Air conditioner control method and system for improving energy-saving effect through energy consumption prediction
Through the combination of multi-layer perceptual neural network and genetic algorithms, an energy consumption prediction model is built and the operation of air conditioners is optimized, which solves the problems of poor energy-saving effects and small usage range in the existing technology, and realizes efficient energy-saving control of air conditioners in large areas.
Patent Information
- Application Number
- CN202411004724.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing air conditioning control technology cannot predict energy consumption through season and weather information, and combines human comfort to achieve the optimal energy-saving effect. It has a small range of use, so it cannot uniformly control the air conditioners in the entire building, community or city, resulting in poor energy-saving effect. .
Energy consumption prediction model is constructed through multi-layer perceptual neural network algorithm, combined with setting parameters, real-time environmental parameters and historical weather data, energy consumption prediction is carried out, and genetic algorithms are used to optimize human thermal comfort and air conditioner energy consumption, and control instructions are issued to Improve energy saving effect, and use the sub-region data collection module for unified control.
High-precision energy consumption prediction and air conditioner operation optimization in the target area are achieved, energy saving effect is improved, and the scope of use of air conditioner control is expanded, so that air conditioners in different sub-regions can be controlled separately.
Smart Images

Figure CN118912648A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an air conditioning control method, and in particular to an air conditioning control method and system for improving energy-saving effect through energy consumption prediction. Background Art
[0002] In relatively large indoor places such as shopping malls, supermarkets, offices, and entertainment barracks, multiple air conditioners are installed to adjust the ambient temperature to meet people's requirements for comfortable temperatures. However, since most air conditioners are not managed by dedicated personnel, people often forget to turn off the air conditioners, which not only wastes electricity and causes economic losses, but also poses a safety hazard.
[0003] In addition, the country currently advocates green, environmental protection and energy conservation. Many companies have also set environmental protection temperatures of 24℃-26℃ in summer and 18℃-20℃ in winter. However, in actual use, due to the large number of people using it at the same time, it is relatively casual and inconvenient for unified management and control. The set temperature often does not meet the requirements of environmental protection and energy conservation, which increases the economic burden of the company and does not meet the requirements of green, environmental protection and energy conservation.
[0004] In view of the above situations, the prior art usually uses an air conditioning controller to enable a non-intelligent air conditioner to have an intelligent temperature control function. The air conditioning controller can collect environmental parameters in the space and perform intelligent settings on the air conditioner based on the environmental parameters, so that it has an intelligent temperature adjustment function.
[0005] Although this intelligent temperature control solution can intelligently set the air conditioner, it still has the following defects:
[0006] 1. Existing technologies cannot estimate energy consumption through seasonal and weather information, and cannot combine human comfort with estimated energy consumption to achieve optimal energy-saving effects, resulting in poor energy-saving effects.
[0007] 2. The existing technology is still aimed at intelligent control of one or several air conditioners in relatively independent spaces or places. It lacks an overall solution for unified control and unified scheduling of air conditioners in the entire building, the entire community, or the entire system, or even the entire city, and its scope of use is relatively small.
[0008] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of the application, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention
[0009] The purpose of the present invention is to overcome the shortcomings of the prior art, such as poor energy-saving effect and small scope of use, and to provide an air-conditioning control method and system with better energy-saving effect and a larger scope of use to improve energy-saving effect.
[0010] To achieve the above objectives, the technical solution of the present invention is:
[0011] An air conditioning control method for improving energy saving effect by energy consumption prediction, the air conditioning control method comprising the following steps:
[0012] S1, data collection, collects setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area;
[0013] S2, build the model, build the initial model for energy consumption prediction of the target area through the multi-layer perception neural network algorithm,
[0014] S3, training the initial energy consumption prediction model based on historical data, wherein the historical data includes setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to train and verify the energy consumption prediction model until the prediction accuracy meets the requirements, at which time the model construction is completed;
[0015] S4, model solving, inputting high-precision weather forecast data of the target area in the future set period into the trained energy consumption prediction model, and solving to obtain the energy consumption prediction data of the target area in the future set period;
[0016] S5, through the target area energy consumption prediction data, combined with the set parameters, air conditioning energy parameters and real-time environmental parameters, the current air conditioning operation status is judged, and the corresponding control instructions are issued to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements. At this time, the current iteration is completed;
[0017] S6, model iteration and update. After completing the solution of the energy consumption prediction model, the newly collected weather data and various operating parameters of the air conditioner are added to the historical data, and the prediction model is trained again in S3 for the next iteration.
