Load regulation and control method and device for air conditioner load aggregation cluster and computer equipment

Abstract

The invention relates to a load regulation and control method and device for an air conditioner load aggregation cluster and computer equipment. The method comprises the following steps: acquiring multi-region total power data of an air conditioner load aggregation cluster, and acquiring an excitation value quantity corresponding to the working temperature of an air conditioner in the air conditioner load aggregation cluster; according to the multi-area total power data, the average aggregation power of the air conditioner load aggregation cluster at the regulated and controlled temperature is determined and serves as the regulated power; according to the difference value between the reference power and the adjusted power, an adjustable potential target function of the air conditioner load aggregation cluster is constructed, and according to the adjusted power and the excitation value quantity, a satisfaction degree target function of the air conditioner load aggregation cluster is constructed; and by taking maximization of the adjustable potential objective function and maximization of the satisfaction objective function as optimization objectives, optimizing the objective variables of the air conditioner load aggregation cluster to obtain a load regulation and control result. By adopting the method, the load regulation and control precision of the air conditioner load aggregation cluster can be improved.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a load control method, device, computer equipment, computer-readable storage medium and computer program product for an air-conditioning load aggregation cluster. Background Art

[0002] Air conditioning load aggregation cluster refers to the aggregation modeling of dispersed air conditioning loads with similar operating characteristics to form an overall load cluster. Air conditioning loads account for a large proportion of the power grid, especially during the peak hours of air conditioning loads in summer and winter. Effective load regulation of air conditioning load aggregation clusters can reduce peak loads, balance power grid supply and demand, reduce the pressure on energy storage equipment, and at the same time, improve energy efficiency and reduce power grid operating costs. In traditional technologies, load regulation of air conditioning load aggregation clusters is often carried out for economic reasons, relying on a single, fixed regulation method, resulting in low load regulation accuracy for air conditioning load aggregation clusters. Summary of the invention

[0003] Based on this, it is necessary to provide a load control method, device, computer equipment, computer-readable storage medium and computer program product for an air conditioning load aggregation cluster that can improve the load control accuracy of the air conditioning load aggregation cluster in response to the above technical problems.

[0004] In a first aspect, the present application provides a load control method for an air conditioning load aggregation cluster, comprising:

[0005] Obtain multi-region total power data of an air conditioning load aggregation cluster, and obtain the incentive value corresponding to the operating temperature of the air conditioner in the air conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioner in each region of the air conditioning load aggregation cluster, and the incentive value is the compensation value for the air conditioning user during the load regulation process;

[0006] Determine, according to the multi-region total power data, the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature as the adjusted power;

[0007] According to the difference between the reference power and the adjusted power, an adjustable potential objective function of the air-conditioning load aggregation cluster is constructed, and according to the adjusted power and the incentive value, a satisfaction objective function of the air-conditioning load aggregation cluster is constructed; the reference power is the average aggregation power of the air-conditioning load aggregation cluster at a reference temperature;

[0008] Taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization goals, the target variables of the air conditioning load aggregation cluster are optimized to obtain the load control result; the target variables include at least one of the operating status of the air conditioner, the average aggregation power of the air conditioner and the duration of the air conditioner being turned on.

[0009] In one of the embodiments, obtaining the incentive value corresponding to the operating temperature of the air conditioner in the air conditioner load aggregation cluster includes:

[0010] Inputting the operating temperature of the air conditioner in the air conditioner load aggregation cluster into the temperature grading control incentive model to obtain the incentive value corresponding to the operating temperature;

[0011] The temperature graded control incentive model is expressed as:

[0012] ;

[0013] ;

[0014] D is the satisfaction of air conditioner users, a is the satisfaction calculation coefficient, is the operating temperature of the jth air conditioner in the i-th area at time t, To regulate the temperature, is the incentive value of the kth temperature level, is the incentive value per unit power for the kth temperature level, is the incentive value per unit power of the mth temperature level, and B is the total incentive budget value.

[0015] In one embodiment, the adjustable potential objective function is expressed as:

[0016] ;

[0017] Said is the adjustable potential objective function, is the average aggregate power of the air conditioning load aggregation cluster at the reference temperature, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature;

[0018] The satisfaction objective function is expressed as:

[0019] ;

[0020] Said is the satisfaction objective function, b is the influence coefficient of temperature deviation on the satisfaction, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature, is the incentive value of the kth temperature level.

[0021] In one embodiment, the objective variables of the air conditioning load aggregation cluster are optimized by taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain a load regulation result, including:

[0022] Taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives, and under the condition of satisfying the constraint conditions, optimizing the objective variables of the air conditioning load aggregation cluster to obtain the load regulation result;

[0023] The constraints include human comfort constraints, air conditioning load aggregation adjustable potential constraints, room temperature change upper and lower limit constraints, air conditioning minimum downtime constraints and satisfaction constraints;

[0024] Among them, the human comfort constraint is used to constrain the temperature adjustment amount of each air conditioner in the air-conditioning load aggregation cluster, the air-conditioning load aggregation adjustable potential constraint is used to constrain the average aggregation power of the air-conditioning load aggregation cluster under the regulated temperature, the upper and lower limit constraints of room temperature change are used to constrain the indoor temperature, the air-conditioning minimum downtime constraint is used to constrain the start-up time and shutdown time of the air-conditioning, and the satisfaction constraint is used to constrain the satisfaction of air-conditioning users.

[0025] In one embodiment, the optimizing the target variable of the air conditioning load aggregation cluster to obtain the load regulation result includes:

[0026] Determine a first variable and a second variable from the target variables of the air conditioning load aggregation cluster; the first variable is a target variable whose vector dimension is higher than a dimension threshold, and the second variable is a target variable whose vector dimension is lower than the dimension threshold;

[0027] For the first variable, randomly select at least two vector dimensions in the first variable as current search directions, establish a search path between a current solution of the first variable and a global optimal solution of the first variable in a current iteration, optimize the first variable according to the current search direction of the first variable and the search path of the first variable, and obtain an optimized first variable;

[0028] For the second variable, randomly select a vector dimension in the first variable as a current search direction, and establish a search path between a current solution of the second variable and two random solutions of the second variable, and optimize the second variable according to the current search direction of the second variable and the search path of the second variable to obtain an optimized second variable;

[0029] The load control result is obtained based on the optimized first variable and the optimized second variable.

[0030] In one embodiment, obtaining multi-region total power data of an air conditioning load aggregation cluster includes:

[0031] Input the rated power and operating status of each air conditioner in any area into the single-area aggregation model to obtain the single-area total power data of any area; the single-area aggregation model is a model that aggregates the power data of each air conditioner in a single area;

[0032] The single-region total power data corresponding to each of the regions is input into a multi-region aggregation model to obtain multi-region total power data of the air-conditioning load aggregation cluster; the multi-region aggregation model is a model for aggregating the power data of each of the regions.

