A method for consistent control of distributed adjustable capacity and time in a virtual power plant

Abstract

This invention discloses a method for consistent control of distributed adjustable capacity and time in a virtual power plant, relating to the field of power system regulation. First, it collects consistency control information of resources within the virtual power plant, including adjustable capacity, sustainable adjustment time, communication cost, economic cost, capacity reliability cost, and time reliability cost. Then, it constructs consistency indicators for the participation of distributed resources within the virtual power plant in regulation. When some users cannot meet the consistency indicators for adjustable capacity or adjustable time, it employs a distributed adjustable capacity consistency control method based on the PSO algorithm and a distributed adjustable time consistency control method based on the LSTM algorithm, respectively. The PSO algorithm is used to optimize the combination of distributed users to find the optimal adjustable capacity combination that satisfies the constraints. The LSTM algorithm is then used to optimize the combination of distributed users in the time dimension to find the optimal adjustable time combination that satisfies the constraints.

Description

Technical Field

[0001] This invention relates to the field of power system regulation, and in particular to a method for consistent control of distributed adjustable capacity and time in a virtual power plant. Background Technology

[0002] A Virtual Power Plant (VPP) is an innovative energy management system that integrates and optimizes various distributed energy resources (such as solar power, wind power, energy storage systems, and controllable loads) located in different geographical locations to form a unified, dispatchable power supply or demand unit. The VPP does not directly own these distributed resources; instead, it uses advanced communication technologies and intelligent control strategies to remotely monitor, dispatch, and optimize their allocation, thereby providing flexible, reliable, and economical power services.

[0003] Consistent control of the distributed adjustable capacity and time of virtual power plants has the following advantages: it can improve regulation efficiency, achieve coordinated optimization of distributed resources, and increase resource adjustability margin; it can ensure system stability, avoid timing mismatches, and enhance the reliability and security of grid operation; it can optimize economic benefits, enhance the competitiveness of virtual power plants in the market, and reduce regulation costs; it can promote energy transition, adapt to the needs of renewable energy integration, and promote resource synergy and low-carbon development. However, existing methods have the following shortcomings:

[0004] 1) The consistency of distributed resource participation in regulation lacks standardization. There is no unified evaluation index for the regulation capacity of distributed resources (such as load regulation and energy storage charging and discharging capacity), making it difficult to quantify the degree of synergy between resources. There is a lack of analysis on margin matching during the regulation of distributed resources, which may lead to overload or idleness of some resources. The response time of different resources varies significantly (such as the fast response of energy storage systems and the slow regulation of industrial loads), and there is a lack of coordination mechanism in the time dimension. Existing methods are mostly based on simple time alignment or delay control, and fail to fully consider dynamic time consistency.

[0005] 2) Limitations of regulation methods: Traditional optimization algorithms (such as linear programming and genetic algorithms) are difficult to balance convergence speed and global optimal solution when dealing with complex nonlinear distributed regulation problems; regulation methods based on static time windows fail to adapt to dynamic demand changes and are prone to response lag or insufficient regulation; lack in-depth mining of historical data and time series characteristics, resulting in weak predictive ability.

[0006] 3) Insufficient overall system performance and inconsistent resource regulation may lead to unstable overall performance of the virtual power plant; failure to balance resource utilization efficiency and regulation costs may result in a decline in the economic benefits of the virtual power plant.

[0007] Furthermore, Particle Swarm Optimization (PSO) is a swarm intelligence-based optimization algorithm with advantages such as fast convergence speed and strong global search capability. However, existing methods have not fully utilized the advantages of PSO in solving complex optimization problems. Control methods based on static time windows fail to adapt to dynamic demand changes, easily leading to response lag or insufficient adjustment; they also lack in-depth mining of historical data and time series characteristics, resulting in weak predictive capabilities. Long Short-Term Memory (LSTM) networks are a special type of recurrent neural network (RNN) capable of capturing long-term dependencies in time series, making them suitable for time series forecasting and pattern recognition. However, existing methods have not applied LSTM to the control and prediction of virtual power plants.