[0018] The air conditioning control related setting parameters collected in S1 are the air conditioning operating temperature, air conditioning operating mode and operating power set by the user;
[0019] The air conditioning energy usage parameters include energy usage data for at least one month in the past;
[0020] The real-time environmental parameters include the temperature and humidity of the indoor environment where the air conditioner is located;
[0021] The high-precision weather forecast data of the target area includes the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days;
[0022] The historical weather data includes hourly weather forecasts for the target area for at least one month in the past.
[0023] In S2, the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set and a test set. The training set is used to train the energy consumption prediction model of the target area, and the test set is used to verify the accuracy of the energy consumption prediction model. When the output energy consumption result is compared with the test set data and the accuracy is greater than 95%, the training of the energy consumption prediction model of the target area is completed. When the output energy consumption result is compared with the test set data and the accuracy is less than or equal to 95%, the process returns to S1 to increase the amount of data or adjust the model parameters to retrain the model, and re-execute the training steps until the prediction accuracy is greater than 95%.
[0024] In S2, 90% of the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set, and the remaining 10% of the data are divided into a test set.
[0025] In S4, the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days are used as input values to solve the energy consumption prediction model to obtain the hourly energy consumption data of the target area in the next seven days.
[0026] In S5, the difference between the temperature set by the user and the ambient temperature is taken as the thermal comfort of the human body, and the minimum value of the thermal comfort of the human body and the predicted energy consumption data of the target area is taken as the objective function. The genetic algorithm is used for iterative optimization to obtain the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption.
[0027] In S5, when the predicted energy consumption data of the target area is less than the set threshold, no operation is performed; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in cooling mode, the air conditioner set temperature is increased by one degree Celsius; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in heating mode, the air conditioner set temperature is reduced by one degree Celsius.
[0028] An air conditioning control system for improving energy-saving effects through energy consumption prediction, the air conditioning control system being used to implement the aforementioned air conditioning control method for improving energy-saving effects through energy consumption prediction;
[0029] The air conditioning control system comprises:
[0030] Data collection module, used to collect setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area;
[0031] The setting parameters related to air conditioning control are the air conditioning operating temperature, air conditioning operating mode and operating power set by the user;
[0032] The air conditioning energy usage parameters include energy usage data for at least one month in the past;
[0033] The real-time environmental parameters include the temperature and humidity of the indoor environment where the air conditioner is located;
[0034] The high-precision weather forecast data of the target area includes the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days;
[0035] The historical weather data includes hourly weather forecasts for the target area for at least one month in the past;
[0036] The model building module builds an energy consumption prediction model for the target area through a multi-layer perception neural network algorithm, and trains and verifies the energy consumption prediction model through the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to obtain an energy consumption prediction model with prediction accuracy that meets the requirements;
[0037] Specifically, it includes: dividing 90% of the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data into a training set, and dividing the remaining 10% of the data into a test set, wherein the training set is used to train the target area energy consumption prediction model, and the test set is used to verify the accuracy of the energy consumption prediction model. When the output energy consumption result is compared with the test set data, and the accuracy is greater than 95%, the target area energy consumption prediction model training is completed. When the output energy consumption result is compared with the test set data, and the accuracy is less than or equal to 95%, return to S1 to increase the amount of data or adjust the model parameters to retrain the model, and re-execute the training steps until the prediction accuracy is greater than 95%;
[0038] The model solving module is used to solve the energy consumption prediction model by taking the outdoor temperature, outdoor humidity and wind speed of the target area every hour in the next seven days as input values, and obtain the energy consumption data of the target area every hour in the next seven days.