[0033] In a second aspect, the present application also provides a load control device for an air conditioning load aggregation cluster, comprising:

[0034] An acquisition module is used to acquire multi-region total power data of an air-conditioning load aggregation cluster, and to acquire an incentive value corresponding to the operating temperature of the air conditioner in the air-conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioner in each region of the air-conditioning load aggregation cluster, and the incentive value is the compensation value for the air-conditioning user during the load regulation process;

[0035] A determination module, configured to determine, according to the multi-region total power data, an average aggregate power of the air conditioning load aggregation cluster at the regulated temperature as the adjusted power;

[0036] A construction module, configured to construct an adjustable potential objective function of the air-conditioning load aggregation cluster according to a difference between a reference power and the adjusted power, and to construct a satisfaction objective function of the air-conditioning load aggregation cluster according to the adjusted power and the incentive value; the reference power is an average aggregate power of the air-conditioning load aggregation cluster at a reference temperature;

[0037] An optimization module is used to optimize the target variables of the air conditioning load aggregation cluster by taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain a load control result; the target variables include at least one of the operating status of the air conditioner, the average aggregate power of the air conditioner, and the duration of the air conditioner being turned on.

[0038] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0040] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0041] The load control method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned air conditioning load aggregation cluster obtain multi-region total power data of the air conditioning load aggregation cluster, and obtain the incentive value corresponding to the working temperature of the air conditioner in the air conditioning load aggregation cluster, wherein the multi-region total power data is the total power data of the air conditioners in each region of the air conditioning load aggregation cluster, and the incentive value is the compensation value for the air conditioning user during the load control process; according to the multi-region total power data, the average aggregated power of the air conditioning load aggregation cluster at the regulated temperature is determined as the adjusted power; according to the difference between the reference power and the adjusted power, an adjustable potential objective function of the air conditioning load aggregation cluster is constructed, and according to the adjusted power and the incentive value, a satisfaction objective function of the air conditioning load aggregation cluster is constructed, wherein the reference power is the average aggregated power of the air conditioning load aggregation cluster at the reference temperature; with the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as the optimization objectives, the target variables of the air conditioning load aggregation cluster are optimized to obtain the load control result, wherein the target variable includes at least one of the operating state of the air conditioner, the average aggregated power of the air conditioner and the duration of the air conditioner on. By combining the multi-regional total power data of the air-conditioning load aggregation cluster and the incentive value corresponding to the operating temperature, efficient regulation of the air-conditioning load aggregation cluster can be achieved; by calculating the difference between the reference power and the adjusted power, an adjustable potential objective function is constructed, which can accurately evaluate the adjustable potential of the air-conditioning load; the satisfaction objective function constructed based on the adjusted power and the incentive value balances the user's response willingness and load reduction needs; by optimizing the target variables including the air-conditioning operating status, power and on-time duration, dynamic adjustment and precise optimization of the load regulation plan are achieved, thereby improving the load regulation accuracy of the air-conditioning load aggregation cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 An application environment diagram of a load control method for an air conditioning load aggregation cluster in an embodiment;

[0044] Figure 2 A schematic diagram of a flow chart of a load control method for an air conditioning load aggregation cluster in one embodiment;

[0045] Figure 3 A schematic diagram of a flow chart of a starfish optimization algorithm in one embodiment;

[0046] Figure 4 It is a structural block diagram of a load control device of an air conditioning load aggregation cluster in one embodiment;

[0047] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] The load control method of the air conditioning load aggregation cluster provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the power dispatching and control center 102 can obtain the flexible air-conditioning power consumption information collected by the load aggregation unit 104. The flexible air-conditioning power consumption information can refer to the operating status information, user response data, etc. related to the air-conditioning load during the flexible regulation process, specify the corresponding regulation scheme and send it to the load aggregation unit 104. The load aggregation unit 104 can collect the power consumption data of the air-conditioning load aggregation cluster in each area, perform load aggregation calculation, evaluate the controllable potential, and then feed back the results to the power dispatching and control center 102. At the same time, the load aggregation unit 104 can refine the regulation scheme, generate temperature control instructions with different incentive levels, and distribute them to air-conditioning users. Air-conditioning users can independently decide whether to participate in the regulation response based on the received temperature adjustment instructions and electricity price incentive information.

[0050] The power dispatching control center 102 or the load aggregation unit 104 obtains the multi-region total power data of the air-conditioning load aggregation cluster, and obtains the incentive value corresponding to the working temperature of the air conditioner in the air-conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioners in each region of the air-conditioning load aggregation cluster, and the incentive value is the compensation value for the air-conditioning user during the load regulation process; the power dispatching control center 102 or the load aggregation unit 104 determines the average aggregated power of the air-conditioning load aggregation cluster at the regulated temperature as the adjusted power according to the multi-region total power data; the power dispatching control center 102 or the load aggregation unit 104 determines the average aggregated power of the air-conditioning load aggregation cluster at the regulated temperature according to the parameters The difference between the reference power and the adjusted power is used to construct an adjustable potential objective function of the air-conditioning load aggregation cluster, and, according to the adjusted power and the incentive value, a satisfaction objective function of the air-conditioning load aggregation cluster is constructed; the reference power is the average aggregation power of the air-conditioning load aggregation cluster at the reference temperature; the power dispatching control center 102 or the load aggregation unit 104 optimizes the target variables of the air-conditioning load aggregation cluster with the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as the optimization objectives, and obtains the load control result; the target variables include at least one of the operating status of the air-conditioning, the average aggregation power of the air-conditioning and the duration of the air-conditioning being turned on.

[0051] In the related art, the air conditioning load aggregation method mainly relies on the simple averaging of the influencing factors of different regions when designing. Although this method simplifies the system calculation complexity to a certain extent, it ignores the differences in air conditioning load characteristics between regions and the diversity of influencing factors such as user usage habits, environmental conditions, and load response capabilities. Specifically, the air conditioning load is affected by multiple factors such as temperature, humidity, user behavior patterns, and building characteristics. The performance of these factors in different regions has significant temporal and spatial differences. For example, in commercial and residential areas, there are large differences in the use time, temperature control requirements, and load response capabilities of air conditioners, and the existing averaging processing methods cannot capture these subtle differences, resulting in the continuous accumulation and amplification of load aggregation errors. Especially during peak hours, the load fluctuations between regions are more severe. A single averaging strategy not only reduces the prediction accuracy, but also may cause the system to be unable to perform effective dynamic load regulation, thereby affecting the controllability and stability of the overall load aggregation. In addition, the expansion of load aggregation errors also increases the burden on energy storage equipment and scheduling systems, which may cause local energy scheduling imbalances and further reduce energy efficiency.

[0052] Moreover, in the related art, the load control strategy for the air-conditioning load aggregation cluster is too focused on the system economy and load control effect, and fails to fully consider the synergistic relationship between the satisfaction of air-conditioning users and the incentive mechanism of load aggregators. Specifically, the user's response willingness and comfort largely determine the effect of load aggregation, while the existing optimization methods often ignore the user's actual needs for temperature comfort, response flexibility and compensation mechanism, and simply rely on economic incentives or fixed control strategies to achieve load adjustment, resulting in low user participation enthusiasm. In particular, when the temperature control deviates greatly from user demand, users may refuse to participate in the control, affecting the overall aggregation effect. In addition, the incentive mechanism of load control lacks linkage with user satisfaction, and fails to form a comprehensive optimization plan that takes into account user response benefits, comfort guarantee and overall system benefits. This disconnection phenomenon makes it difficult to balance the interests of all parties in the process of load control, the control cost is high, the incentive means lack of pertinence, and it is difficult to achieve efficient integration and full release of load resources.

