Method and device for determining regulation and control strategy, storage medium and electronic device

Abstract

The invention discloses a regulation and control strategy determination method and device, a storage medium and an electronic device, and the method comprises the steps: obtaining real-time parameter data and first weather forecast data corresponding to an energy management system, the first weather forecast data is weather forecast data in a first time period after first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time; predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data to obtain a prediction result; and determining a target regulation and control strategy of the energy management system according to the prediction result. According to the method, the problem that the accuracy of a prediction result and the effectiveness of a regulation and control strategy are limited due to the fact that real-time parameter data and high-precision weather forecast data cannot be fully integrated when an energy management system performs energy demand prediction and regulation and control strategy determination in related technologies can be solved.

Description

Technical Field

[0001] The present application relates to the field of energy, and more specifically, to a method and device for determining a control strategy, a storage medium, and an electronic device. Background Art

[0002] At present, all countries and regions are facing the challenge of coping with the climate crisis. Therefore, achieving green transformation of energy systems and improving energy efficiency are crucial to promoting environmental sustainable development. As an important part of the energy system, the optimization of the operation mode and efficiency of the power system is of great significance to achieving sustainable development goals. With the widespread application of renewable energy and the continuous growth of electricity demand, the power system faces complexity and uncertainty in the process of energy conversion, storage and distribution. Therefore, improving the operating efficiency and responsiveness of the power system under different environmental conditions and optimizing the performance of the power system have become the hot spots of current research.

[0003] In the power system, energy demand forecasting is a key link in achieving energy efficiency improvement. Accurate energy demand forecasting can help power system operators plan power supply and dispatch strategies in advance to cope with future changes in energy demand. However, traditional energy demand forecasting methods often fail to capture the complexity and dynamics of energy demand, which leads to reduced accuracy of forecast results.

[0004] In the related technology, some studies have attempted to use convolutional neural networks (CNN models) to predict energy demand. For example, CN01 discloses a method for predicting energy demand based on convolutional neural networks. This method aims at predicting the energy demand of power grids and achieves accurate prediction of energy demand by designing a specific network structure and optimization strategy. CN02 proposes a CNN model for predicting wind power generation. By combining historical wind speed data and real-time wind speed data, it effectively predicts the changing trend of wind power generation.

[0005] However, most of the prediction methods in related technologies rely on artificially designed features, and ignore the impact of complex environmental conditions corresponding to the energy management system (such as temperature, humidity, wind speed, light, etc.) on energy demand, and are unable to fully integrate real-time parameter data with high-precision meteorological forecast data, resulting in limited accuracy of prediction results and effectiveness of control strategies.

[0006] Regarding the relevant technologies, energy management systems are often unable to fully integrate real-time parameter data and high-precision meteorological forecast data when predicting energy demand and determining control strategies, resulting in limited accuracy of prediction results and effectiveness of control strategies. No effective solution has yet been found. Summary of the invention

[0007] The embodiments of the present application relate to a method and device for determining a control strategy, a storage medium and an electronic device. Through the embodiments of the present application, it is possible to solve the problem in the related art that the energy management system is often unable to fully integrate real-time parameter data and high-precision meteorological forecast data when performing energy demand forecasting and control strategy determination, resulting in limited accuracy of the prediction results and effectiveness of the control strategy.

[0008] According to an embodiment of the present application, a method for determining a control strategy is provided, including: obtaining real-time parameter data and first meteorological forecast data corresponding to an energy management system, wherein the first meteorological forecast data is meteorological forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operating data of the energy management system at the first time; predicting energy demand data corresponding to the energy management system based on the real-time parameter data and the first meteorological forecast data to obtain a prediction result; and determining a target control strategy of the energy management system based on the prediction result.

[0009] In an exemplary embodiment, energy demand data corresponding to the energy management system is predicted based on the real-time parameter data and the first meteorological forecast data to obtain a prediction result, including: obtaining historical parameter data and second meteorological forecast data corresponding to the energy management system, wherein the second meteorological forecast data is meteorological forecast data within a second time period after a second time corresponding to the historical parameter data; training a first algorithm model based on the historical parameter data and the second meteorological forecast data to obtain a trained first algorithm model; inputting the real-time parameter data and the first meteorological forecast data into the trained first algorithm model, so that the trained first algorithm model predicts the energy demand corresponding to the energy management system and outputs the prediction result.

[0010] In an exemplary embodiment, determining a target control strategy corresponding to the energy management system based on the prediction results includes: obtaining operating rules and constraints corresponding to the energy management system; inputting the operating rules and the prediction results into a second algorithm model so that the second algorithm model outputs multiple first control strategies corresponding to the energy management system; and determining the target control strategy among the multiple first control strategies based on the constraints.

[0011] In an exemplary embodiment, after determining the target control strategy corresponding to the energy management system according to the prediction result, the method further includes: performing parameter control on the energy management system according to the target control strategy, and obtaining the energy consumption data of the energy management system in the first time period after the parameter control; comparing the prediction result with the energy consumption data, and determining whether to update the target control strategy based on the comparison result.