[0008] To address these issues, we designed a method for consistent control of distributed adjustable capacity and time in a virtual power plant. Summary of the Invention

[0009] The purpose of this invention is to improve consistency by optimizing the PSO algorithm to achieve efficient coordination of distributed resource regulation capacity and ensuring temporal synchronization of the regulation process through LSTM algorithm prediction. This improves system stability and economy, enhances resource utilization efficiency, and reduces the risks of resource idleness and overload; optimizes regulation costs, and maximizes the benefits of the virtual power plant. Furthermore, it enhances adaptability and intelligence, dynamically adapting to changes in resources and demand, and promoting the development of virtual power plants towards intelligence and automation.

[0010] To achieve the above objectives, this invention proposes a method for consistent control of distributed adjustable capacity and time in a virtual power plant, comprising the following steps:

[0011] Step S1: Collect consistency control information of internal resources of the virtual power plant. The consistency control information includes the adjustable capacity, sustainable adjustment time, user communication cost, user economic cost, user capacity trusted cost, and user time trusted cost of each user.

[0012] Step S2: Based on the consistency control information collected in Step S1, a consistency index for the participation of distributed resources in the virtual power plant in regulation is constructed. This consistency index stipulates that a user can participate in the regulation of the virtual power plant only when the user's adjustable capacity is greater than a preset capacity threshold and the sustainable adjustment time is greater than a preset time threshold. The consistency index includes an adjustable capacity consistency index and an adjustable time consistency index.

[0013] Step S3: In the virtual power plant control process, when some users fail to meet the adjustable capacity consistency index in step S2, a distributed adjustable capacity consistency control method based on particle swarm optimization algorithm is proposed. First, a distributed adjustable capacity consistency control objective function for the virtual power plant is constructed, with the goal of minimizing communication, economic, and reliable capacity costs, and corresponding constraints are set. Then, based on the particle swarm optimization algorithm, the distributed users are combined for optimization to find the optimal adjustable capacity combination that meets the constraints, and the consistent adjustable capacity of the distributed user combination is calculated based on the combination result.

[0014] Step S4: In the virtual power plant control process, when some users cannot meet the adjustable time consistency index in step S2, a distributed adjustable time consistency control method for virtual power plants based on the Long Short-Term Memory (LSTM) network algorithm is proposed. First, a distributed adjustable time consistency control objective function for virtual power plants is constructed, with the goal of minimizing communication, economic, and reliable time costs, and corresponding constraints are set. Then, based on the LSM network algorithm, the distributed users are combined and optimized to find the optimal adjustable time combination that meets the constraints, and the consistency adjustable time of the distributed user combination is calculated based on the combination result.

[0015] Preferably, in step S1, the consistency control information of the virtual power plant's internal resources is collected as shown in the following formula:

[0016]

[0017] In the formula: X i (t) represents the consistency control information of virtual power plant user i collected at time t; △P i (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let be the capacity reliability cost of user i collected at time t. Let t be the time reliability cost of collecting data from user i.

[0018] Preferably, in step S2, the consistency index for the participation of distributed resources in the regulation and control within the virtual power plant is constructed as shown in the following formula:

[0019] △P i (t)≥△P min (2)

[0020] △T i (t)≥△T min (3) Where: △Pi (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min For adjustable time thresholds, only adjustable capacity ΔP is available. i (t) is greater than the adjustable capacity threshold ΔP min And the adjustment time △T can be sustained i (t) is greater than the adjustable time threshold ΔT min Only users with certain qualifications can participate in the virtual power plant control.

[0021] Preferably, in step S3, during the virtual power plant control process, when a user fails to meet the adjustable capacity consistency index in step S2, a virtual power plant distributed adjustable capacity consistency control method based on particle swarm optimization algorithm is proposed; this method is expressed by the following formula:

[0022] min F C (4)

[0023]

[0024] ψ C (i,j)=ψ i (t)+ψ j (t) (7)

[0025]

[0026] △P i (t)+△P j (t)≥△P min (11)

[0027]

[0028] δ' C =f PSO (X C (t)) (13)