[0053] Therefore, in view of the problems of neglecting regional differences, increasing aggregation errors, and disconnection between user satisfaction and the incentive mechanism of load control in the process of air-conditioning load aggregation in related technologies, it is urgent to develop a more refined and intelligent air-conditioning load aggregation method and a load control method for air-conditioning load aggregation clusters. By introducing regional difference analysis and user behavior modeling, the load characteristics and dynamic fluctuation laws of each region can be accurately captured to achieve accurate aggregation and control of air-conditioning loads. At the same time, the optimization strategy needs to further strengthen the coupling design of user satisfaction and load control incentive mechanism, balance user comfort, response benefits and system economy by building a flexible incentive constraint system, improve user participation willingness and control effect, and finally achieve coordinated optimization of multiple interests.

[0054] In an exemplary embodiment, Figure 2 As shown, a load control method for an air conditioning load aggregation cluster is provided, and the method is applied to Figure 1 The power dispatching control center 102 or the load aggregation unit 104 in the example is used for explanation, including:

[0055] Step S202, obtaining multi-region total power data of the air conditioning load aggregation cluster, and obtaining the incentive value corresponding to the operating temperature of the air conditioner in the air conditioning load aggregation cluster.

[0056] Among them, the multi-region total power data is the total power data of the air conditioners in each region in the air conditioning load aggregation cluster, and the incentive value is the compensation value for air conditioning users during the load control process.

[0057] Among them, the multi-region total power data can be the aggregated total power of the air-conditioning load in each region calculated according to the regional division in the air-conditioning load aggregation cluster. The region can include a community, commercial building complex or industrial park, etc., which can reflect the total load situation of each region at the current moment in real time.

[0058] In the specific implementation, the real-time power consumption of the air conditioner in each area can be obtained through smart meters or regional monitoring equipment, and then the total power data of multiple areas can be calculated based on the decentralized air conditioning load operation data (such as the real-time power and operating status of each air conditioner).

[0059] The incentive value refers to the amount of economic compensation provided to users during load regulation to guide them to cooperate with regulation (such as adjusting the temperature setting value). The incentive value can be dynamically calculated through an incentive mechanism (such as tiered prices) based on the temperature adjustment range that users are willing to accept.

[0060] In a specific implementation, the incentive value of the user at different working temperatures can be calculated based on the set incentive price rules (such as providing a fixed compensation amount for each increase of 1 kWh of electricity).

[0061] Step S204: Determine the average aggregate power of the air conditioning load aggregation cluster under the regulated temperature according to the multi-region total power data as the adjusted power.

[0062] In the specific implementation, the power data of the air-conditioning load aggregation cluster at different temperatures can be filtered out from the multi-region total power data. For example, the average aggregation power of the air-conditioning load aggregation cluster at the reference temperature and the average aggregation power of the air-conditioning load aggregation cluster at the regulated temperature can be determined based on the multi-region total power data.

[0063] The regulated temperature may be a temperature value obtained by appropriately adjusting the temperature of the air conditioner through an optimization strategy during the load regulation process.

[0064] The adjusted power may be the average aggregate power of the air-conditioning load aggregation cluster after the temperature setting value is adjusted.

[0065] The average aggregate power may refer to the average power value calculated by summarizing the average aggregate power data of air conditioners in various dispersed areas. The average aggregate power may reflect the overall power consumption characteristics of the entire air conditioner load aggregation cluster.

[0066] Step S206, constructing an adjustable potential objective function of the air conditioning load aggregation cluster according to the difference between the reference power and the adjusted power, and constructing a satisfaction objective function of the air conditioning load aggregation cluster according to the adjusted power and the incentive value.

[0067] The reference power is the average aggregate power of the air conditioning load aggregation cluster at the reference temperature.

[0068] The reference temperature may be a temperature value set by a user when the air-conditioning equipment is in normal operation and before load regulation is performed, or may be a default temperature setting value that the user feels comfortable with, such as 25 degrees Celsius.

[0069] The reference power may be the average aggregate power of the air-conditioning load aggregation cluster when no load regulation is performed (ie, at a reference temperature).

[0070] Among them, the adjustable potential objective function can be used to reflect the load reduction potential of the air-conditioning load aggregation cluster during the load regulation process, and is constructed based on the difference between the reference power and the adjusted power.

[0071] Among them, the satisfaction objective function can measure the user's satisfaction with participating in regulation based on the regulated power and incentive value, taking into account the balance between load reduction demand and user comfort.

[0072] Optionally, the adjustable potential objective function may be determined based on the difference between the reference power and the adjusted power.

[0073] Optionally, the satisfaction objective function may be determined based on the product of the air conditioner user's satisfaction, the adjusted power, and the incentive value.

[0074] Step S208, taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives, optimizing the objective variables of the air conditioning load aggregation cluster to obtain the load regulation result.

[0075] In one embodiment, the optimization objective is to maximize the adjustable potential objective function and the satisfaction objective function, and by assigning weights to the two objective functions, a comprehensive objective function is constructed, and the comprehensive objective function is used as the optimization objective to optimize the objective variables of the air conditioning load aggregation cluster to obtain the load control result. Optionally, a weighted summation method can be used to convert the multi-objective solution into a single objective solution, and the comprehensive objective function can be expressed as:

[0076] ;

[0077] ;

[0078] in, is the comprehensive objective function, is the adjustable potential objective function, is the satisfaction objective function, is the weight corresponding to the adjustable potential objective function, is the weight corresponding to the satisfaction objective function. Optionally, the weight can be selected based on user needs.

[0079] Alternatively, two objective functions can be optimized simultaneously through Pareto Improvement to obtain a set of non-dominated solutions, ensuring a balance between regulation effect and user satisfaction.

[0080] The target variable may be a variable set used to describe the controllable factors in the air conditioning load aggregation cluster, including at least one of the operating status of the air conditioner, the average aggregate power of the air conditioner, and the duration of the air conditioner on. By optimizing the target variable, the load control effect (such as reduction potential and user satisfaction) can be maximized.

[0081] Among them, the operating status of the air conditioner may include whether the air conditioner is turned on or off; the average aggregate power of the air conditioner may include the current power level of the air conditioner; the duration of the air conditioner being on may include the working time of the air conditioner in the control strategy.

[0082] In specific implementation, optimizing the target variables of the air conditioning load aggregation cluster may include: deciding which air conditioners are turned on or off during a specific time period; adjusting the average aggregate power setting value of the air conditioner, usually by adjusting the temperature setting value; and optimizing the length of time the air conditioner is turned on.

[0083] Optionally, the target variable can be dynamically adjusted to meet the optimization purpose through intelligent optimization algorithms (such as meta-heuristic algorithms such as the starfish optimization algorithm).

[0084] The load control results may include specific control plans for air conditioners in each area, such as on / off status, power setting value, and operating time, and the load control results are sent to each air conditioner to implement load control.