[0012] In an exemplary embodiment, determining whether to update the target control strategy based on the comparison result includes: determining the degree of match between the prediction result and the energy consumption data based on the comparison result; determining not to update the target control strategy when the comparison result indicates that the degree of match is greater than or equal to a preset threshold, and the energy consumption data is less than the energy demand data corresponding to the prediction result; updating the target control strategy to obtain an updated target control strategy when the comparison result indicates that the degree of match is less than the preset threshold, and / or the energy consumption data is greater than or equal to the energy demand data corresponding to the prediction result.

[0013] In an exemplary embodiment, the target control strategy is updated to obtain an updated target control strategy, including: adjusting parameters in a second algorithm model according to the matching degree to update the second algorithm model, wherein the second algorithm model is used to output the target control strategy; determining multiple second control strategies corresponding to the energy management system according to the updated second algorithm model; and determining the updated target control strategy among the multiple second control strategies.

[0014] According to another embodiment of the embodiment of the present application, a device for determining a control strategy is also provided, including: an acquisition module, used to acquire real-time parameter data and first meteorological forecast data corresponding to an energy management system, wherein the first meteorological forecast data is meteorological forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operating data of the energy management system at the first time; a prediction module, used to predict energy demand data corresponding to the energy management system based on the real-time parameter data and the first meteorological forecast data to obtain a prediction result; a determination module, used to determine a target control strategy of the energy management system based on the prediction result.

[0015] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above method when running.

[0016] According to another aspect of the embodiments of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method through the computer program.

[0017] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, wherein the computer program is executed by a processor to perform the method.

[0018] In an embodiment of the present application, the operation data of the energy management system at the first time, that is, the real-time parameter data, and the first weather forecast data in the first time period after the first time are obtained; the energy demand data corresponding to the energy management system is predicted according to the real-time parameter data and the first weather forecast data to obtain the prediction result; the target control strategy of the energy management system is determined according to the prediction result. That is to say, the embodiment of the present application integrates the real-time parameter data and the first weather forecast data, and then predicts the energy demand of the energy management system, and determines the target control strategy of the energy management system according to the prediction result. Through the embodiment of the present application, the problem in the related technology that the energy management system is often unable to fully integrate the real-time parameter data and the high-precision weather forecast data when predicting the energy demand and determining the control strategy, resulting in the accuracy of the prediction result and the effectiveness of the control strategy being limited, can be solved, and the real-time parameter data and the high-precision weather forecast data are fully integrated to improve the accuracy of the prediction result and the effectiveness of the control strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal of a method for determining a control strategy in an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for determining a control strategy according to an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a digital twin platform according to an optional embodiment of the present application;

[0023] Figure 4 It is a structural block diagram of a device for determining a control strategy according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices; "plurality" means two or more.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or similar computing device or cloud platform or independent physical server or software platform, wherein the above software platform is run through one or more servers. Taking running on a computer terminal as an example, Figure 1 1 is a hardware structure block diagram of a computer terminal for determining a control strategy according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data. In an exemplary embodiment, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. A person skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 A different configuration with more features is shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the methods in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, the above-mentioned methods are implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] In this embodiment, a method for determining a control strategy is provided, which is applied to the above-mentioned computer terminal. Figure 2 : is a flow chart of a method for determining a control strategy according to an embodiment of the present application, the process comprising the following steps:

[0030] Step S202, acquiring real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time;

[0031] The first time mentioned above may be the current time, and the real-time parameter data mentioned above may be the heat data, flow data, temperature data, etc. corresponding to the energy management system at the current time.

[0032] Step S204, predicting the energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data to obtain a prediction result;

[0033] Step S206: determining a target control strategy of the energy management system according to the prediction result.

[0034] Among them, the above-mentioned target control strategy can be: adjusting valve opening, optimizing heating / cooling time, etc., and the target control strategy can achieve efficient use of energy and comfortable control of the indoor environment.

[0035] In an embodiment of the present application, the operation data of the energy management system at the first time, that is, the real-time parameter data, and the first weather forecast data in the first time period after the first time are obtained; the energy demand data corresponding to the energy management system is predicted according to the real-time parameter data and the first weather forecast data to obtain the prediction result; the target control strategy of the energy management system is determined according to the prediction result. That is to say, the embodiment of the present application integrates the real-time parameter data and the first weather forecast data, and then predicts the energy demand of the energy management system, and determines the target control strategy of the energy management system according to the prediction result. Through the embodiment of the present application, the problem in the related technology that the energy management system is often unable to fully integrate the real-time parameter data and the high-precision weather forecast data when predicting the energy demand and determining the control strategy, resulting in the accuracy of the prediction result and the effectiveness of the control strategy being limited, can be solved, and the real-time parameter data and the high-precision weather forecast data are fully integrated to improve the accuracy of the prediction result and the effectiveness of the control strategy.

[0036] Optionally, the above-mentioned step S204 predicts the energy demand data corresponding to the energy management system according to the real-time parameter data and the first meteorological forecast data to obtain a prediction result, including: obtaining historical parameter data and second meteorological forecast data corresponding to the energy management system, wherein the second meteorological forecast data is meteorological forecast data within a second time period after the second time corresponding to the historical parameter data; training a first algorithm model according to the historical parameter data and the second meteorological forecast data to obtain a trained first algorithm model; inputting the real-time parameter data and the first meteorological forecast data into the trained first algorithm model, so that the trained first algorithm model predicts the energy demand corresponding to the energy management system and outputs the prediction result.