[0039] The air conditioning control module is used to judge the current operation status of the air conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air conditioning control, the air conditioning energy parameters, and the real-time environmental parameters, and issue corresponding control instructions to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements;
[0040] The specific control method includes: taking the difference between the temperature set by the user and the ambient temperature as the thermal comfort of the human body, taking the minimum value of the thermal comfort of the human body and the predicted energy consumption data of the target area as the objective function, and using the genetic algorithm for iterative optimization to obtain the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption;
[0041] Or when the target area predicted energy consumption data is less than the set threshold, no operation is performed; when the target area predicted energy consumption data is greater than the set threshold and the air conditioner is in cooling mode, the air conditioner set temperature is increased by one degree Celsius; when the target area predicted energy consumption data is greater than the set threshold and the air conditioner is in heating mode, the air conditioner set temperature is reduced by one degree Celsius
[0042] The model iteration update module is used to complete the solution of an energy consumption prediction model, add the weather data of the current date to the historical weather data to retrain and verify the energy consumption prediction model until the prediction accuracy meets the requirements.
[0043] The data collection module includes a central data collection module and a plurality of sub-region data collection modules, wherein the central data collection module is used to collect high-precision weather forecast data and historical weather data of the target area, and the sub-region data collection modules are used to collect setting parameters related to air conditioning control, air conditioning energy parameters and real-time environmental parameters;
[0044] The sub-region data collection module is arranged in the sub-region where each air conditioner in the target region is located, and the sub-region is a spatially independent air conditioner operation region in the target region;
[0045] The air-conditioning control module includes a central control module and multiple air-conditioning control modules. The central control module is used to judge the current operation status of the air-conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air-conditioning control, the air-conditioning energy parameters, and the real-time environmental parameters. The air-conditioning control module is used to issue corresponding control instructions to control the air-conditioning so that the operation of the air-conditioning meets the energy-saving management requirements. Each air-conditioning in the target area is correspondingly provided with an air-conditioning control module.
[0046] An air conditioning control device that improves energy saving effect by predicting energy consumption,
[0047] The device comprises a processor and a memory;
[0048] The memory is used to store computer program code and transmit the computer program code to the processor;
[0049] The processor is used to execute the aforementioned air conditioning control method for improving energy saving effect through energy consumption prediction according to the instructions in the computer program code.
[0050] Compared with the prior art, the present invention has the following beneficial effects:
[0051] 1. In the present invention, an air conditioning control method for improving energy-saving effect through energy consumption prediction is used to construct an energy consumption prediction model for a target area using a multi-layer perception neural network algorithm using set parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data, and the high-precision weather forecast data of the target area is used as an input value to solve the energy consumption prediction model to obtain the predicted energy consumption data of the target area, and the energy consumption data is combined with the set parameters, air conditioning energy parameters and real-time environmental parameters to judge the current operation of the air conditioner, and issue corresponding control instructions to control the air conditioner so that the operation of the air conditioner meets the energy-saving management requirements. Therefore, the design can obtain the predicted energy consumption data of the target area through the energy consumption prediction model, and then judge and control the current operation of the air conditioner, effectively improving the energy-saving effect of the air conditioner.
[0052] 2. In the air conditioning control method for improving energy-saving effect by energy consumption prediction of the present invention, the difference between the temperature set by the user and the ambient temperature is used as the thermal comfort of the human body, so that the thermal comfort of the human body becomes a quantifiable standard, and the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption are obtained by using a genetic algorithm, so as to improve the energy-saving effect under the premise of satisfying the human body comfort. Therefore, this design can effectively improve the energy-saving effect by quantifying the thermal comfort of the human body, obtaining the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption.
[0053] 3. In the air conditioning control system of the present invention that improves energy-saving effect through energy consumption prediction, the sub-region data collection module is used to collect setting parameters, air conditioning energy parameters and real-time environmental parameters related to air conditioning control in the sub-region, and each air conditioner in the target region is correspondingly provided with an air conditioning control module, so that the air conditioning control method of the present invention can control the air conditioners in different sub-regions separately. Therefore, the present design can control the air conditioners in different sub-regions separately, effectively improving the application scope of the air conditioning control system. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] Figure 1 The present invention is a flow chart of an air conditioning control method for improving energy-saving effect through energy consumption prediction.
[0055] Figure 2 It is a structural schematic diagram of the air conditioning control method of the present invention for improving the energy-saving system through energy consumption prediction.
