Power demand response optimization method, device, storage medium and computer equipment

Abstract

The present application provides a method, device, storage medium, and computer equipment for optimizing power demand response. The method includes: initializing the initial positions of multiple feasible solutions based on a target optimization function that aims to maximize the total profit of power generation companies and service providers, and each feasible solution includes the operating status and power generation of each generator set corresponding to the target optimization function, that is, using the operating status and power generation of each generator set as decision variables, and using a preset combination rate to determine the state mode of each feasible solution, so as to iteratively update the position of each feasible solution, and finally output the position corresponding to the feasible solution with the maximum profit, that is, the latest target position, and adjust the operating status and power generation of each generator set according to the latest target position. In this way, while ensuring the economic benefits of the power system, it is possible to maintain the supply and demand balance of the power system, thereby improving the utilization rate of power resources.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, apparatus, storage medium, and computer equipment for optimizing power demand response. Background Art

[0002] In recent years, demand response management has become a crucial element in power system operation and management. Applying demand response management to power systems effectively utilizes power resources and maintains stable operation. The primary goal of demand response management is to balance power supply and demand and maintain system stability without congestion of various demand-side resources.

[0003] At present, when implementing demand response management in the power system, the electricity demand during non-peak hours suddenly increases due to the reduction of electricity consumption by electricity users during peak hours, resulting in a load recoil effect. This makes the demand response management less effective, making it difficult for the power system to maintain a balance between supply and demand, thereby reducing the utilization rate of power resources. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the demand response management in the existing technology is poor, the power system has difficulty in maintaining supply and demand balance, and the utilization rate of power resources is reduced.

[0005] In a first aspect, the present application provides a method for optimizing power demand response, the method comprising:

[0006] When a demand response optimization instruction is received, a target optimization function and its corresponding constraints are obtained to initialize the initial positions of multiple feasible solutions; wherein the target optimization function is a mathematical model that aims to maximize the total profit of the power generation company and the service provider, and each feasible solution includes the operating status and power generation of each generator set corresponding to the target optimization function;

[0007] In one iteration, determining a state mode corresponding to each feasible solution among the plurality of feasible solutions according to a preset combination rate;

[0008] Adopt the update strategy corresponding to the state mode of each feasible solution and update the position of each feasible solution;

[0009] Determine a reference total profit and a target total profit; wherein the target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution;

[0010] If the target total profit is greater than the reference total profit, the target position is updated to the position of the feasible solution corresponding to the target total profit determined in this iteration;

[0011] Determine whether the current iteration round is equal to the preset round. If the current iteration round is equal to the preset round, adjust the operating status and power generation of each generator set according to the latest target position. If the current iteration round is less than the preset round, enter the next iteration.

[0012] In one embodiment, determining the state mode corresponding to each feasible solution among the multiple feasible solutions according to a preset combination rate includes:

[0013] Randomly select feasible solutions of a number corresponding to the binding rate from multiple feasible solutions, set the state mode of the randomly selected feasible solutions to tracking mode, and set the state mode of feasible solutions not selected in this iteration to search mode.

[0014] In one embodiment, determining the reference total profit includes:

[0015] If the current iteration round is the first iteration, determine the initial total profit; wherein the initial total profit is the maximum profit among the profits corresponding to the initial positions of each feasible solution;

[0016] Determine the initial total profit as the reference total profit corresponding to this iteration;

[0017] If the current iteration round is not the first iteration, the target total profit determined in the previous iteration round will be determined as the reference total profit in this iteration.

[0018] In one embodiment, an update strategy corresponding to the state mode of each feasible solution is adopted to update the position of each feasible solution, including:

[0019] For any feasible solution in each feasible solution, if the state mode of the feasible solution is search mode, create multiple copies corresponding to the feasible solution;

[0020] According to the preset number of dimensions, the position of each replica corresponding to the feasible solution is updated;

[0021] The feasible solution and each of its corresponding copies are determined as candidate solutions, and the position of the feasible solution is updated to the position with the maximum profit among the profits corresponding to the current positions of the candidate solutions.

[0022] In one embodiment, an update strategy corresponding to the state mode of each feasible solution is adopted to update the position of each feasible solution, including:

[0023] For any feasible solution in each feasible solution, if the state mode of the feasible solution is tracking mode, then determine whether the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration;

[0024] If the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration, the position of the feasible solution is updated using the preset formula;

[0025] If the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to its position in the previous iteration, the profit change range is determined, and the position and speed of the feasible solution are adjusted according to the profit change range, and the adjusted position of the feasible solution is updated using the preset formula.