[0085] In the load control method of the above-mentioned air-conditioning load aggregation cluster, the multi-region total power data of the air-conditioning load aggregation cluster is obtained, and the incentive value corresponding to the working temperature of the air-conditioning in the air-conditioning load aggregation cluster is obtained, wherein the multi-region total power data is the total power data of the air-conditioning in each region of the air-conditioning load aggregation cluster, and the incentive value is the compensation value for the air-conditioning user in the load control process; according to the multi-region total power data, the average aggregate power of the air-conditioning load aggregation cluster at the reference temperature is determined as the reference power, and, according to the multi-region total power data, the average aggregate power of the air-conditioning load aggregation cluster at the regulated temperature is determined as the adjusted power; according to the difference between the reference power and the adjusted power, the adjustable potential objective function of the air-conditioning load aggregation cluster is constructed, and, according to the adjusted power and the incentive value, the satisfaction objective function of the air-conditioning load aggregation cluster is constructed; with the maximization of the adjustable potential objective function and the satisfaction objective function as the optimization goal, the target variables of the air-conditioning load aggregation cluster are optimized to obtain the load control result, wherein the target variable includes at least one of the operating state of the air-conditioning, the average aggregate power of the air-conditioning, and the duration of the air-conditioning on. By combining the multi-regional total power data of the air-conditioning load aggregation cluster and the incentive value corresponding to the operating temperature, efficient regulation of the air-conditioning load aggregation cluster can be achieved; by calculating the difference between the reference power and the adjusted power, an adjustable potential objective function is constructed, which can accurately evaluate the adjustable potential of the air-conditioning load; the satisfaction objective function constructed based on the adjusted power and the incentive value balances the user's response willingness and load reduction needs; by optimizing the target variables including the air-conditioning operating status, power and on-time duration, dynamic adjustment and precise optimization of the load regulation plan are achieved, thereby improving the load regulation accuracy of the air-conditioning load aggregation cluster.

[0086] In another embodiment, the multi-area total power data of the air-conditioning load aggregation cluster is obtained, including: inputting the rated power and operating status of each air-conditioner in any area into a single-area aggregation model to obtain the single-area total power data of any area; inputting the single-area total power data corresponding to each area into the multi-area aggregation model to obtain the multi-area total power data of the air-conditioning load aggregation cluster.

[0087] The single-area aggregation model is a model for aggregating the power data of each air conditioner in a single area. Optionally, the single-area aggregation model may be a mathematical model for aggregating the power data of each air conditioner in a certain area.

[0088] The multi-region aggregation model is a model for aggregating power data of each region. Optionally, the multi-region aggregation model can be a model for further aggregating the total power data of the entire air conditioning load aggregation cluster based on the total power data of a single region of each region.

[0089] The rated power of each air conditioner may be the power output of the air conditioner at maximum working efficiency, which is a fixed parameter of the equipment.

[0090] The operating state of the air conditioner may include on or off, which may be represented by a binary variable, such as 1 for on state and 0 for off state.

[0091] As an example, the single-area aggregation model can be used to multiply the rated powers of all air conditioners in the area by their operating states and sum them up to obtain the total power data of the single area.

[0092] As an example, the single-area total power data of all areas can be added together through the multi-area aggregation model to obtain the multi-area total power data of the entire air-conditioning load aggregation cluster.

[0093] For example, suppose there are N air conditioners in a certain area, the operating state of each air conditioner is S(t), and the rated power of the jth air conditioner is According to the law of large numbers, the single-region aggregation model can be expressed as:

[0094] ;

[0095] ;

[0096] ;

[0097] in, The total power of the air conditioners in any area; is the rated power of the jth air conditioner that is turned on; is the operating status of each air conditioner that is turned on; N is the total number of air conditioners in any area; The start time of the jth air conditioner; The shutdown time of the jth air conditioner that is turned on; The duration that the air conditioner is turned on.

[0098] Exemplarily, the single-region aggregation model is a single-region primary aggregation model. In order to accurately reflect the differences in parameter distribution characteristics of different environments, a partitioned air conditioning load aggregation method can be used. First, the air conditioning loads with similar parameter distribution characteristics are aggregated in the same region, and then secondary aggregation is performed based on the aggregation results of each region to obtain a more accurate aggregation model. Aggregate the air conditioning in any region through the single-region aggregation model, and then perform secondary aggregation through the multi-region aggregation model to obtain the operating status and total air conditioning power of the air conditioning in M ​​regions. The multi-region aggregation model can be expressed as:

[0099] ;

[0100] ;

[0101] in, is the total power data of multiple zones, which can be equal to the total air conditioning power of M zones; M is the total number of zones; is the number of air conditioners in the jth area; is the rated power of the jth air conditioner in area i; It is used to indicate whether the jth air conditioner in the i-th area is in the on-state at time t; The average value used to indicate whether all air conditioners in M ​​areas are in the on working state at time t.

[0102] The technical solution of this embodiment proposes a modeling method that combines partition aggregation with secondary aggregation. Through primary aggregation within a region and secondary aggregation across regions, the adaptability of the model to the distribution characteristics of different environmental parameters is effectively improved, and the accuracy of the aggregated load is significantly improved.

[0103] It can be seen that the present invention can realize the precise aggregation and dynamic regulation of air-conditioning load, effectively improve the control accuracy of the system, user response willingness and overall operating efficiency, and ensure that the system reaches the optimal state in terms of economy, stability and user experience.

[0104] In another embodiment, obtaining the incentive value corresponding to the working temperature of the air conditioner in the air conditioner load aggregation cluster includes: inputting the working temperature of the air conditioner in the air conditioner load aggregation cluster into the temperature grading regulation incentive model to obtain the incentive value corresponding to the working temperature; wherein the temperature grading regulation incentive model is expressed as:

[0105] ;

[0106] ;

[0107] D is the satisfaction of air conditioner users, a is the satisfaction calculation coefficient, is the operating temperature of the jth air conditioner in the i-th area at time t, To regulate the temperature, is the incentive value of the kth temperature level, is the incentive value per unit power for the kth temperature level, is the incentive value per unit power for the mth temperature level, and B is the total incentive budget value.

[0108] Among them, the temperature-grading control incentive model can be based on the adjustment degree of the working temperature of the air-conditioning equipment, calculate the user's satisfaction with participating in load control and the grading incentive value, and provide economic incentives to users on this basis, quantify the user's response willingness and incentive intensity, and ensure that the control goals are achieved while taking into account the user experience.

[0109] Among them, the satisfaction of air-conditioning users can be used to indicate the degree of acceptance of air-conditioning users to the adjusted temperature.

[0110] The operating temperature of the air conditioner may refer to the temperature set during the operation of the air conditioner.

[0111] In the specific implementation, in order to increase the enthusiasm of users to participate in air-conditioning load reduction and ensure the comfort requirements of users for air-conditioning temperature, a temperature-grading control incentive model can be introduced to consider the user satisfaction under different temperature levels and set the corresponding incentive value.