[0056] Figure 3 It is a layout diagram of the air conditioning control module in Example 1. DETAILED DESCRIPTION
[0057] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0058] Embodiment 1:
[0059] See also Figure 1 and Figure 3 , an air conditioning control method for improving energy saving effect by energy consumption prediction, the air conditioning control method comprising the following steps:
[0060] S1, data collection, collects setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area;
[0061] S2, build the model, build the initial model for energy consumption prediction of the target area through the multi-layer perception neural network algorithm,
[0062] S3, training the initial energy consumption prediction model based on historical data, wherein the historical data includes setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to train and verify the energy consumption prediction model until the prediction accuracy meets the requirements, at which time the model construction is completed;
[0063] S4, model solving, inputting high-precision weather forecast data of the target area in the future set period into the trained energy consumption prediction model, and solving to obtain the energy consumption prediction data of the target area in the future set period;
[0064] S5, through the target area energy consumption prediction data, combined with the set parameters, air conditioning energy parameters and real-time environmental parameters, the current air conditioning operation status is judged, and the corresponding control instructions are issued to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements. At this time, the current iteration is completed;
[0065] S6, model iteration and update. After completing the solution of the energy consumption prediction model, the newly collected weather data and various operating parameters of the air conditioner are added to the historical data, and the prediction model is trained again in S3 for the next iteration.
[0066] The air conditioning control related setting parameters collected in S1 are the air conditioning operating temperature, air conditioning operating mode and operating power set by the user;
[0067] The air conditioning energy usage parameters include energy usage data for at least one month in the past;
[0068] The real-time environmental parameters include the temperature and humidity of the indoor environment where the air conditioner is located;
[0069] The high-precision weather forecast data of the target area includes the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days;
[0070] The historical weather data includes hourly weather forecasts for the target area for at least one month in the past.
[0071] In S2, the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set and a test set. The training set is used to train the energy consumption prediction model of the target area, and the test set is used to verify the accuracy of the energy consumption prediction model. When the output energy consumption result is compared with the test set data and the accuracy is greater than 95%, the training of the energy consumption prediction model of the target area is completed. When the output energy consumption result is compared with the test set data and the accuracy is less than or equal to 95%, the process returns to S1 to increase the amount of data or adjust the model parameters to retrain the model, and re-execute the training steps until the prediction accuracy is greater than 95%.
[0072] In S2, 90% of the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set, and the remaining 10% of the data are divided into a test set.
[0073] In S4, the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days are used as input values to solve the energy consumption prediction model to obtain the hourly energy consumption data of the target area in the next seven days.
[0074] In S5, the difference between the temperature set by the user and the ambient temperature is taken as the thermal comfort of the human body, and the minimum value of the thermal comfort of the human body and the predicted energy consumption data of the target area is taken as the objective function. The genetic algorithm is used for iterative optimization to obtain the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption.
[0075] In S5, when the predicted energy consumption data of the target area is less than the set threshold, no operation is performed; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in cooling mode, the air conditioner set temperature is increased by one degree Celsius; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in heating mode, the air conditioner set temperature is reduced by one degree Celsius.
[0076] Embodiment 2:
[0077] See also Figure 2 , an air conditioning control system for improving energy-saving effect by energy consumption prediction, the air conditioning control system is used to implement the air conditioning control method for improving energy-saving effect by energy consumption prediction as described in Example 1;
[0078] The air conditioning control system comprises:
[0079] Data collection module, used to collect setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area;
[0080] The model building module builds an energy consumption prediction model for the target area through a multi-layer perception neural network algorithm, and trains and verifies the energy consumption prediction model through the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to obtain an energy consumption prediction model with prediction accuracy that meets the requirements;
[0081] The model solving module is used to use the collected high-precision weather forecast data of the target area as input values to solve the energy consumption prediction model and obtain the predicted energy consumption data of the target area;
[0082] The air conditioning control module is used to judge the current operation status of the air conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air conditioning control, the air conditioning energy parameters, and the real-time environmental parameters, and issue corresponding control instructions to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements;
[0083] The model iteration update module is used to complete the solution of an energy consumption prediction model, add the weather data of the current date to the historical weather data to retrain and verify the energy consumption prediction model until the prediction accuracy meets the requirements.