[0037] It is understandable that energy demand forecasting is a core step to ensure efficient and economical operation of the system. The embodiment of the present application combines real-time parameter data with high-precision weather forecast data and uses advanced intelligent algorithm models to forecast energy demand to obtain more accurate forecast results. Specifically:

[0038] The operation data of the energy management system at various historical moments in the past are obtained from the digital twin platform, including historical parameter data such as heat output, fluid flow, indoor temperature, and the second weather forecast data after the corresponding historical moment. For example, assuming that it is October 10, 2023, the weather data and historical parameter data from October 10 to October 15, 2022 (i.e., the second time period) can be collected, and these data will serve as the basis for training the first algorithm model.

[0039] The above historical parameter data and the second weather forecast data are used to train the first algorithm model. The first algorithm model can be based on machine learning methods, such as regression analysis, neural networks, or support vector machines. The purpose of training the first algorithm model is to learn and understand the inherent relationship between system operation and meteorological conditions, so as to be able to predict energy demand based on current and future meteorological conditions. For example, the first algorithm model will learn that when the outdoor temperature drops, the heat load inside the building will increase, and the operating parameters of the heating equipment need to be adjusted to meet the demand.

[0040] After the model training is completed, the real-time parameter data at the current moment and the first weather forecast data for a period of time in the future (such as temperature and humidity changes in the next 24 hours) are input into the trained first algorithm model. The trained first algorithm model calculates the energy demand forecast value of the energy management system at a specific time point based on the current system status and future weather conditions.

[0041] The prediction results output by the first algorithm model will be used to formulate target control strategies. For example, if the prediction results show that the temperature will drop significantly in the future, the operation time of the heating equipment may be increased or the valve opening may be adjusted in advance to ensure the stability of the indoor temperature and the comfort of the users. At the same time, the prediction results can also help the system optimize energy distribution and reduce operating costs. For example, when it is predicted that the supply of renewable energy (such as solar energy) will increase, these resources will be used first.

[0042] Through the above steps, it is possible to use historical and real-time data, combined with weather forecast information, to train a more accurate first algorithm model, thereby achieving high-precision prediction of energy demand. This method not only improves the accuracy of the prediction, but also improves the flexibility and effectiveness of the control strategy, which helps the energy management system to achieve intelligent management, improve energy utilization efficiency, and reduce operating costs.

[0043] Optionally, the above-mentioned step S206 of determining the target control strategy corresponding to the energy management system according to the prediction results includes: obtaining operating rules and constraints corresponding to the energy management system; inputting the operating rules and the prediction results into a second algorithm model so that the second algorithm model outputs multiple first control strategies corresponding to the energy management system; and determining the target control strategy among the multiple first control strategies according to the constraints.

[0044] It is understandable that formulating a target control strategy based on the forecast results of energy demand is an important step to ensure efficient system operation and optimal energy utilization. Specifically:

[0045] It is necessary to obtain the corresponding operating rules and constraints of the energy management system, where: the operating rules usually refer to the basic principles and requirements for the operation of the energy management system, for example, ensuring that the user's indoor temperature is maintained within the set comfort range, or giving priority to the use of renewable energy, etc. Constraints include hard restrictions on the operation of the energy management system, such as the maximum output power of the equipment, the safe range of operation, etc., as well as soft constraints related to cost and environmental protection, such as minimizing energy consumption costs and controlling carbon emissions.

[0046] For example, operating rules may include reducing heating intensity at night in response to lower user demand; constraints may include not exceeding the building's heat load limit and ensuring that the control strategy is implemented within the energy budget.

[0047] The prediction results and operating rules are then input into the second algorithm model, which is a decision optimization model. Its purpose is to output a series of feasible first control strategies based on the predicted energy demand and operating rules. The prediction results (i.e., the energy demand forecast for a period of time in the future) are combined with the operating rules to generate a variety of possible control strategy solutions through calculation and simulation. For example, three first control strategies may be calculated to increase the heating intensity by 10%, 20%, and 30% respectively when an increase in demand is predicted.

[0048] After obtaining multiple first control strategies, these first control strategies are further screened and optimized according to the constraints. The constraints not only include the physical limitations of equipment operation, but also consider multi-dimensional factors such as cost, environmental protection, and user satisfaction. Through comprehensive evaluation, the target control strategy that best meets the constraints and optimizes system operation is selected from multiple first control strategies. For example, the control strategy with the lowest cost and carbon emissions within the target range while meeting the indoor temperature comfort level may be selected as the target strategy.

[0049] That is, in the embodiment of the present application, by combining the operation rules with the prediction results, the second algorithm model is used to generate multiple first control strategies, and then the best target control strategy is selected according to the constraint conditions. This strategy formulation method based on prediction, rules and constraints not only takes into account the efficiency and economy of system operation, but also ensures the safety and environmental protection of operation, realizes the intelligent control of the energy management system, and ensures the optimal comprehensive performance of the system.