[0026] In one embodiment, the preset formula is:

[0027]

[0028] Where, The updated position of feasible solution i using the preset formula, is the current position of the feasible solution i, w is the inertia weight, is the current speed of the feasible solution i, C is a preset constant, r is a random number between 0 and 1, is the location of the feasible solution corresponding to the target total profit determined in the previous iteration.

[0029] In one embodiment, based on the profit change, the position and speed of the feasible solution are adjusted according to the following formula:

[0030]

[0031] Where, is the speed at which the feasible solution i is updated according to the profit change, is the current speed of feasible solution i, α is the acceleration factor, ΔP R is the profit change, is the position of the feasible solution i after it is updated according to the profit change range, is the current position of feasible solution i.

[0032] In a second aspect, the present application provides a power demand response optimization device, the device comprising:

[0033] an instruction receiving module, configured to, upon receiving a demand response optimization instruction, obtain a target optimization function and its corresponding constraints to initialize the initial positions of multiple feasible solutions; wherein the target optimization function is a mathematical model that aims to maximize the total profit of the power generation company and the service provider, and each feasible solution includes the operating status and generated power of each generator set corresponding to the target optimization function;

[0034] a state mode determination module, configured to determine, in one iteration, a state mode corresponding to each feasible solution among the plurality of feasible solutions according to a preset combination rate;

[0035] A position update module is used to update the position of each feasible solution by adopting an update strategy corresponding to the state mode of each feasible solution;

[0036] A profit determination module is used to determine a reference total profit and a target total profit; wherein the target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution;

[0037] a target position updating module, configured to update the target position to a position of a feasible solution corresponding to the target total profit determined in this iteration if the target total profit is greater than the reference total profit;

[0038] The iteration judgment module is used to determine whether the current iteration round is equal to the preset round. If the current iteration round is equal to the preset round, the operating status and power generation of each generator set are adjusted according to the latest target position. If the current iteration round is less than the preset round, the next iteration is entered.

[0039] In a third aspect, the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the power demand response optimization method as described in any of the above embodiments.

[0040] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;

[0041] The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, the steps of the power demand response optimization method as described in any one of the above embodiments are performed.

[0042] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0043] The present application provides a method, device, storage medium, and computer equipment for optimizing power demand response. The method includes: initializing the initial positions of multiple feasible solutions based on a target optimization function that aims to maximize the total profit of power generation companies and service providers, and each feasible solution includes the operating status and power generation of each generator set corresponding to the target optimization function, that is, using the operating status and power generation of each generator set as decision variables, and using a preset combination rate to determine the state mode of each feasible solution, so as to iteratively update the position of each feasible solution, and finally output the position corresponding to the feasible solution with the maximum profit, that is, the latest target position, and adjust the operating status and power generation of each generator set according to the latest target position. In this way, while ensuring the economic benefits of the power system, it is possible to maintain the supply and demand balance of the power system, thereby improving the utilization rate of power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 A flow chart of a power demand response optimization method provided in an embodiment of the present application;

[0046] Figure 2 A flowchart illustrating the steps of updating the position of each feasible solution by adopting an update strategy corresponding to the state mode of each feasible solution provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of the structure of a power demand response optimization device provided in an embodiment of the present application;

[0048] Figure 4 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] Understandably, with multiple consumers requesting electricity during the same timeframe, the total electricity demand is high. Consequently, power generation companies are sometimes unable to meet customer requests, leading to customer dissatisfaction or contract termination. Some of the ongoing issues related to power system operations include limited system resource availability, forcing managers to operate the system at its most extreme limits and causing electricity market prices to continue to rise. This has also prompted researchers to explore, investigate, and test new approaches to effectively utilize power resources in power operations.

[0051] Under the premise of exploring new methods, power demand response has become an important direction in the operation of power systems in recent years. The application of demand response management in power systems enables administrators to use power resources effectively while maintaining the safe and stable operation of the power system. However, in the process of implementing power demand response, after electricity users reduce electricity consumption during peak hours, the demand for electricity during non-peak hours increases sharply, resulting in a load recoil effect, which makes the effect of demand response management poor. Therefore, the present application provides a power demand response optimization method, and the following embodiments are described by applying this method to a server. It can be understood that the power demand response optimization method can be executed by a single server or a server cluster consisting of multiple servers, and the present application does not impose specific restrictions on this.

