fully adopted.

7. The integrated power consumption energy-saving control device for commercial buildings according to claim 5, characterized in that: The local alarm and energy monitoring module (24) is used to monitor the energy consumption of the commercial building, and monitor various energy data in real time. At the same time, alarm rules are set to send an alarm when the energy consumption exceeds the set threshold, reminding relevant personnel to take corresponding energy-saving measures.

8. The integrated power consumption energy-saving control device for commercial buildings according to claim 7, characterized in that: The local alarm and energy monitoring module (24) includes a building load data monitoring module (241) and a threshold alarm module (242); The building load data monitoring module (241) is used to monitor the commercial building load data in real time. The commercial building load includes the air conditioning system, lighting socket system, power system, and special electricity consumption; The threshold alarm module (242) is used to set the threshold of energy consumption and issue an alarm when the threshold is exceeded.

9. The integrated energy-saving control device for commercial building electricity consumption according to claim 8, characterized in that: The local alarm and energy monitoring module (24) further includes a data analysis module (243) and a remote monitoring module (244); The data analysis module (243) is used to analyze the monitored energy data, generate a report, and help the building manager understand the energy consumption situation; The remote monitoring module (244) supports the remote monitoring function, and can monitor the energy data anytime and anywhere and perform real-time energy management.

Images