[0084] The data collection module includes a central data collection module and a plurality of sub-region data collection modules, wherein the central data collection module is used to collect high-precision weather forecast data and historical weather data of the target area, and the sub-region data collection modules are used to collect setting parameters related to air conditioning control, air conditioning energy parameters and real-time environmental parameters;
[0085] The sub-region data collection module is arranged in the sub-region where each air conditioner in the target region is located, and the sub-region is a spatially independent air conditioner operation region in the target region;
[0086] The air-conditioning control module includes a central control module and multiple air-conditioning control modules. The central control module is used to judge the current operation status of the air-conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air-conditioning control, the air-conditioning energy parameters, and the real-time environmental parameters. The air-conditioning control module is used to issue corresponding control instructions to control the air-conditioning so that the operation of the air-conditioning meets the energy-saving management requirements. Each air-conditioning in the target area is correspondingly provided with an air-conditioning control module.
[0087] Embodiment 3:
[0088] An air conditioning control device that improves energy saving effect by predicting energy consumption,
[0089] The device includes a processor and a memory; the memory is used to store computer program code and transmit the computer program code to the processor; the processor is used to execute the air conditioning control method for improving energy saving effect through energy consumption prediction as described in Example 1 according to the instructions in the computer program code.
[0090] The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiment. Any equivalent modifications or changes made by ordinary technicians in this field based on the contents disclosed by the present invention should be included in the protection scope recorded in the claims.
Claims
1. An air conditioning control method for improving energy saving effect by energy consumption prediction, characterized in that: The air conditioning control method comprises the following steps: S1, data collection, collecting setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area; S2, build the model, build the initial model for energy consumption prediction of the target area through the multi-layer perception neural network algorithm, S3, training the initial energy consumption prediction model based on historical data, wherein the historical data includes setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to train and verify the energy consumption prediction model until the prediction accuracy meets the requirements, at which time the model construction is completed; S4, model solving, inputting high-precision weather forecast data of the target area in the future set period into the trained energy consumption prediction model, and solving to obtain the energy consumption prediction data of the target area in the future set period; S5, through the target area energy consumption prediction data, combined with the set parameters, air conditioning energy parameters and real-time environmental parameters, the current air conditioning operation status is judged, and the corresponding control instructions are issued to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements. At this time, the current iteration is completed; S6, model iteration and update. After completing the solution of the energy consumption prediction model, the newly collected weather data and various operating parameters of the air conditioner are added to the historical data, and the prediction model is trained again in S3 for the next iteration.
2. The air conditioning control method for improving energy saving effect by energy consumption prediction according to claim 1, characterized in that: The air conditioning control related setting parameters collected in S1 are the air conditioning operating temperature, air conditioning operating mode and operating power set by the user; The air conditioning energy usage parameters include energy usage data for at least one month in the past; The real-time environmental parameters include the temperature and humidity of the indoor environment where the air conditioner is located; The high-precision weather forecast data of the target area includes the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days; The historical weather data includes hourly weather forecasts for the target area for at least one month in the past.
3. The air conditioning control method for improving energy saving effect by energy consumption prediction according to claim 2, characterized in that: In S2, the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set and a test set. The training set is used to train the energy consumption prediction model of the target area, and the test set is used to verify the accuracy of the energy consumption prediction model. When the output energy consumption result is compared with the test set data and the accuracy is greater than 95%, the training of the energy consumption prediction model of the target area is completed. When the output energy consumption result is compared with the test set data and the accuracy is less than or equal to 95%, the process returns to S1 to increase the amount of data or adjust the model parameters to retrain the model, and re-execute the training steps until the prediction accuracy is greater than 95%.
4. The air conditioning control method for improving energy saving effect by energy consumption prediction according to claim 3, characterized in that: In S2, 90% of the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data are divided into a training set, and the remaining 10% of the data are divided into a test set.
5. An air conditioning control method for improving energy saving effect by energy consumption prediction according to any one of claims 1 to 4, characterized in that: In S4, the hourly outdoor temperature, outdoor humidity and wind speed of the target area in the next seven days are used as input values to solve the energy consumption prediction model to obtain the hourly energy consumption data of the target area in the next seven days.