[0112] The relationship between user satisfaction and the incentive value of the temperature grades can be established through the formula of the above-mentioned temperature graded control incentive model. The incentive value of different temperature grades can be determined based on the relative relationship between the satisfaction of their respective air-conditioning users. Optionally, the incentive temperature grades can be divided into 3, with the starting temperature being 25°C and each increase of 1.5 degrees Celsius (°C) corresponding to 1 grade, so that the incentive value of the corresponding controlled temperature grade can be calculated through the formula of the above-mentioned temperature graded control incentive model.

[0113] The technical solution of this embodiment, in view of the user's comfort requirements in load regulation, proposes a temperature-graded incentive model, calculates the dissatisfaction under different gears through graded temperature setting values, and constructs a functional relationship between incentive prices and user satisfaction. This mechanism not only accurately meets the user's comfort requirements, but also significantly improves the user's enthusiasm for participating in load reduction through differentiated incentive prices, effectively solving the problem of insufficient user response willingness under traditional regulation methods.

[0114] In another embodiment, the adjustable potential objective function is expressed as:

[0115] ;

[0116] is the adjustable potential objective function, is the average aggregate power of the air conditioning load aggregation cluster at the reference temperature, is the average aggregate power of the air conditioning load aggregation cluster under the regulated temperature;

[0117] The satisfaction objective function is expressed as:

[0118] ;

[0119] is the satisfaction objective function, D is the satisfaction of air-conditioning users, b is the influence coefficient of temperature deviation on satisfaction, is the average aggregate power of the air conditioning load aggregation cluster under the regulated temperature, is the incentive value of the kth temperature level.

[0120] In order to achieve the control objectives of the power grid efficiently and consider the operating benefits of the load aggregation cluster, two objective functions can be established: maximizing the adjustable potential of the air-conditioning load aggregation cluster and maximizing user satisfaction.

[0121] In the specific implementation, for large-scale air conditioning load aggregation clusters, the adjustment of the temperature setting value is a direct factor affecting the dispatchable potential of the air conditioner. At the same outdoor temperature, the higher the air conditioner set temperature is adjusted, the more the aggregate power value decreases, and the greater the dispatch potential. Optionally, the average aggregate power when the temperature setting value of the air conditioning load aggregation cluster is 25℃ can be defined as the reference power, and its value is The average aggregate power after the air conditioner is set to the set temperature is the adjusted power, and its value is , the adjustable potential is the difference between the reference power and the adjusted power. It can be used to characterize the size of the adjustable potential. The adjustable potential objective function is used to optimize the aggregated load of a large-scale air-conditioning load aggregation cluster, and adjust it according to the temperature setting value to maximize the adjustable potential. One of the optimization goals is to maximize the adjustable potential of the air-conditioning load aggregation cluster. The adjustable potential can refer to the load change after the temperature setting value is adjusted. In other words, it can also refer to the power change when the temperature is changed from the reference temperature to the regulated temperature.

[0122] At the same time, by defining the control potential after adjusting the temperature set value, the impact of different temperature set values ​​on the adjustable potential is quantified, providing a scientific theoretical basis and technical support for large-scale air-conditioning load control.

[0123] In the specific implementation, the satisfaction objective function can comprehensively consider the satisfaction of air-conditioning users, and optimize the control scheme of air-conditioning load through the incentive mechanism, so as to ultimately improve the enthusiasm of users to participate in load reduction. The satisfaction objective function is used to maximize the satisfaction of air-conditioning users, and achieve this optimization goal by reasonably setting the incentive value.

[0124] The technical solution of this embodiment combines the load reduction potential with user satisfaction by defining an adjustable potential objective function and a satisfaction objective function. Specific variables (such as reference power, adjusted power, satisfaction, incentive value, etc.) together constitute the basic framework for load regulation optimization, achieving the dual goals of reducing load and optimizing user experience.

[0125] In another embodiment, the objective variables of the air conditioning load aggregation cluster are optimized with the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as the optimization objectives to obtain the load control result, including: taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as the optimization objectives, and optimizing the objective variables of the air conditioning load aggregation cluster when it is determined that the constraints are met to obtain the load control result; wherein the constraints include human comfort constraints, air conditioning load aggregation adjustable potential constraints, room temperature change upper and lower limit constraints, air conditioning minimum downtime constraints and satisfaction constraints; wherein the human comfort constraints are used to constrain the temperature adjustment amount of each air conditioner in the air conditioning load aggregation cluster, the air conditioning load aggregation adjustable potential constraints are used to constrain the average aggregation power of the air conditioning load aggregation cluster at the adjusted temperature, the room temperature change upper and lower limit constraints are used to constrain the indoor temperature, the air conditioning minimum downtime constraints are used to constrain the start-up time and shutdown time of the air conditioner, and the satisfaction constraints are used to constrain the satisfaction of air conditioning users.

[0126] In the specific implementation, the human comfort constraint can be used to ensure user comfort. For each air conditioner in the air conditioning load aggregation cluster, the temperature adjustment should not exceed the maximum adjustment range. The human comfort constraint can be expressed as:

[0127] ;

[0128] in, is the controlled temperature of the air conditioner at time t, i.e. the temperature after control; is the set temperature of the air conditioner user at time t, that is, the temperature value set by the user before load regulation, that is, the reference temperature; is the maximum adjustment amount.

[0129] In a specific implementation, the air conditioning load aggregation adjustable potential constraint can be used to ensure that the adjustable potential of the air conditioning load aggregation cluster does not exceed the theoretical air conditioning load cluster aggregation power. The air conditioning load aggregation adjustable potential constraint can be expressed as:

[0130] ;

[0131] in, Aggregate the adjustable potential of the cluster for the actual air conditioning load; Aggregate power for the theoretical air conditioning load cluster.

[0132] In the specific implementation, the upper and lower limit constraints of room temperature change can be used to ensure the range of indoor temperature. The upper and lower limit constraints of room temperature change can be expressed as:

[0133] ;

[0134] in, , are the minimum and maximum indoor temperatures at time t respectively; is the indoor temperature at time t.

[0135] In the specific implementation, the minimum downtime constraint of the air conditioner can be expressed as:

[0136] ;

[0137] in, is the start time of the jth air conditioner in the i-th area at time t; is the shutdown time of the jth air conditioner in the i-th area at time t. , They are the minimum on-time and minimum off-time of the air conditioner respectively.

[0138] In the specific implementation, the satisfaction constraint can be expressed as:

[0139] ;

[0140] Where D is the user's satisfaction.

[0141] The technical solution of this embodiment, by maximizing the adjustable potential objective function and the satisfaction objective function, can take into account the user's comfort and response willingness as much as possible while reducing the power grid load, thereby achieving dual optimization of load regulation and user satisfaction; introduce multiple constraints (such as human comfort, room temperature variation range, etc.) to ensure the flexibility and accuracy of load regulation, so that the regulation process is more in line with user needs and actual operating conditions; through the combination of human comfort constraints, satisfaction constraints and incentive mechanisms, the solution can effectively control the temperature adjustment range, avoid users refusing to participate due to discomfort, and improve users' acceptance of regulation; the minimum downtime constraint of the air conditioner ensures that the equipment will not reduce its life or efficiency due to frequent switching during the regulation process, thereby improving the operating stability of the air conditioning system; through the adjustable potential constraint of the air conditioning load aggregation, the load reduction target after regulation is reasonably planned to ensure that the system achieves an efficient reduction effect and optimizes energy utilization efficiency; through the upper and lower limit constraints of room temperature variation, the solution can dynamically adapt to environmental requirements in different scenarios while keeping the indoor temperature within a reasonable range.