[0052] like Figure 1 As shown, the present application provides a method for optimizing power demand response, the method comprising:

[0053] Step S101: When a demand response optimization instruction is received, a target optimization function and its corresponding constraints are obtained to initialize the initial positions of multiple feasible solutions.

[0054] The objective optimization function is a mathematical model designed to maximize the total profit of the power generation company and the service provider. Each feasible solution includes the operating status and power generation capacity of each generator set corresponding to the objective optimization function. The service provider refers to a demand response service provider.

[0055] In this step, when it is necessary to optimize the power demand response, a demand response optimization instruction can be triggered through the client. When the server receives the demand response optimization instruction, it will obtain the pre-established target optimization function and the constraints corresponding to the target optimization function. Based on the target optimization function and its corresponding constraints, the initial positions of multiple feasible solutions are initialized. Specifically, according to the target optimization function, the solution space corresponding to the target optimization function can be determined, and then according to the constraints, the upper and lower limits of the parameters in the initial position of the feasible solution can be determined. Combined with the upper and lower limits of the parameters in the initial position of the feasible solution, the target solution space can be obtained. The initialization of the initial positions of multiple feasible solutions can be completed by randomly selecting a certain number of feasible solutions in the target solution space.

[0056] It can be understood that the position of each feasible solution represents a solution that satisfies the objective optimization function, and the solution to the objective optimization function represents the operating state and power generation of each corresponding generator set. The operating state is either a start state or a stop state, which can be represented by 0 and 1 respectively.

[0057] Specifically, the objective optimization function can be expressed as:

[0058] Max(P R )=TR v -TO cost

[0059] Where, P R is the total profit of the power generation company and the service provider, Max(P R ) represents the objective of the objective optimization function, which is to maximize the total profit of the power generation company and the service provider. v is the total revenue of power generation companies and service providers, TO cost is the sum of the total operating costs of the power generation company and the service provider.

[0060] Among them, TR v The expression can be expressed as follows:

[0061]

[0062] Where t is the time index, T is the total duration, N is the number of generator sets, i is the index of the generator set, represents the power generated by generator set i at hour t, represents the predicted spot price of generator set i, Indicates the operating status of generator set i at hour t. When , it means that the corresponding generator set is in the stopped state. , it indicates that the corresponding generator set is in the starting state.

[0063] It can be understood that the predicted spot price of generator set i refers to the transaction price of the power generated by generator set i in the predicted spot transaction.

[0064] Among them, TO cost The expression can be expressed as follows:

[0065]

[0066] Where, is the total operating cost of the power generation company, is the total operating cost of the service provider.

[0067] in, The expression can be expressed as follows:

[0068]

[0069] Where t is the time index, T is the total duration, N is the number of generator sets, i is the index of the generator set, is the fuel cost of generator set i, which is determined by the quadratic function of the power generated by generator set i, a i 、b i 、c i are the coefficients of the quadratic function, is the power generated by generator set i, represents the power generated by generator set i at hour t, SU cost is the startup cost of the generator set, P cost is the fixed cost of the generator set.

[0070] The constraints corresponding to the objective optimization function include:

[0071] (1) Equality constraint: This represents the power balance between generation and load, i.e., the total generated power should be equal to the required power. The expression can be expressed as:

[0072]

[0073] Where t is the time index, T is the total duration, N is the number of generator sets, i is the index of the generator set, represents the power generated by generator set i at hour t, represents the operating status of generator set i at hour t, It represents the total power demand at hour t.

[0074] (2) Inequality constraint: It indicates that the power generation limit should be within the power generation limit of the generator set. It can be expressed as:

[0075]

[0076] Where N is the number of generator sets, i is the index of the generator set, and t is the time index. represents the power generated by generator set i at hour t, represents the minimum power generation of generator set i,

[0077] Indicates the maximum power generation of generator set i.

[0078] Step S102: In one iteration, a state mode corresponding to each feasible solution among a plurality of feasible solutions is determined according to a preset combination rate.

[0079] The merging rate, also known as the grouping rate, refers to the proportion of feasible solutions in tracking mode among multiple feasible solutions. Typically, most feasible solutions are in search mode, while a small number are in tracking mode. Therefore, the merging rate is relatively small. State modes include tracking mode and search mode.

[0080] In this step, the multiple feasible solutions determined in step S101 can be set to tracking mode or search mode according to a preset combination rate, so as to determine the method of updating the position of the feasible solution according to the state mode of each feasible solution.