6. The air conditioning control method for improving energy saving effect by energy consumption prediction according to claim 5, characterized in that: In S5, the difference between the temperature set by the user and the ambient temperature is taken as the thermal comfort of the human body, and the minimum value of the thermal comfort of the human body and the predicted energy consumption data of the target area is taken as the objective function. The genetic algorithm is used for iterative optimization to obtain the optimal value of the thermal comfort of the human body and the optimal value of the air conditioning energy consumption.
7. The air conditioning control method for improving energy saving effect by energy consumption prediction according to claim 5, characterized in that: In S5, when the predicted energy consumption data of the target area is less than the set threshold, no operation is performed; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in cooling mode, the air conditioner set temperature is increased by one degree Celsius; when the predicted energy consumption data of the target area is greater than the set threshold and the air conditioner is in heating mode, the air conditioner set temperature is reduced by one degree Celsius.
8. An air conditioning control system for improving energy saving effect by energy consumption prediction, characterized in that: The air conditioning control system is used to implement the air conditioning control method for improving energy saving effect by energy consumption prediction as described in any one of claims 1 to 7; The air conditioning control system comprises: Data collection module, used to collect setting parameters related to air conditioning control, air conditioning energy parameters, real-time environmental parameters, high-precision weather forecast data and historical weather data of the target area; The model building module builds an energy consumption prediction model for the target area through a multi-layer perception neural network algorithm, and trains and verifies the energy consumption prediction model through the collected setting parameters, air conditioning energy parameters, real-time environmental parameters and historical weather data to obtain an energy consumption prediction model with prediction accuracy that meets the requirements; The model solving module is used to use the collected high-precision weather forecast data of the target area as input values to solve the energy consumption prediction model and obtain the predicted energy consumption data of the target area; The air conditioning control module is used to judge the current operation status of the air conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air conditioning control, the air conditioning energy parameters, and the real-time environmental parameters, and issue corresponding control instructions to control the air conditioning so that the operation of the air conditioning meets the energy-saving management requirements; The model iteration update module is used to complete the solution of an energy consumption prediction model, add the weather data of the current date to the historical weather data to retrain and verify the energy consumption prediction model until the prediction accuracy meets the requirements.
9. The air conditioning control system for improving energy saving effect by energy consumption prediction according to claim 8, characterized in that: The data collection module includes a central data collection module and a plurality of sub-region data collection modules, wherein the central data collection module is used to collect high-precision weather forecast data and historical weather data of the target area, and the sub-region data collection modules are used to collect setting parameters related to air conditioning control, air conditioning energy parameters and real-time environmental parameters; The sub-region data collection module is arranged in the sub-region where each air conditioner in the target region is located, and the sub-region is a spatially independent air conditioner operation region in the target region; The air-conditioning control module includes a central control module and multiple air-conditioning control modules. The central control module is used to judge the current operation status of the air-conditioning according to the predicted energy consumption data of the target area combined with the setting parameters related to the air-conditioning control, the air-conditioning energy parameters, and the real-time environmental parameters. The air-conditioning control module is used to issue corresponding control instructions to control the air-conditioning so that the operation of the air-conditioning meets the energy-saving management requirements. Each air-conditioning in the target area is correspondingly provided with an air-conditioning control module.
10. An air conditioning control device for improving energy saving effect by energy consumption prediction, characterized in that: The device comprises a processor and a memory; The memory is used to store computer program code and transmit the computer program code to the processor; The processor is used to execute the air conditioning control method for improving energy saving effect through energy consumption prediction as described in any one of claims 1 to 7 according to the instructions in the computer program code.
Citation Information
Patent Citations
Method for optimized setting of air conditioner temperature in office building
CN104896660A
Thermoelectric coupling network optimal power flow modeling method considering user comfort
CN111967683A
Central air conditioning system energy consumption prediction method, device and computing equipment
CN113970170A
Energy consumption prediction method and device for heating ventilation air conditioner
CN116205360A
Fuzzy control system of central air conditioner
CN203533800U
Cited By
Air conditioner energy-saving control method and system based on smart cloud analysis
CN119983484A
Air conditioner energy saving method and device based on neural network and genetic algorithm
CN119989863A
Energy management optimization method and system based on intelligent monitoring display
CN120176261A