[0029] △P i ' ,j (t)=△P i (t)+△P j (t),δ' C (i,j)=1 (14) where: F C The goal is to achieve consistent control of the distributed adjustable capacity of a virtual power plant. Let ψ be the communication cost matrix for capacity combinations. C Let λ be the economic cost matrix of capacity combinations. C For the reliable capacity cost matrix, δC It is a capacity combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix. C (i,j) is the element in the i-th row and j-th column of the economic cost matrix, λ C (i,j) is the element in the i-th row and j-th column of the reliable capacity cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let be the capacity reliability cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the capacity reliability cost of user j collected at time t, m be the number of users participating in the adjustable capacity combination, and ΔP be the value of P. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min Adjustable time threshold; X C (t) represents the input sample for the particle swarm optimization algorithm, δ' C δ' is the adjustable capacity user combination matrix output by the particle swarm optimization algorithm. C (i,j) are the elements of the adjustable capacity user combination matrix output by the particle swarm optimization algorithm, f PSO () represents the distributed adjustable capacity consistency solution model for a virtual power plant based on the particle swarm optimization algorithm, where △P i ' ,j (t) represents the consistent adjustable capacity calculated based on the combined output results of the particle swarm optimization algorithm.

[0030] Preferably, in the virtual power plant control process, when a user fails to meet the adjustable time consistency index in step S2, a distributed adjustable time consistency control method for virtual power plants based on LSTM is proposed; this method is expressed by the following formula:

[0031] min F T (15)

[0032]

[0033] ψ T (i,j)=ψ i (t)+ψ j (t) (18)

[0034]

[0035] △T i (t)+△T j (t)≥△T min (twenty two)

[0036]

[0037] δ' T =f LSTM (X T (t)) (24)

[0038] △T i ' ,j (t)=△T i (t)+△T j (t),δ' T (i,j)=1 (25)

[0039] In the formula: F T The objective is to achieve distributed, adjustable time consistency control for virtual power plants. Let ψ be the communication cost matrix for time combination. T Let λ be the economic cost matrix for time combinations. T Let δ be the reliable time cost matrix. T This is a time combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix for time combination. T (i,j) is the element in the i-th row and j-th column of the economic cost matrix of time combinations, λ T (i,j) is the element in the i-th row and j-th column of the reliable time cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let t be the time-based reliable cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the time reliability cost of user j collected at time t, n be the number of users participating in the adjustable time combination, and ΔP. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min For an adjustable time threshold, X T (t) represents the input sample for the Long Short-Term Memory (LSTM) network algorithm, δ'T δ' is the adjustable-time user combination matrix output by the Long Short-Term Memory (LSTM) network algorithm. T (i,j) are the elements of the adjustable-time user combination matrix output by the Long Short-Term Memory (LSTM) network algorithm, f LSTM () represents the distributed adjustable time consistency solution model for a virtual power plant based on the Long Short-Term Memory (LSTM) network algorithm, where ΔT i ' ,j (t) is the consistency adjustable time calculated based on the LSTM output combination result.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] 1. By constructing a virtual power plant internal resource consistency control information acquisition technology, this invention can comprehensively and accurately collect the adjustable information and control cost information of each user within the virtual power plant, providing a solid information foundation for consistency control. Through the proposed distributed adjustable capacity and time consistency control method based on PSO algorithm and LSTM algorithm, this invention achieves accurate coordination and prediction of distributed resource adjustment capacity and adjustment time, significantly improving the consistency control level of the virtual power plant.

[0042] 2. The consistency index for the participation of distributed resources in the regulation of a virtual power plant constructed in this invention effectively screens distributed resources that meet regulation requirements, reducing unnecessary computation and regulation costs. By optimizing the combination of distributed users using the PSO algorithm, this invention identifies the adjustable resource combination with the lowest communication, economic, and reliable capacity costs, achieving efficient resource utilization and cost minimization. The application of the LSTM algorithm further enhances consistency control in the time dimension, reducing additional costs caused by time mismatches. Through accurate prediction and collaborative control, this invention reduces the grid operation risks caused by time mismatches, improving the reliability and security of the power grid.

[0043] 3. This invention combines advanced PSO and LSTM algorithms to achieve intelligent control and automated scheduling of distributed resources in virtual power plants, promoting the development of virtual power plants towards intelligence and automation. This method not only improves the accuracy and efficiency of regulation, but also reduces the reliance on manual intervention, thereby enhancing the overall operation level of virtual power plants. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating a method for consistent control of distributed adjustable capacity and time in a virtual power plant, as described in an embodiment of the present invention. Detailed Implementation

[0045] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0046] Please see Figure 1 This example proposes a method for consistent control of distributed adjustable capacity and time in a virtual power plant, including the following steps:

[0047] S1. A technology for collecting information on resource consistency control within a virtual power plant is proposed. This technology collects adjustable information and control cost information from each user within the virtual power plant, providing an information foundation for consistency control of internal distributed resources. The collected information mainly includes each user's adjustable capacity, sustainable adjustment time, user communication cost, user economic cost, user capacity reliability cost, and user time reliability cost.