[0050] Optionally, after determining the target control strategy corresponding to the energy management system according to the prediction result in the above step S206, the method also includes: performing parameter control on the energy management system according to the target control strategy, and obtaining the energy consumption data of the energy management system in the first time period after the parameter control; comparing the prediction result with the energy consumption data, and determining whether to update the target control strategy based on the comparison result.

[0051] Among them, determining whether to update the target control strategy according to the comparison result includes: determining the matching degree between the prediction result and the energy consumption data according to the comparison result; when the comparison result indicates that the matching degree is greater than or equal to a preset threshold, and the energy consumption data is less than the energy demand data corresponding to the prediction result, determining not to update the target control strategy; when the comparison result indicates that the matching degree is less than the preset threshold, and / or the energy consumption data is greater than or equal to the energy demand data corresponding to the prediction result, updating the target control strategy to obtain an updated target control strategy.

[0052] It is understandable that after the implementation of the target control strategy, its effect will be continuously monitored, and based on the comparison between the predicted results and the actual energy consumption data, the effectiveness and adaptability of the control strategy will be intelligently evaluated to determine whether it needs to be updated. Specifically:

[0053] Once the target control strategy is determined, the relevant parameters of the energy management system, such as the operating time of the heating or cooling equipment, valve opening, etc., can be automatically adjusted to achieve the predicted energy demand level. For example, suppose the forecast results show that energy demand will increase by 5% in the next 24 hours due to the decrease in outdoor temperature. The target control strategy may adjust the operating time of the heating equipment from 8 hours per day to 8.5 hours to meet the predicted energy demand.

[0054] After implementing the target control strategy for a period of time, the corresponding energy consumption data can be collected, which usually includes the actual energy consumption value after control, indoor temperature changes, etc. For example, after implementing the above adjusted operation strategy for 24 hours, the actual energy consumption is recorded to evaluate the effect of the control strategy.

[0055] The prediction results before implementing the control strategy are compared and analyzed with the actual energy consumption data collected to evaluate the matching degree and effectiveness of the control strategy. This comparison process usually calculates the difference between the predicted energy consumption and the actual energy consumption, as well as the deviation between the actual indoor temperature and the preset temperature target.

[0056] Through comparative analysis, we can determine the matching degree between the prediction results and the actual energy consumption data, as well as the implementation effect of the control strategy. Specifically, we decide whether to update the control strategy based on the following two situations:

[0057] (1) If the comparison results show that the match between the predicted energy demand and the actual energy consumption data is higher than or equal to the preset match threshold (such as 90%), and the actual energy consumption is lower than or equal to the predicted energy demand, this indicates that the target control strategy is well executed and does not need to be updated. For example, assuming that the preset match threshold is 90%, and the actual energy consumption is 95% of the predicted demand, the system considers that the prediction is accurate and the strategy is effective, and the existing strategy remains unchanged.

[0058] (2) If the comparison result indicates that the matching degree is lower than the preset threshold, or the actual energy consumption is significantly higher than the predicted energy demand, this indicates that the current control strategy may not be able to effectively respond to environmental changes and needs to be updated. For example, if the actual energy consumption exceeds the predicted demand by more than 10%, or the matching degree is only 80%, the existing strategy will be considered invalid and needs to be adjusted.

[0059] According to the actual operation effect and environmental changes, the target control strategy is adjusted, such as fine-tuning parameters such as equipment operation time and valve opening, to achieve better energy consumption control and indoor temperature stability. The adjusted strategy will be implemented again and subsequent comparative analysis will be carried out to form a closed-loop process of continuous optimization.

[0060] For example, suppose the intelligent control system predicts that a commercial building's energy demand will increase by 20% in the coming week due to a drop in external temperature. Based on this prediction, a target control strategy is formulated, which is to increase the operating time of the heating equipment. One week later, the system compares the predicted results with the actual energy consumption data. If it is found that the actual energy consumption has only increased by 15% and the indoor temperature is maintained within the preset comfort range, this indicates that the prediction is slightly high, but the control strategy is effective, and the system may not adjust the strategy. On the contrary, if the actual energy consumption increases by 25%, exceeding the predicted value, or the indoor temperature does not reach the preset target, this indicates that the control strategy may need to be optimized. The system will update the target control strategy based on the actual operating results, such as further adjusting the operating time or adding other energy-saving measures to improve the adaptability and effectiveness of the strategy.

[0061] The intelligent control system can intelligently optimize the control strategy based on actual operating results and environmental changes to ensure the efficiency of system operation and user satisfaction, while promoting the rational use of energy and the realization of environmental protection goals.

[0062] Among them, updating the target control strategy to obtain an updated target control strategy includes: adjusting the parameters in the second algorithm model according to the matching degree to update the second algorithm model, wherein the second algorithm model is used to output the target control strategy; determining multiple second control strategies corresponding to the energy management system according to the updated second algorithm model; and determining the updated target control strategy among the multiple second control strategies.