[0142] In another embodiment, the target variables of the air conditioning load aggregation cluster are optimized to obtain a load control result, including: determining a first variable and a second variable from the target variables of the air conditioning load aggregation cluster; the first variable is a target variable whose vector dimension is higher than a dimension threshold, and the second variable is a target variable whose vector dimension is lower than the dimension threshold; for the first variable, randomly selecting at least two vector dimensions in the first variable as the current search direction, and establishing a search path between the current solution of the first variable and the global optimal solution of the first variable in the current iteration, optimizing the first variable according to the current search direction of the first variable and the search path of the first variable to obtain the optimized first variable; for the second variable, randomly selecting a vector dimension in the first variable as the current search direction, and establishing a search path between the current solution of the second variable and two random solutions of the second variable, optimizing the second variable according to the current search direction of the second variable and the search path of the second variable to obtain the optimized second variable; based on the optimized first variable and the optimized second variable, obtaining the load control result.

[0143] The vector dimension is the number of dimensions of the target variable, which is used to measure the complexity of the variable. For example, if the target variable represents the operating status of all air conditioners in a certain area, its dimension may be equal to the number of air conditioners in the area. Since there are many air conditioners, the operating status of the air conditioners can be the first vector; if the target variable represents the average aggregate power, its dimension may be equal to the number of areas, and one area corresponds to one average aggregate power. Since the number of areas is far less than the number of air conditioners, the average aggregate power of the air conditioners can be the second variable.

[0144] The dimension threshold is a criterion for dividing the complexity of the target variable. According to whether the dimension of the variable is higher than the threshold, the target variable is divided into the first variable and the second variable.

[0145] Among them, the current solution is the current value of the target variable at a certain moment in the optimization process and is the starting point of the optimization search; the global optimal solution is the optimal solution found in the current iteration of the optimization process.

[0146] Among them, the search path is the optimization path from the current solution to the target solution, which is used to guide the optimization algorithm to gradually approach the global optimal solution.

[0147] In the specific implementation, at least two vector dimensions in the first variable are randomly selected as the current search direction, and a search path is constructed from the current solution to the global optimal solution to ensure that the search direction is conducive to approaching the global optimum. The first variable is optimized according to the search path and search direction, and the value of the first variable is gradually improved. In view of the high-dimensional characteristics of complex variables, collaborative search in multiple dimensions is used to improve the optimization effect.

[0148] In the specific implementation, a vector dimension in the second variable is randomly selected as the current search direction; a search path is constructed between the current solution and two random solutions; the second variable is optimized according to the search path and search direction, and the value of the second variable is gradually improved. In view of the low-dimensional characteristics of simple variables, a single-dimensional random search is used to avoid excessive calculation.

[0149] In the first variable, the search path from the current solution to the global optimal solution is used to ensure that the optimization process is targeted at the global optimal solution. In the second variable, local disturbances are introduced through random solutions to enhance the exploration ability. Then, the optimized first and second variables are integrated to obtain the optimized complete target variable set, and the load control result is output.

[0150] By dividing the target variable into the first variable and the second variable, and adopting the optimization strategies of multi-dimensional collaborative search and unidimensional random search respectively, the balance between globality and locality is achieved while ensuring the optimization efficiency, and finally an efficient load control solution is provided for the air-conditioning load aggregation cluster.

[0151] Exemplarily, the objective variable of the air conditioning load aggregation cluster is optimized by using the StarFish Optimization Algorithm (SFOA). The StarFish Optimization Algorithm is a meta-heuristic algorithm (intelligent optimization algorithm) inspired by the exploration, predation and regeneration behaviors of starfish. The algorithm uses a hybrid search mode that combines five-dimensional and one-dimensional search modes to improve computational efficiency.

[0152] In order to facilitate the understanding of those skilled in the art, Figure 3 A flowchart of a starfish optimization algorithm is provided by way of example.

[0153] First, initialize a set of solutions, defining each solution as containing the operating state of the air conditioner , average aggregate power of air conditioners , Duration of air conditioning on .

[0154] ;

[0155] Then, the formula for random initialization can be described as follows:

[0156] ;

[0157] in, represents the v-th dimension position of the u-th starfish, r represents a random number between (0,1), and are the upper and lower bounds of the v-th dimension design variable respectively; u is the starfish index, that is, the starfish currently being optimized; v is the position index of the starfish currently being optimized, and each starfish may have multiple dimensional positions during the optimization process.

[0158] Then, we enter the exploration phase of the algorithm. In order to simulate the exploration behavior of the starfish, the exploration phase is built into the starfish optimization algorithm to simulate the search capabilities of the starfish's five arms. In the exploration phase of the starfish optimization algorithm, the five-dimensional search mode in different optimization problems is combined with the one-dimensional search mode.

[0159] If the dimension of the optimization problem is greater than 5, the search space of the problem is very wide, requiring the starfish to move all five arms to explore the surrounding environment. Therefore, a mathematical model for this stage is established:

[0160] ;

[0161] ;

[0162] ;

[0163] In the formula, and Respectively represent the updated position and current position of the starfish. represents the v dimension of the current best position, v is 5 dimensions randomly selected from all dimensions, r represents a random number between (0,1); E is the current number of iterations, E max is the maximum number of iterations, In the range [0,π / 2].

[0164] If the dimension of the optimization problem is less than or equal to 5, the exploration phase uses a one-dimensional search mode to update the position. In this case, the starfish searches for food sources by moving only one arm, using the position information of other starfish. The updated position can be established as:

[0165] ;

[0166] ;

[0167] In the formula, and are the positions of two randomly selected starfish in the v dimension, H 1 and H 2 are two random numbers between (-1,1), v is a randomly selected value in all dimensions, and R is the energy of the starfish.

[0168] Then, we entered the development phase of the algorithm. The starfish optimization algorithm took into account predation and regeneration behaviors in the development phase and sought a global solution, so two update strategies were designed in the development phase. In order to simulate the predation phase of starfish, the starfish optimization algorithm adopted a parallel two-way search strategy, which requires the use of information from other starfish and the best position of the current population. First, the five distances between the best position and other starfish are calculated, and then two distances are randomly selected as confirmation, and the position of each starfish is updated using a parallel two-way search strategy. The distance calculation formula is:

[0169] ;

[0170] in, is the distance between the 5 best global starfish and other starfish, and u is the 5 randomly selected starfish. Therefore, the update law of each starfish in the predation behavior is modeled as:

[0171] ;

[0172] Among them, H 3 and H 4 is a random number between (0,1), Randomly select and .

[0173] When a predator tries to capture a starfish, it may escape by cutting off one of its arms. Therefore, in the starfish optimization algorithm, the regeneration phase is simulated only for the last starfish in the population (i.e., u=U). Since the regeneration process takes several months and the starfish move very slowly, we modeled the position update rule during the regeneration phase as follows:

[0174] ;

[0175] Where E is the current iteration, E max is the maximum number of iterations, and U is the total size.