[0048] The collected information on the consistency control of internal resources of the virtual power plant is shown in formula (1), which mainly includes the adjustable capacity of each user, the sustainable adjustment time, the user communication cost, the user economic cost, the user capacity reliability cost, and the user time reliability cost.

[0049]

[0050] In the formula: X i (t) represents the consistency control information of virtual power plant user i collected at time t; △P i (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let be the capacity reliability cost of user i collected at time t. Let t be the time reliability cost of collecting data from user i.

[0051] S2. Constructing a consistency index for the participation of distributed resources in the control of a virtual power plant. In virtual power plant control, different users have different adjustable capacities and sustainable control times. Controlling all users would significantly increase computational load and affect efficiency. Therefore, this invention constructs a consistency index for the participation of distributed resources in the control of a virtual power plant. This index stipulates that only users whose adjustable capacity exceeds a capacity threshold and whose sustainable control time exceeds a time threshold can participate in virtual power plant control. This index aims to reduce the control cost and improve the efficiency of virtual power plant control. The constructed consistency index includes an adjustable capacity consistency index and an adjustable time consistency index. Specifically, the adjustable capacity consistency index is defined as follows: when a user's adjustable capacity exceeds a capacity threshold, they can participate in virtual power plant control. The adjustable time consistency index is defined as follows: when a user's sustainable control time exceeds a time threshold, they can participate in virtual power plant control.

[0052] The consistency index for the participation of distributed resources in the control of a virtual power plant is constructed as shown in formulas (2)-(3), providing a consistency index for the conditions for each distributed user to participate in the virtual power plant. In the control of a virtual power plant, different users have different adjustable capacities and sustainable control times. If control is applied to all users, the computational load will be greatly increased, affecting computational efficiency. Therefore, this invention constructs a consistency index for the participation of distributed resources in the control of a virtual power plant. This index stipulates that only users whose adjustable capacity is greater than the capacity threshold and whose sustainable control time is greater than the time threshold can participate in the control of the virtual power plant. This index aims to reduce the control cost of the virtual power plant and improve its control efficiency.

[0053] Formula (2) is the consistency index of adjustable capacity of distributed resources in the virtual power plant constructed in this invention. When the adjustable capacity of a user is greater than the capacity threshold, the user can participate in the control of the virtual power plant.

[0054] Formula (3) is the adjustable time consistency index of distributed resources in the virtual power plant constructed in this invention. When the user's sustainable control time is greater than the time threshold, they can participate in the virtual power plant control.

[0055] △P i (t)≥△P min (2)

[0056] △T i (t)≥△T min (3)

[0057] In the formula: △P i (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T minThis is an adjustable time threshold.

[0058] S3. A distributed adjustable capacity consistency control method for virtual power plants based on the Particle Swarm Optimization (PSO) algorithm is proposed. During the virtual power plant control process, when users cannot all meet the adjustable capacity consistency index in step S2, the unmet distributed users can be combined to construct a combined resource that meets the adjustable capacity consistency index. This invention proposes to optimize distributed users based on the PSO algorithm to find the adjustable resource combination with the minimum communication, economic, and reliable capacity costs. First, a distributed adjustable capacity consistency control objective function for virtual power plants is constructed, with the goal of minimizing communication, economic, and reliable capacity costs during the combination process. Constraints include: user participation in adjustable capacity combination constraints, i.e., users whose adjustable capacity is less than the adjustable capacity threshold and whose adjustable time is greater than the time threshold can participate in adjustable capacity combination; and adjustable capacity combination condition constraints, i.e., the adjustable capacity of the combined users should not be lower than the adjustable capacity threshold. Then, this invention proposes a method for solving the consistency of distributed adjustable capacity in virtual power plants based on the PSO particle swarm optimization algorithm. The method optimizes the combination of users based on the PSO particle swarm optimization algorithm to find the optimal adjustable capacity combination that meets the constraints. Based on the optimal adjustable capacity combination result output by the PSO particle swarm optimization algorithm, the consistent adjustable capacity of the distributed user combination is calculated.