[0063] It is understandable that in order to continuously optimize the energy demand forecast and control strategy formulation, the parameters of the second algorithm model can be dynamically adjusted and updated according to the matching degree between the forecast results and the actual energy consumption data to improve the model's forecast accuracy and the effectiveness of strategy formulation. Specifically:

[0064] After comparing the prediction results with the actual energy consumption data, the matching information obtained will be used to feedback and optimize the second algorithm model. As the core of strategy generation, the adjustment of the parameters of the second algorithm model directly affects the accuracy of the output control strategy. According to the comparison results of the matching degree with the preset threshold, the model parameters, such as weight coefficient and learning rate, are intelligently adjusted to improve the prediction accuracy and adaptability of strategy formulation.

[0065] For example, if the match is lower than a preset threshold, the weights of certain parameters may be increased to reduce sensitivity to specific inputs (such as wind speed) to reduce prediction errors; conversely, if the match is higher than the threshold, the parameters may be fine-tuned to maintain the accuracy of the current strategy formulation.

[0066] After the second algorithm model parameters are adjusted and updated, the second algorithm model is re-run to generate a series of new second control strategies. These strategies are generated based on historical operating data, the latest weather forecast, real-time energy consumption, and the adjusted model parameters. Each second control strategy includes fine-tuning of system parameters to more accurately respond to changes in energy demand.

[0067] For example, the updated second algorithm model may output strategies such as adjusting fluid flow, optimizing equipment operation cycle, and dynamically adjusting indoor and outdoor temperature difference compensation based on higher prediction accuracy.

[0068] From the multiple second control strategies output by the updated second algorithm model, the effectiveness and feasibility of each strategy will be comprehensively evaluated based on the latest real-time parameter data, operating rules and constraints, and an updated target control strategy will be finally determined. This strategy will optimize energy utilization, ensure indoor temperature comfort, and take into account multiple factors such as cost, safety and environmental protection.

[0069] For example, if a certain strategy in the updated second control strategy can significantly reduce energy consumption while ensuring comfortable indoor temperature and does not violate the constraints of safety and equipment operation, then this strategy can be determined as the updated target control strategy.

[0070] Through this series of feedback loops and model optimization processes, each adjustment of the parameters of the second algorithm model means that the system is self-optimizing and upgrading the prediction model and control strategy based on actual operation data and environmental feedback information. This not only improves the operating efficiency of the energy management system, but also promotes the rational use of energy and energy conservation and emission reduction, providing technical support for the realization of green and intelligent energy management.

[0071] In order to better understand the process of the method for determining the above-mentioned control strategy, the method for determining the above-mentioned control strategy is described below in combination with an optional embodiment, but is not used to limit the technical solution of the embodiment of the present application.

[0072] The optional embodiment of the present application provides an intelligent control system based on intelligent algorithms and visual monitoring, wherein the intelligent algorithm, also known as "soft computing", is inspired by the laws of nature (biology) and imitates its principles to solve problems. With the increase in data volume and the complexity of monitoring requirements, traditional monitoring methods have been unable to meet the needs. Data visualization technology is an important means of monitoring and analysis.

[0073] The intelligent control system based on intelligent algorithms and visual monitoring proposed in the optional embodiment of the present application organically combines the two to achieve intelligent management and control of complex systems. The intelligent control system based on intelligent algorithms and visual monitoring uses intelligent algorithms to analyze and process the collected data to discover potential problems and trends; at the same time, the analysis results are intuitively displayed to the user through visual monitoring technology to help the user make decisions quickly. This technical integration not only improves the intelligence level of the system, but also enhances the reliability and stability of the system.

[0074] In the process of building an efficient energy management system, historical data (covering heating and cooling operation data at various historical moments in the past, i.e. historical parameter data) are fully utilized as valuable resources, and accurate intelligent algorithm models (i.e. the first algorithm model after training) are trained through advanced machine learning and artificial intelligence technologies. These models can not only capture the inherent laws of system operation, but also learn and adapt to the impact of external environmental changes on energy demand.

[0075] In order to further improve the accuracy of prediction and control, the intelligent control system based on intelligent algorithms and visual monitoring accesses IoT measurement point data (i.e. real-time parameter data) from the digital twin platform in real time, including but not limited to heat output, fluid flow, indoor temperature and outdoor environmental parameters. These real-time data are combined with weather forecast data (e.g. weather forecast for the next few hours to days, i.e. first weather forecast data) and passed as input to the intelligent algorithm model. Based on this comprehensive information, the intelligent algorithm model accurately predicts the energy demand at the current moment and automatically calculates the optimal control strategy (i.e. target control strategy), such as adjusting valve opening, optimizing heating / cooling time, etc., to achieve efficient use of energy and comfortable control of the indoor environment.

[0076] in, Figure 3 is a schematic diagram of a digital twin platform according to an optional embodiment of the present application, such as Figure 3 As shown, the digital twin platform includes:

[0077] There are four modules: technical middle platform, microservice architecture, business middle platform and operation and maintenance management, among which:

[0078] The technical middle platform represents the underlying technical support and services of the intelligent control system based on intelligent algorithms and visual monitoring, including access control, authority management, API management, map management, and middleware management. It mainly involves the infrastructure and security control of the intelligent control system based on intelligent algorithms and visual monitoring, such as the setting of access rights and the provision of API services, which are the basis for realizing the functions of the intelligent control system.