[0176] After multiple iterations, the population will gradually converge to the Pareto optimal solution. Set the maximum number of iterations T max is the convergence criterion, and the final solution, that is, the optimized target variables, can be expressed as:

[0177] ;

[0178] By optimizing these three objective variables using a heuristic optimization algorithm, we can try to find the optimal solution that maximizes the two objective functions.

[0179] The Starfish Optimization Algorithm is used to solve the multi-objective optimization problem of air-conditioning load clusters (including maximizing adjustable potential and maximizing user satisfaction), and the load control strategy is efficiently optimized through a two-stage optimization process (exploration stage and development stage). The algorithm maintains an appropriate balance between global search and local development, significantly improves the optimization solution efficiency and convergence speed, and provides an efficient and accurate solution for real-time load control.

[0180] Compared with the prior art, the technical solution of the present invention shows significant advantages in large-scale air-conditioning load aggregation cluster modeling, user satisfaction incentive mechanism and real-time optimization strategy, especially in key technical issues such as regulation potential evaluation, load scheduling optimization and algorithm solution efficiency. First, in the modeling of large-scale air-conditioning load aggregation cluster, the present invention proposes a modeling method combining partition aggregation and secondary aggregation. By aggregating the air-conditioning load once in the region and then aggregating the results of each region twice, the adaptability of the model to the distribution characteristics of different environmental parameters is effectively improved, and the accuracy of the aggregated load is significantly improved. In addition, by defining the regulation potential after the temperature setting value is adjusted, the influence of different temperature setting values ​​on the adjustable potential is quantified, thereby providing a theoretical basis for large-scale load regulation. Secondly, in the user satisfaction incentive mechanism, the present invention innovatively introduces a temperature grade incentive model. By grading the user temperature setting value and calculating the dissatisfaction under different gears, a functional relationship between the incentive price and the user satisfaction is established, ensuring the comfort requirements of users in the process of participating in the air-conditioning load regulation. At the same time, the mechanism improves the enthusiasm of users to participate in load reduction through differentiated incentive prices, and alleviates the problem of low user response willingness under traditional temperature control methods. Finally, in terms of real-time optimization strategy, this paper adopts the Starfish optimization algorithm to solve the multi-objective optimization problem of air-conditioning load cluster (including maximizing adjustable potential and maximizing user satisfaction), and realizes efficient optimization of load control strategy through a two-stage optimization process (exploration stage and development stage). The algorithm maintains a proper balance between exploration and development, has good global search capability and local development capability, and significantly improves the optimization solution efficiency and convergence speed.

[0181] In summary, the present invention successfully solves the problems of insufficient modeling accuracy, low user participation and low optimization efficiency in the prior art through accurate air-conditioning load aggregation modeling, integration of user satisfaction and incentive mechanism, and efficient real-time optimization solution method. This solution not only realizes the precise control of large-scale air-conditioning loads, but also effectively improves the achievement rate of power grid control targets. It has significant economy, stability and practicality, and provides important support for the construction of low-carbon power systems.

[0182] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0183] Based on the same inventive concept, the embodiment of the present application also provides a load control device for an air conditioning load aggregation cluster for implementing the load control method for the air conditioning load aggregation cluster involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the load control device embodiments of one or more air conditioning load aggregation clusters provided below can refer to the limitations of the load control method for the air conditioning load aggregation cluster above, and will not be repeated here.

[0184] In an exemplary embodiment, Figure 4 As shown, a load control device for an air conditioning load aggregation cluster is provided, comprising:

[0185] The acquisition module 410 is used to obtain the multi-region total power data of the air conditioning load aggregation cluster, and to obtain the incentive value corresponding to the working temperature of the air conditioner in the air conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioner in each region of the air conditioning load aggregation cluster, and the incentive value is the compensation value for the air conditioner user during the load regulation process;

[0186] A determination module 420 is used to determine, according to the multi-region total power data, an average aggregate power of the air conditioning load aggregation cluster at the regulated temperature as the adjusted power;

[0187] A construction module 430 is used to construct an adjustable potential objective function of the air conditioning load aggregation cluster according to the difference between the reference power and the adjusted power, and to construct a satisfaction objective function of the air conditioning load aggregation cluster according to the adjusted power and the incentive value; the reference power is the average aggregate power of the air conditioning load aggregation cluster at a reference temperature;

[0188] The optimization module 440 is used to optimize the target variables of the air conditioning load aggregation cluster with the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain the load control result; the target variables include at least one of the operating status of the air conditioner, the average aggregation power of the air conditioner and the duration of the air conditioner being turned on.

[0189] In one embodiment, the acquisition module 410 is specifically used to input the working temperature of the air conditioner in the air conditioner load aggregation cluster into the temperature classification control incentive model to obtain the incentive value corresponding to the working temperature;

[0190] The temperature graded control incentive model is expressed as:

[0191] ;

[0192] ;

[0193] D is the satisfaction of air conditioner users, a is the satisfaction calculation coefficient, is the operating temperature of the jth air conditioner in the i-th area at time t, To regulate the temperature, is the incentive value of the kth temperature level, is the incentive value per unit power for the kth temperature level, is the incentive value per unit power of the mth temperature level, and B is the total incentive budget value.

[0194] In one embodiment, the adjustable potential objective function is expressed as:

[0195] ;

[0196] Said is the adjustable potential objective function, is the average aggregate power of the air conditioning load aggregation cluster at the reference temperature, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature;

[0197] The satisfaction objective function is expressed as:

[0198] ;

[0199] Said is the satisfaction objective function, b is the influence coefficient of temperature deviation on the satisfaction, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature, is the incentive value of the kth temperature level.

[0200] In one embodiment, the objective variables of the air conditioning load aggregation cluster are optimized by taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain a load regulation result, including:

[0201] Taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives, and under the condition of satisfying the constraint conditions, optimizing the objective variables of the air conditioning load aggregation cluster to obtain the load regulation result;

[0202] The constraints include human comfort constraints, air conditioning load aggregation adjustable potential constraints, room temperature change upper and lower limit constraints, air conditioning minimum downtime constraints and satisfaction constraints;

[0203] Among them, the human comfort constraint is used to constrain the temperature adjustment amount of each air conditioner in the air-conditioning load aggregation cluster, the air-conditioning load aggregation adjustable potential constraint is used to constrain the average aggregation power of the air-conditioning load aggregation cluster under the regulated temperature, the upper and lower limit constraints of room temperature change are used to constrain the indoor temperature, the air-conditioning minimum downtime constraint is used to constrain the start-up time and shutdown time of the air-conditioning, and the satisfaction constraint is used to constrain the satisfaction of air-conditioning users.