[0081] Step S103: adopt an update strategy corresponding to the state mode of each feasible solution to update the position of each feasible solution.

[0082] In this step, after the state mode of each feasible solution is determined, the position of each feasible solution can be updated according to the update strategy corresponding to the state mode of each feasible solution.

[0083] Step S104: Determine the reference total profit and the target total profit.

[0084] The target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution. The reference total profit is the profit in the current iteration used to compare with the target total profit.

[0085] In this step, it is necessary to determine the maximum profit among the profits corresponding to the current position of each feasible solution as the target total profit corresponding to this iteration, and determine the reference total profit in the current iteration for comparison with the target total profit.

[0086] Step S105: If the target total profit is greater than the reference total profit, the target position is updated to the position of the feasible solution corresponding to the target total profit determined in this iteration.

[0087] In this step, when the target total profit is greater than the reference total profit, the target position needs to be updated. When the target total profit is not greater than the reference total profit, the target position does not need to be updated, and step S106 and subsequent steps are directly executed.

[0088] It is understandable that the target position has a preset initial default value, that is, the initial default value before the target position is updated. The initial default value of the target position can be set to the position with the largest profit among the profits corresponding to the initial positions of multiple feasible solutions.

[0089] Step S106: Determine whether the current iteration round is equal to the preset round.

[0090] Among them, the preset rounds can be set by relevant personnel based on experience.

[0091] It is understandable that whether the current iteration round is equal to the preset round is used as the exit condition of the iteration, that is, when the number of iterations reaches the preset round, the iteration can be exited to obtain the latest position.

[0092] Step S107: If the current iteration round is equal to the preset round, the operating state and power generation of each generator set are adjusted according to the latest target position.

[0093] In this step, each feasible solution position represents a solution to the target optimization function, which includes the operating status and power generation of each generator set. Therefore, the target position also includes the operating status and power generation of each generator set. Furthermore, the latest target position is the optimal position that satisfies the target optimization function. Therefore, the operating status and power generation of each generator set can be adjusted based on the latest target position to optimize the power demand response.

[0094] Step S108: If the current iteration round is less than the preset round, proceed to the next iteration.

[0095] The present application provides a method, device, storage medium, and computer equipment for optimizing power demand response. The method includes: initializing the initial positions of multiple feasible solutions based on a target optimization function that aims to maximize the total profit of power generation companies and service providers, and each feasible solution includes the operating status and power generation of each generator set corresponding to the target optimization function, that is, using the operating status and power generation of each generator set as decision variables, and using a preset combination rate to determine the state mode of each feasible solution, so as to iteratively update the position of each feasible solution, and finally output the position corresponding to the feasible solution with the maximum profit, that is, the latest target position, and adjust the operating status and power generation of each generator set according to the latest target position. In this way, while ensuring the economic benefits of the power system, it is possible to maintain the supply and demand balance of the power system, thereby improving the utilization rate of power resources.

[0096] In one embodiment, determining a state mode corresponding to each feasible solution among a plurality of feasible solutions according to a preset combination rate includes:

[0097] Randomly select feasible solutions of a number corresponding to the binding rate from multiple feasible solutions, set the state mode of the randomly selected feasible solutions to tracking mode, and set the state mode of the feasible solutions not selected in this iteration to search mode.

[0098] In this embodiment, a number of feasible solutions corresponding to the binding rate can be randomly selected based on the binding rate, and the state of the randomly selected feasible solutions can be set to tracking mode, while the state mode of the remaining feasible solutions can be set to search mode. It is understood that the selection of feasible solutions can also be based on preset selection rules, as long as the binding rate is satisfied. This application does not impose specific limitations on this.

[0099] Furthermore, a higher binding rate results in a greater degree of merging between feasible solutions. This means that closer feasible solutions are more likely to merge, reducing population diversity and accelerating the algorithm's convergence, but this may lead to trapping in local optimal solutions. Conversely, a lower binding rate results in less merging between feasible solutions. This means that feasible solutions are kept farther apart, increasing population diversity and improving the algorithm's global search capabilities. Therefore, the binding rate setting can be adjusted based on the specific problem. For simple problems or those with good initial solutions, the binding rate can be appropriately increased to accelerate algorithm convergence. For complex problems or those that require a more comprehensive search of the solution space, the binding rate can be appropriately reduced to increase the algorithm's global search capabilities.