[0079] The microservice architecture includes modules such as load balancing, registration center, real-time monitoring and service governance, which are closely related to the collection and processing of real-time data (i.e. real-time parameter data) obtained by the intelligent control system based on intelligent algorithms and visual monitoring. The real-time monitoring module is responsible for receiving real-time data from IoT measurement points, such as heat output, fluid flow, indoor temperature, etc., and passing these data to the business middle platform for further analysis and processing. Service governance ensures efficient collaboration between microservices, as well as system stability and performance.

[0080] The business platform includes digital portal, smart monitoring, smart operation, smart operation and maintenance, smart services and third-party subsystems. The smart monitoring module collects and analyzes real-time data and weather forecast data, while the smart operation module uses intelligent algorithms for accurate prediction and automatic control. The digital portal provides an interactive interface between users and the intelligent control system based on intelligent algorithms and visual monitoring, visually displaying system status and data. Smart operation and maintenance and smart services focus on system maintenance and user services respectively.

[0081] Operation and maintenance management involves operation and maintenance monitoring, system security, alarm management, performance monitoring and inspection management of the intelligent control system based on intelligent algorithms and visual monitoring, ensuring the stability and security of the operation of the intelligent control system based on intelligent algorithms and visual monitoring. It is mainly used for system monitoring and maintenance measures, such as real-time monitoring of system status, timely discovery and handling of potential problems, to maintain efficient operation of the system.

[0082] The virtual representation of the physical system and the intuitive display of the real-time status achieved through the visual monitoring platform are actually the application of digital twin technology. Digital twin technology not only realizes the intuitive display of real-time data, including the specific values ​​of each measuring point, change trend charts, etc., but also presents the physical world's heating / cooling system in a virtual form on the screen through three-dimensional modeling technology. This immersive experience allows managers to easily monitor the overall operating status of the system and discover potential problems in a timely manner.

[0083] The intelligent control system based on intelligent algorithms and visual monitoring can simultaneously display predicted data and real-time data, and conduct comparative analysis. Through intuitive charts and animation effects, managers can clearly see the implementation effects of control measures, such as room temperature fluctuations, energy consumption reduction, etc. In addition, the intelligent control system based on intelligent algorithms and visual monitoring has also added a control effect feedback mechanism, which compares the actual operating effect with the predicted value, automatically evaluates the effectiveness of the control strategy, and updates the intelligent algorithm model in real time accordingly. This process forms a closed-loop optimization system, which continuously promotes the self-improvement and performance improvement of the algorithm model, and ensures the continuous optimization and efficient operation of the energy management system.

[0084] The following effects can be achieved through the intelligent control system of the intelligent algorithm and visual monitoring of the optional embodiment of the present application:

[0085] 1. Efficient and accurate prediction and control.

[0086] Real-time data processing and analysis: Intelligent algorithms can receive and process IoT measurement point data (such as heat, flow, temperature, etc.) and weather forecast data obtained from the digital twin platform in real time, achieving accurate predictions for the current moment and the future.

[0087] Intelligent decision-making and control: Based on real-time data and prediction results, intelligent algorithms can automatically calculate the optimal control strategy, such as adjusting the operating parameters of heating / cooling equipment to achieve efficient use of energy and precise control of the indoor environment.

[0088] 2. Intuitive and easy-to-understand visual display.

[0089] Real-time data monitoring: Through the visual interface, operators can intuitively see the real-time data of each measuring point, change trends and the overall operating status of the system.

[0090] Prediction and comparative analysis: The system can compare and analyze the predicted data with the real-time data, and intuitively display the control effects in the form of charts, animations, etc., to help operators quickly understand the effectiveness of control measures.

[0091] 3. Enhanced interactivity and feedback mechanism.

[0092] Human-computer interaction: The visual monitoring platform provides a friendly human-computer interaction interface, allowing operators to easily view system status, adjust parameters and receive alarm information.

[0093] Feedback optimization: Through the real-time feedback mechanism, operators can tune the intelligent algorithm model according to the actual operation of the system, and continuously improve the model's prediction accuracy and control effect.

[0094] 4. Improve the intelligence level of the system.

[0095] Improved automation: The combination of intelligent algorithms and visual monitoring enables the system to automatically complete processes such as prediction, regulation and feedback, reducing the need for human intervention.

[0096] Intelligent decision support: The system can provide intelligent decision support for operators, helping them make more reasonable and scientific control decisions.

[0097] 5. Optimize resource allocation and reduce energy consumption.

[0098] Refined management: Through the intelligent control system, refined management of energy supply and demand can be achieved, resource allocation can be optimized, and energy utilization efficiency can be improved.

[0099] Energy conservation and emission reduction: Accurate prediction and regulation can help reduce unnecessary energy waste, reduce energy consumption and emissions, and meet the requirements of green development.

[0100] That is, the optional embodiment of the present application utilizes machine learning and artificial intelligence technology, combined with historical data and real-time IoT measurement point data, to train an accurate intelligent algorithm model to achieve accurate prediction of energy demand and calculation of the optimal control strategy; at the same time, in terms of visualization, the operating status of the physical system is intuitively presented on the screen in a virtual form. Through intuitive charts, animations, and trend lines, managers can instantly observe the system's real-time data, prediction results, and the implementation effects of control measures, greatly enhancing the observability and controllability of the system.