[0204] In one embodiment, the target variable of the air conditioning load aggregation cluster is optimized to obtain a load regulation result, including:

[0205] Determine a first variable and a second variable from the target variables of the air conditioning load aggregation cluster; the first variable is a target variable whose vector dimension is higher than a dimension threshold, and the second variable is a target variable whose vector dimension is lower than the dimension threshold;

[0206] For the first variable, randomly select at least two vector dimensions in the first variable as current search directions, establish a search path between a current solution of the first variable and a global optimal solution of the first variable in a current iteration, optimize the first variable according to the current search direction of the first variable and the search path of the first variable, and obtain an optimized first variable;

[0207] For the second variable, randomly select a vector dimension in the first variable as a current search direction, and establish a search path between a current solution of the second variable and two random solutions of the second variable, and optimize the second variable according to the current search direction of the second variable and the search path of the second variable to obtain an optimized second variable;

[0208] The load control result is obtained based on the optimized first variable and the optimized second variable.

[0209] In one embodiment, obtaining multi-region total power data of an air conditioning load aggregation cluster includes:

[0210] Input the rated power and operating status of each air conditioner in any area into the single-area aggregation model to obtain the single-area total power data of any area; the single-area aggregation model is a model that aggregates the power data of each air conditioner in a single area;

[0211] The single-region total power data corresponding to each of the regions is input into a multi-region aggregation model to obtain multi-region total power data of the air-conditioning load aggregation cluster; the multi-region aggregation model is a model for aggregating the power data of each of the regions.

[0212] Each module in the load control device of the above-mentioned air conditioning load aggregation cluster can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0213] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a load control method for an air conditioning load aggregation cluster is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0214] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0215] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0216] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0217] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0218] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0219] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0220] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0221] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A load control method for an air conditioning load aggregation cluster, characterized in that: The method comprises: Obtain multi-region total power data of an air conditioning load aggregation cluster, and obtain the incentive value corresponding to the operating temperature of the air conditioner in the air conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioner in each region of the air conditioning load aggregation cluster, and the incentive value is the compensation value for the air conditioning user during the load regulation process; Determine, according to the multi-region total power data, the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature as the adjusted power; According to the difference between the reference power and the adjusted power, an adjustable potential objective function of the air-conditioning load aggregation cluster is constructed, and according to the adjusted power and the incentive value, a satisfaction objective function of the air-conditioning load aggregation cluster is constructed; the reference power is the average aggregation power of the air-conditioning load aggregation cluster at a reference temperature; Taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization goals, the target variables of the air conditioning load aggregation cluster are optimized to obtain the load control result; the target variables include at least one of the operating status of the air conditioner, the average aggregation power of the air conditioner and the duration of the air conditioner being turned on.

2. The method according to claim 1, characterized in that The obtaining of the incentive value corresponding to the operating temperature of the air conditioner in the air conditioner load aggregation cluster includes: Inputting the operating temperature of the air conditioner in the air conditioner load aggregation cluster into the temperature grading control incentive model to obtain the incentive value corresponding to the operating temperature; The temperature graded control incentive model is expressed as: ； ； D is the satisfaction of air conditioner users, a is the satisfaction calculation coefficient, is the operating temperature of the jth air conditioner in the i-th area at time t, To regulate the temperature, is the incentive value of the kth temperature level, is the incentive value per unit power for the kth temperature level, is the incentive value per unit power of the mth temperature level, and B is the total incentive budget value.

3. The method according to claim 2, characterized in that The adjustable potential objective function is expressed as: ； Said is the adjustable potential objective function, is the average aggregate power of the air conditioning load aggregation cluster at the reference temperature, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature; The satisfaction objective function is expressed as: ； Said is the satisfaction objective function, b is the influence coefficient of temperature deviation on the satisfaction, is the average aggregate power of the air conditioning load aggregation cluster at the regulated temperature, is the incentive value of the kth temperature level.

4. The method according to claim 1, characterized in that: The objective variables of the air conditioning load aggregation cluster are optimized by taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain the load regulation result, including: Taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives, and under the condition of satisfying the constraint conditions, optimizing the objective variables of the air conditioning load aggregation cluster to obtain the load regulation result; The constraints include human comfort constraints, air conditioning load aggregation adjustable potential constraints, room temperature change upper and lower limit constraints, air conditioning minimum downtime constraints and satisfaction constraints; Among them, the human comfort constraint is used to constrain the temperature adjustment amount of each air conditioner in the air-conditioning load aggregation cluster, the air-conditioning load aggregation adjustable potential constraint is used to constrain the average aggregation power of the air-conditioning load aggregation cluster under the regulated temperature, the upper and lower limit constraints of room temperature change are used to constrain the indoor temperature, the air-conditioning minimum downtime constraint is used to constrain the start-up time and shutdown time of the air-conditioning, and the satisfaction constraint is used to constrain the satisfaction of air-conditioning users.

5. The method according to claim 4, characterized in that The optimizing the target variable of the air conditioning load aggregation cluster to obtain the load regulation result includes: Determine a first variable and a second variable from the target variables of the air conditioning load aggregation cluster; the first variable is a target variable whose vector dimension is higher than a dimension threshold, and the second variable is a target variable whose vector dimension is lower than the dimension threshold; For the first variable, randomly select at least two vector dimensions in the first variable as current search directions, establish a search path between a current solution of the first variable and a global optimal solution of the first variable in a current iteration, optimize the first variable according to the current search direction of the first variable and the search path of the first variable, and obtain an optimized first variable; For the second variable, randomly select a vector dimension in the first variable as a current search direction, and establish a search path between a current solution of the second variable and two random solutions of the second variable, and optimize the second variable according to the current search direction of the second variable and the search path of the second variable to obtain an optimized second variable; The load control result is obtained based on the optimized first variable and the optimized second variable.

6. The method according to claim 1, characterized in that The method of obtaining the multi-region total power data of the air conditioning load aggregation cluster includes: Input the rated power and operating status of each air conditioner in any area into the single-area aggregation model to obtain the single-area total power data of any area; the single-area aggregation model is a model that aggregates the power data of each air conditioner in a single area; The single-region total power data corresponding to each of the regions is input into a multi-region aggregation model to obtain multi-region total power data of the air-conditioning load aggregation cluster; the multi-region aggregation model is a model for aggregating the power data of each of the regions.

7. A load control device for an air conditioning load aggregation cluster, characterized in that: The device comprises: An acquisition module is used to acquire multi-region total power data of an air-conditioning load aggregation cluster, and to acquire an incentive value corresponding to the operating temperature of the air conditioner in the air-conditioning load aggregation cluster; the multi-region total power data is the total power data of the air conditioner in each region of the air-conditioning load aggregation cluster, and the incentive value is the compensation value for the air-conditioning user during the load regulation process; A determination module, configured to determine, according to the multi-region total power data, an average aggregate power of the air conditioning load aggregation cluster at the regulated temperature as the adjusted power; A construction module, configured to construct an adjustable potential objective function of the air-conditioning load aggregation cluster according to a difference between a reference power and the adjusted power, and to construct a satisfaction objective function of the air-conditioning load aggregation cluster according to the adjusted power and the incentive value; the reference power is an average aggregate power of the air-conditioning load aggregation cluster at a reference temperature; An optimization module is used to optimize the target variables of the air conditioning load aggregation cluster by taking the maximization of the adjustable potential objective function and the maximization of the satisfaction objective function as optimization objectives to obtain a load control result; the target variables include at least one of the operating status of the air conditioner, the average aggregate power of the air conditioner, and the duration of the air conditioner being turned on.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images