[0100] In one embodiment, determining the reference total profit includes:

[0101] If the current iteration round is the first iteration, determine the initial total profit; the initial total profit is the maximum profit among the profits corresponding to the initial positions of each feasible solution;

[0102] Determine the initial total profit as the reference total profit corresponding to this iteration;

[0103] If the current iteration round is not the first iteration, the target total profit determined in the previous iteration round will be determined as the reference total profit in this iteration.

[0104] In this embodiment, when the current iteration is the first, the maximum profit corresponding to the initial position of each feasible solution is determined and used as the reference total profit for the current iteration. If the current iteration is not the first, the target total profit determined in the previous iteration is used as the reference total profit for the current iteration. In this way, a feasible solution that maximizes the total profit of the power generation company and the service provider can be found, maintaining the supply and demand balance of the power system while ensuring the economic benefits of the power system, thereby improving the utilization rate of power resources.

[0105] like Figure 2 As shown, in one embodiment, an update strategy corresponding to the state mode of each feasible solution is adopted to update the position of each feasible solution, including:

[0106] Step S201: for any feasible solution among each feasible solution, determine whether the state mode of the feasible solution is a search mode.

[0107] In this step, it is necessary to first judge the state mode of each feasible solution, and then adopt the update strategy corresponding to its state mode to update its position.

[0108] It is understandable that in search mode, feasible solutions will move towards the direction of the global optimal solution and the individual optimal solution in the hope of finding a better solution. In tracking mode, feasible solutions will move towards the direction of the historical optimal solution in the hope of converging to the global optimal solution faster.

[0109] Step S202: If the state mode of the feasible solution is the search mode, create multiple copies corresponding to the feasible solution.

[0110] In this step, when the state mode of the feasible solution is the search mode, multiple copies corresponding to the feasible solution are created, which may specifically include: determining the search memory size of the feasible solution, and copying the feasible solution multiple copies according to the search memory size of the feasible solution; wherein the number of copies can be determined according to the search memory size of the feasible solution.

[0111] Step S203: updating the position of each replica corresponding to the feasible solution according to a preset number of dimensions.

[0112] The number of dimensions refers to the seeking range of selected dimensions (SRD), which specifies the amount of change in the selected dimension. A typical value is 0.2.

[0113] In this step, the number of dimensions may be randomly added or subtracted based on the current position of each replica to update the position of each replica corresponding to the feasible solution.

[0114] Step S204: The feasible solution and each of its corresponding copies are determined as candidate solutions, and the position of the feasible solution is updated to the position with the maximum profit among the profits corresponding to the current positions of the candidate solutions.

[0115] In this step, the feasible solution and each of its corresponding copies can be determined as candidate solutions, and the candidate solution with the maximum corresponding profit is selected from each candidate solution, and the position of the feasible solution is updated to the position of the selected candidate solution.

[0116] Step S205: If the state mode of the feasible solution is the tracking mode, it is determined whether the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration.

[0117] In this step, if the state mode of the feasible solution is tracking mode, it is determined whether the current profit corresponding to the feasible solution is greater than the profit corresponding to the previous iteration. Based on the direction of profit change, it is determined whether the position and speed of the feasible solution need to be adjusted according to the magnitude of the profit change.

[0118] Step S206: If the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration, the position of the feasible solution is updated using a preset formula.

[0119] It can be understood that when the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to its position in the previous iteration, it means that the feasible solution is moving in a better direction. At this time, there is no need to update the position and speed of the feasible solution according to the profit change amplitude. Instead, the position of the feasible solution can be directly updated using the preset formula.

[0120] Step S207: If the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to the position in the previous iteration, the profit change range is determined, and the position and speed of the feasible solution are adjusted according to the profit change range, and the adjusted position of the feasible solution is updated using a preset formula.

[0121] In this step, when the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to its position in the previous iteration, it is necessary to adjust the position and speed of the feasible solution according to the profit change, and finally use the preset formula to update the position of the adjusted feasible solution.

[0122] It can be understood that by comparing the profit of each feasible solution in the current iteration with the profit in the previous iteration, the results of the comparison determine whether the position and speed of the feasible solution need to be adjusted based on the magnitude of the profit change. This can improve the convergence and search capabilities of the algorithm, thereby obtaining the optimal solution and improving the effectiveness of power demand response. While ensuring the economic benefits of the power system, it also maintains the supply and demand balance of the power system and improves the utilization rate of power resources.