[0101] That is to say, the optional embodiment of the present application can comprehensively consider complex and changeable meteorological conditions (such as outdoor temperature, humidity, wind speed, wind direction, solar radiation intensity, etc.) and specific heating area, building materials, thermal insulation performance, personnel activity intensity and other multi-dimensional factors through advanced intelligent algorithms, and make accurate predictions, thereby scientifically calculating the required heat consumption. This prediction not only improves energy utilization efficiency, but also ensures the economy and environmental protection of the heating system.

[0102] Based on the prediction, the intelligent control system based on intelligent algorithms and visual monitoring integrates an automatic control mechanism, which intelligently adjusts the opening of the heating valve by real-time monitoring of the difference between the indoor temperature and the preset temperature. This process achieves accurate tracking and automatic control of the temperature return, ensuring that the room temperature in different areas and rooms can be kept consistent, and improving the user's comfort experience.

[0103] In addition, the intelligent control system based on intelligent algorithms and visual monitoring is also equipped with a powerful visual monitoring platform, which displays important information such as the operating status, energy consumption data, and equipment health of the heating system in an intuitive and easy-to-understand graphical interface. Managers can not only remotely observe the real-time operation of the system through the platform, but also promptly discover potential problems and issue early warnings, reducing the workload of on-site inspections. At the same time, the platform also supports flexible configuration modification functions, allowing managers to adjust system parameters and optimize operating strategies according to actual needs to adapt to different seasonal changes and user needs. This intelligent control system predicts heat consumption through intelligent algorithms, automatically controls valves to ensure consistent room temperature, and combines with a visual monitoring platform for efficient management. It not only improves the intelligence level of the heating system, but also significantly improves energy utilization efficiency and reduces operating costs, bringing users a more comfortable, convenient, and environmentally friendly heating experience.

[0104] In summary, the optional embodiments of the present application deeply integrate intelligent algorithms with visual monitoring, which not only transforms the originally abstract and complex algorithm logic and execution effects into intuitive and easy-to-understand graphics and interfaces, but also enables operators with non-technical backgrounds to quickly grasp the system status and control results. Through a highly interactive visualization platform, operators can instantly observe the dynamic comparison between algorithm predictions and actual operating data, and intuitively perceive the direct effects of control measures. This intuitive feedback mechanism greatly enhances the sense of participation and decision-making ability of operators, enabling them to flexibly adjust parameters or put forward new optimization suggestions based on actual operating conditions, and then continuously optimize and improve the intelligent algorithm model through feedback loops. This process not only promotes the self-learning and evolution of the algorithm model, but also strengthens the collaboration and interaction between people and systems, and jointly promotes the intelligence level of energy management systems to new heights.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0106] The present application also provides a structural block diagram of a device for determining a control strategy. Figure 4 is a structural block diagram of a device for determining a control strategy according to an embodiment of the present application; Figure 4 As shown, including:

[0107] An acquisition module 42 is used to acquire real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time;

[0108] A prediction module 44, configured to predict energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data, so as to obtain a prediction result;

[0109] The determination module 46 is used to determine the target control strategy of the energy management system according to the prediction result.

[0110] Through the above-mentioned device, the operation data of the energy management system at the first time, that is, the real-time parameter data, and the first meteorological forecast data in the first time period after the first time are obtained; the energy demand data corresponding to the energy management system is predicted according to the real-time parameter data and the first meteorological forecast data to obtain the prediction result; the target control strategy of the energy management system is determined according to the prediction result. That is to say, the embodiment of the present application integrates the real-time parameter data and the first meteorological forecast data, and then predicts the energy demand of the energy management system, and determines the target control strategy of the energy management system according to the prediction result. Through the embodiment of the present application, the problem in the related technology that the energy management system is often unable to fully integrate the real-time parameter data and the high-precision meteorological forecast data when predicting the energy demand and determining the control strategy, resulting in the accuracy of the prediction result and the effectiveness of the control strategy being limited, can be solved, and the real-time parameter data and the high-precision meteorological forecast data are fully integrated to improve the accuracy of the prediction result and the effectiveness of the control strategy.

[0111] In an exemplary embodiment, the prediction module 44 is also used to obtain historical parameter data and second meteorological forecast data corresponding to the energy management system, wherein the second meteorological forecast data is meteorological forecast data within a second time period after the second time corresponding to the historical parameter data; the first algorithm model is trained according to the historical parameter data and the second meteorological forecast data to obtain a trained first algorithm model; the real-time parameter data and the first meteorological forecast data are input into the trained first algorithm model, so that the trained first algorithm model predicts the energy demand corresponding to the energy management system and outputs the prediction result.

[0112] In an exemplary embodiment, the determination module 46 is also used to obtain the operating rules and constraints corresponding to the energy management system; input the operating rules and the prediction results into the second algorithm model so that the second algorithm model outputs multiple first control strategies corresponding to the energy management system; and determine the target control strategy among the multiple first control strategies according to the constraints.