[0123] In one embodiment, the preset formula is:

[0124]

[0125] Where, The updated position of feasible solution i using the preset formula, is the current position of the feasible solution i, w is the inertia weight, is the current speed of the feasible solution i, C is a preset constant, r is a random number between 0 and 1, is the location of the feasible solution corresponding to the target total profit determined in the previous iteration.

[0126] It can be understood that, in this embodiment, is the current position of feasible solution i, which refers to the position of feasible solution i when using the preset formula. is the current speed of feasible solution i, which refers to the speed of feasible solution i when using the preset formula.

[0127] Exemplarily, when executing step S206, is the position of the feasible solution i after the last iteration, is the speed of the feasible solution i after the last iteration. When executing step S207, is the position of the feasible solution i after adjusting the profit change, It is the speed of feasible solution i after adjusting according to the profit change.

[0128] In one embodiment, the position and speed of the feasible solution are adjusted according to the following formula based on the profit change:

[0129]

[0130] Where, is the speed at which the feasible solution i is updated according to the profit change, is the current speed of feasible solution i, α is the acceleration factor, ΔP R is the profit change, is the position of the feasible solution i after it is updated according to the profit change range, is the current position of feasible solution i.

[0131] It can be understood that, in this embodiment, is the current position of feasible solution i, which refers to the position of feasible solution i when the position and speed are adjusted according to the profit change range. is the current speed of feasible solution i, which refers to the speed of feasible solution i when the position and speed are adjusted according to the profit change.

[0132] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed 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 portion of steps or stages in other steps.

[0133] The power demand response optimization device provided in an embodiment of the present application is described below. The power demand response optimization device described below and the power demand response optimization method described above can be referenced to each other.

[0134] like Figure 3 As shown, the present application provides a power demand response optimization device 300, which includes:

[0135] The instruction receiving module 301 is configured to, upon receiving a demand response optimization instruction, obtain a target optimization function and its corresponding constraints to initialize the initial positions of multiple feasible solutions; wherein the target optimization function is a mathematical model that aims to maximize the total profit of the power generation company and the service provider, and each feasible solution includes the operating status and generated power of each generator set corresponding to the target optimization function;

[0136] The state mode determination module 302 is used to determine the state mode corresponding to each feasible solution among multiple feasible solutions according to a preset combination rate in one iteration;

[0137] A position updating module 303 is configured to update the position of each feasible solution by adopting an update strategy corresponding to the state mode of each feasible solution;

[0138] The profit determination module 304 is used to determine a reference total profit and a target total profit; wherein the target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution;

[0139] A target position updating module 305 is configured to update the target position to the position of the feasible solution corresponding to the target total profit determined in this iteration if the target total profit is greater than the reference total profit;

[0140] The iteration judgment module 306 is used to determine whether the current iteration round is equal to the preset round. If the current iteration round is equal to the preset round, the operating status and power generation of each generator set are adjusted according to the latest target position. If the current iteration round is less than the preset round, the next iteration is entered.

[0141] In one embodiment, the state mode determination module includes:

[0142] The mode determination submodule is used to randomly select feasible solutions of a number corresponding to the binding rate from multiple feasible solutions, set the state mode of the randomly selected feasible solutions to the tracking mode, and set the state mode of the feasible solutions not selected in this iteration to the search mode.

[0143] In one embodiment, the profit determination module includes:

[0144] The first judgment submodule is used to determine the initial total profit if the current iteration round is the first iteration; wherein the initial total profit is the maximum profit among the profits corresponding to the initial positions of each feasible solution;

[0145] A determination submodule, used to determine the initial total profit as the reference total profit corresponding to this iteration;

[0146] The second judgment submodule is used to determine the target total profit determined in the previous iteration round as the reference total profit in this iteration if the current iteration round is not the first iteration.

[0147] In one embodiment, the location update module includes:

[0148] A replica creation submodule is used to create multiple replicas corresponding to any one of the feasible solutions if the state mode of the feasible solution is a search mode;

[0149] A replica position update submodule is used to update the position of each replica corresponding to the feasible solution according to a preset number of dimensions;

[0150] The first position updating submodule is configured to determine the feasible solution and each of its corresponding copies as candidate solutions, and update the position of the feasible solution to a position having the maximum profit among the profits corresponding to the current positions of the candidate solutions.

[0151] In one embodiment, the location update module includes:

[0152] The third judgment submodule is used to determine, for any feasible solution among each feasible solution, whether the profit corresponding to the position of the feasible solution in the current iteration is greater than the profit corresponding to the position in the previous iteration if the state mode of the feasible solution is the tracking mode;

[0153] The second position updating submodule is configured to update the position of the feasible solution using a preset formula if the profit corresponding to the position of the feasible solution in the current iteration is greater than the profit corresponding to the position in the previous iteration;

[0154] The third position update submodule is used to determine the profit change range if the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to its position in the previous iteration, adjust the position and speed of the feasible solution according to the profit change range, and update the adjusted position of the feasible solution using a preset formula.

[0155] The division of the various modules in the above-mentioned power demand response optimization device is only for illustration. In other embodiments, the power demand response optimization device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned power demand response optimization device. The various modules in the above-mentioned power demand response optimization device can be implemented in whole or in part by software, hardware, or a combination thereof. 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 operations corresponding to the above-mentioned modules.

[0156] In one embodiment, the present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the power demand response optimization method as described in any of the above embodiments.

[0157] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the power demand response optimization method as described in any one of the above embodiments.

[0158] Schematically, as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 400 can be provided as a server. Figure 4 Computer device 400 includes a processing component 402, which further includes one or more processors, and a memory resource represented by memory 401 for storing instructions executable by processing component 402, such as an application. The application stored in memory 401 may include one or more modules, each corresponding to a set of instructions. In addition, processing component 402 is configured to execute the instructions to perform the power demand response optimization method of any of the above-described embodiments.

[0159] The computer device 300 may further include a power supply component 403 configured to perform power management of the computer device 400, a wired or wireless network interface 404 configured to connect the computer device 400 to a network, and an input / output (I / O) interface 405. The computer device 400 may operate based on an operating system stored in the memory 401, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0160] Those skilled in the art will understand that Figure 4 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0161] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment comprising a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or equipment comprising the elements. Herein, the singular forms "one", "an" and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the existence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the existence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0162] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0163] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing power demand response, characterized in that: The method comprises: When a demand response optimization instruction is received, a target optimization function and its corresponding constraints are obtained to initialize the initial positions of multiple feasible solutions; wherein the target optimization function is a mathematical model that aims to maximize the total profit of the power generation company and the service provider, and each feasible solution includes the operating status and power generation of each generator set corresponding to the target optimization function; In one iteration, determining a state mode corresponding to each feasible solution among the plurality of feasible solutions according to a preset combination rate; For any feasible solution in each feasible solution, if the state mode of the feasible solution is tracking mode, then determine whether the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration; If the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration, the position of the feasible solution is updated using the preset formula; If the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to the position in the previous iteration, then determining the profit change range, adjusting the position and speed of the feasible solution according to the profit change range, and updating the adjusted position of the feasible solution using the preset formula; Determine a reference total profit and a target total profit; wherein the target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution; If the target total profit is greater than the reference total profit, the target position is updated to the position of the feasible solution corresponding to the target total profit determined in this iteration; Determine whether the current iteration round is equal to the preset round. If the current iteration round is equal to the preset round, adjust the operating status and power generation of each generator set according to the latest target position. If the current iteration round is less than the preset round, enter the next iteration; The objective optimization function is expressed as: Max(P R )=TR v -TO cost Where, P R is the total profit of the power generation company and the service provider, TR v is the total revenue of power generation companies and service providers, TO cost is the sum of the total operating costs of the power generation company and the service provider, where TR v andTO cost The expressions are: Where t is the time index, T is the total duration, N is the number of generator sets, i is the index of the generator set, represents the power generated by generator set i at hour t, represents the predicted spot price of generator set i, represents the operating status of generator set i at hour t; Where, is the total operating cost of the power generation company, is the total operating cost of the service provider, The expression is: Where, is the fuel cost of generator set i, which is determined by the quadratic function of the power generated by generator set i, a i 、b i 、c i are the coefficients of the quadratic function, is the power generated by generator set i, SU cost is the starting cost of the generator set, P cost Fixed costs for the generator sets; According to the profit change range, the position and speed of the feasible solution are adjusted according to the following formula: Where, is the speed at which the feasible solution i is updated according to the profit change, is the current speed of feasible solution i, α is the acceleration factor, ΔP R is the profit change, is the position of the feasible solution i after it is updated according to the profit change range, is the current position of feasible solution i.

2. The power demand response optimization method according to claim 1, characterized in that: The determining, according to a preset combination rate, a state mode corresponding to each feasible solution among the plurality of feasible solutions includes: Randomly select feasible solutions of a number corresponding to the binding rate from multiple feasible solutions, set the state mode of the randomly selected feasible solutions to tracking mode, and set the state mode of feasible solutions not selected in this iteration to search mode.