[0113] In an exemplary embodiment, the determination module 46 is also used to perform parameter control on the energy management system according to the target control strategy, and obtain the energy consumption data of the energy management system in the first time period after the parameter control; compare the prediction result with the energy consumption data, and determine whether to update the target control strategy based on the comparison result.

[0114] In an exemplary embodiment, the determination module 46 is also used to determine the degree of match between the prediction result and the energy consumption data based on the comparison result; when the comparison result indicates that the degree of match is greater than or equal to a preset threshold, and the energy consumption data is less than the energy demand data corresponding to the prediction result, determine not to update the target control strategy; when the comparison result indicates that the degree of match is less than the preset threshold, and / or the energy consumption data is greater than or equal to the energy demand data corresponding to the prediction result, update the target control strategy to obtain an updated target control strategy.

[0115] In an exemplary embodiment, the determination module 46 is also used to adjust the parameters in the second algorithm model according to the matching degree to update the second algorithm model, wherein the second algorithm model is used to output the target control strategy; determine multiple second control strategies corresponding to the energy management system according to the updated second algorithm model; and determine the updated target control strategy among the multiple second control strategies.

[0116] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.

[0117] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0118] S1, acquiring real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time;

[0119] S2, predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data to obtain a prediction result;

[0120] S3, determining a target control strategy of the energy management system according to the prediction result.

[0121] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0122] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0123] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0124] S1, acquiring real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time;

[0125] S2, predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data to obtain a prediction result;

[0126] S3, determining a target control strategy of the energy management system according to the prediction result.

[0127] An embodiment of the present application further provides a computer program product, including a computer program, which is used by a processor to execute the steps in any of the above method embodiments.

[0128] Optionally, in this embodiment, the computer program product may be executed by a processor to perform the following steps:

[0129] S1, acquiring real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time;

[0130] S2, predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first weather forecast data to obtain a prediction result;

[0131] S3, determining a target control strategy of the energy management system according to the prediction result.

[0132] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0133] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0134] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0135] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a control strategy, characterized in that: include: Acquire real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time; Predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first meteorological forecast data to obtain a prediction result; The target control strategy of the energy management system is determined according to the prediction result.

2. The method for determining the control strategy according to claim 1, characterized in that: Predicting energy demand data corresponding to the energy management system according to the real-time parameter data and the first meteorological forecast data to obtain a prediction result includes: Acquire historical parameter data and second weather forecast data corresponding to the energy management system, wherein the second weather forecast data is weather forecast data within a second time period after a second time corresponding to the historical parameter data; Training the first algorithm model according to the historical parameter data and the second meteorological forecast data to obtain a trained first algorithm model; The real-time parameter data and the first weather forecast data are input into the trained first algorithm model, so that the trained first algorithm model predicts the energy demand corresponding to the energy management system and outputs the prediction result.

3. The method for determining a control strategy according to claim 1, characterized in that: Determining a target control strategy corresponding to the energy management system according to the prediction result includes: Obtaining operating rules and constraints corresponding to the energy management system; Inputting the operation rules and the prediction results into a second algorithm model so that the second algorithm model outputs a plurality of first control strategies corresponding to the energy management system; The target control strategy is determined from among the plurality of first control strategies according to the constraint conditions.

4. The method for determining a control strategy according to claim 1, characterized in that: After determining the target control strategy corresponding to the energy management system according to the prediction result, the method further includes: The energy management system is parameter-controlled according to the target control strategy, and the energy consumption data of the energy management system in the first time period after the parameter control is obtained; the prediction result is compared with the energy consumption data, and it is determined whether to update the target control strategy according to the comparison result.

5. The method for determining the control strategy according to claim 4, characterized in that: Determining whether to update the target control strategy according to the comparison result includes: Determining the matching degree between the prediction result and the energy consumption data according to the comparison result; When the comparison result indicates that the matching degree is greater than or equal to a preset threshold, and the energy consumption data is less than the energy demand data corresponding to the prediction result, determining not to update the target control strategy; When the comparison result indicates that the matching degree is less than the preset threshold, and / or the energy consumption data is greater than or equal to the energy demand data corresponding to the prediction result, the target control strategy is updated to obtain an updated target control strategy.

6. The method for determining the control strategy according to claim 5, characterized in that: Updating the target control strategy to obtain an updated target control strategy includes: Adjusting parameters in a second algorithm model according to the matching degree to update the second algorithm model, wherein the second algorithm model is used to output the target control strategy; Determine a plurality of second control strategies corresponding to the energy management system according to the updated second algorithm model; The updated target control strategy is determined among the plurality of second control strategies.

7. A device for determining a control strategy, characterized in that: include: An acquisition module, used to acquire real-time parameter data and first weather forecast data corresponding to the energy management system, wherein the first weather forecast data is weather forecast data within a first time period after a first time corresponding to the real-time parameter data, and the real-time parameter data is operation data of the energy management system at the first time; A prediction module, used to predict the energy demand data corresponding to the energy management system according to the real-time parameter data and the first meteorological forecast data to obtain a prediction result; A determination module is used to determine the target control strategy of the energy management system according to the prediction result.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that The computer program is used by a processor to execute the steps of the method described in any one of claims 1 to 6.

Images