3. The power demand response optimization method according to claim 1, characterized in that: Determine the reference gross profit, including: If the current iteration round is the first iteration, determine the initial total profit; wherein the initial total profit is the maximum profit among the profits corresponding to the initial positions of each feasible solution; Determine the initial total profit as the reference total profit corresponding to this iteration; If the current iteration round is not the first iteration, the target total profit determined in the previous iteration round will be determined as the reference total profit in this iteration.

4. The power demand response optimization method according to claim 1, characterized in that: Adopt the update strategy corresponding to the state mode of each feasible solution to update the position of each feasible solution, including: For any feasible solution in each feasible solution, if the state mode of the feasible solution is search mode, create multiple copies corresponding to the feasible solution; According to the preset number of dimensions, the position of each replica corresponding to the feasible solution is updated; The feasible solution and each of its corresponding copies are determined as candidate solutions, and the position of the feasible solution is updated to the position with the maximum profit among the profits corresponding to the current positions of the candidate solutions.

5. The power demand response optimization method according to claim 4, characterized in that: The preset formula is: Where, The updated position of feasible solution i using the preset formula, is the current position of the feasible solution i, w is the inertia weight, is the current speed of the feasible solution i, C is a preset constant, r is a random number between 0 and 1, is the location of the feasible solution corresponding to the target total profit determined in the previous iteration.

6. A power demand response optimization device, characterized in that: The device comprises: an instruction receiving module, configured to, upon receiving a demand response optimization instruction, obtain a target optimization function and its corresponding constraints to initialize the initial positions of multiple feasible solutions; wherein the target optimization function is a mathematical model that aims to maximize the total profit of the power generation company and the service provider, and each feasible solution includes the operating status and generated power of each generator set corresponding to the target optimization function; a state mode determination module, configured to determine, in one iteration, a state mode corresponding to each feasible solution among the plurality of feasible solutions according to a preset combination rate; A position updating module is used to determine, for any one of the feasible solutions, whether the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration if the state mode of the feasible solution is a tracking mode; if the profit corresponding to the position of the feasible solution in this iteration is greater than the profit corresponding to the position in the previous iteration, update the position of the feasible solution using a preset formula; if the profit corresponding to the position of the feasible solution in this iteration is not greater than the profit corresponding to the position in the previous iteration, determine the profit change range, adjust the position and speed of the feasible solution according to the profit change range, and update the adjusted position of the feasible solution using the preset formula; A profit determination module is used to determine a reference total profit and a target total profit; wherein the target total profit is the maximum profit among the profits corresponding to the current position of each feasible solution; a target position updating module, configured to update the target position to a position of a feasible solution corresponding to the target total profit determined in this iteration if the target total profit is greater than the reference total profit; An iteration judgment module is used to judge whether the current iteration round is equal to the preset round. If the current iteration round is equal to the preset round, the operating state and power generation of each generator set are adjusted according to the latest target position. If the current iteration round is less than the preset round, the next iteration is entered; The objective optimization function is expressed as: Max(P R )=TR v -TO cost Where, P R is the total profit of the power generation company and the service provider, TR v is the total revenue of power generation companies and service providers, TO cost is the sum of the total operating costs of the power generation company and the service provider, where TR v andTO cost The expressions are: Where t is the time index, T is the total duration, N is the number of generator sets, i is the index of the generator set, represents the power generated by generator set i at hour t, represents the predicted spot price of generator set i, represents the operating status of generator set i at hour t; Where, is the total operating cost of the power generation company, is the total operating cost of the service provider, The expression is: Where, is the fuel cost of generator set i, which is determined by the quadratic function of the power generated by generator set i, a i 、b i 、c i are the coefficients of the quadratic function, is the power generated by generator set i, SU cost is the starting cost of the generator set, P cost Fixed costs for the generator sets; According to the profit change range, the position and speed of the feasible solution are adjusted according to the following formula: Where, is the speed at which the feasible solution i is updated according to the profit change, is the current speed of feasible solution i, α is the acceleration factor, ΔP R is the profit change, is the position of the feasible solution i after it is updated according to the profit change range, is the current position of feasible solution i.

7. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to perform the steps of the power demand response optimization method according to any one of claims 1 to 5.

8. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, execute the steps of the power demand response optimization method according to any one of claims 1 to 5.

Images