[0059] The constructed virtual power plant distributed adjustable capacity consistency control method based on the PSO particle swarm optimization algorithm is shown in formulas (4)-(14). During the virtual power plant control process, when users cannot all meet the adjustable capacity consistency index in step S2, the unmet distributed users can be combined to construct a combined adjustable resource that meets the consistency index. This invention proposes to optimize distributed users based on the PSO particle swarm optimization algorithm, optimizing the adjustable resource combination with the minimum communication, economic, and reliable capacity costs.

[0060] Formula (4) is the objective function for the distributed adjustable capacity consistency control of the virtual power plant constructed in this invention. During the combination process, the goal is to minimize the communication, economic, and reliable capacity costs. Its calculation process is shown in Formula (5), which is mainly calculated based on the communication, economic, and reliable capacity matrices and the capacity combination matrix.

[0061] Formula (6) is the communication cost matrix calculation model for capacity combination. The element in the i-th row and j-th column of the matrix is ​​calculated according to Formula (6).

[0062] Formula (7) is the economic cost matrix calculation model for capacity combination. The element in the i-th row and j-th column of the matrix is ​​calculated according to Formula (7).

[0063] Formula (8) is the calculation model for the reliable capacity cost matrix. The element in the i-th row and j-th column of the matrix is ​​calculated according to Formula (8).

[0064] Formula (9) is a capacity combination matrix, which is m×m in dimension, where m is the number of users participating in the adjustable capacity combination, and an element of 1 indicates that the users in the row and column corresponding to that element are combined in terms of capacity.

[0065] Formula (10) is a constraint on users participating in adjustable capacity combinations, that is, users whose adjustable capacity is less than the adjustable capacity threshold and whose adjustable time is greater than the time threshold can participate in adjustable capacity combinations.

[0066] Formula (11) is a constraint on the adjustable capacity combination, that is, the adjustable capacity of the combined user should not be lower than the adjustable capacity threshold.

[0067] Formulas (12)-(14) are methods for solving the consistency of distributed adjustable capacity of virtual power plants based on the PSO particle swarm optimization algorithm. This invention uses the PSO particle swarm optimization algorithm to perform combined optimization on each user and solve for the optimal adjustable capacity combination that meets the constraints.

[0068] Formula (12) is the input sample for the PSO particle swarm optimization algorithm, including the adjustable capacity of each user, the sustainable adjustment time, the communication cost, the economic cost, the trusted capacity cost, the trusted capacity consistency control objective function, the adjustable capacity threshold, and the time threshold.

[0069] Formula (13) is the training model of the PSO particle swarm optimization algorithm. This invention trains the input samples based on the PSO particle swarm optimization algorithm to solve for the optimal adjustable capacity combination.

[0070] Formula (14) is a consistency capacity model based on the PSO particle swarm optimization algorithm. The consistency adjustable capacity of the distributed user combination is calculated based on the optimal adjustable capacity combination result output by the PSO particle swarm optimization algorithm.

[0071] min F C (4)

[0072]

[0073] ψ C (i,j)=ψ i (t)+ψ j (t) (7)

[0074]

[0075] △P i (t)+△P j (t)≥△P min (11)

[0076]

[0077] δ' C =f PSO (X C (t)) (13)

[0078] △P i ' ,j (t)=△P i (t)+△P j (t),δ' C (i,j)=1 (14)

[0079] In the formula: F C The goal is to achieve consistent control of the distributed adjustable capacity of a virtual power plant. Let ψ be the communication cost matrix for capacity combinations. C Let λ be the economic cost matrix of capacity combinations. C For the reliable capacity cost matrix, δ C This is the capacity combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix. C (i,j) is the element in the i-th row and j-th column of the economic cost matrix, λ C (i,j) is the element in the i-th row and j-th column of the reliable capacity cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let be the capacity reliability cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the capacity reliability cost collected for user j at time t. Let m be the number of users participating in the adjustable capacity combination, and ΔP be the value of P. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min This is an adjustable time threshold. X C (t) represents the input sample of the PSO particle swarm optimization algorithm, δ' C δ' is the adjustable capacity user combination matrix output by the PSO particle swarm optimization algorithm. C (i,j) are the elements of the adjustable capacity user combination matrix output by the PSO particle swarm optimization algorithm, f PSO() A virtual power plant distributed adjustable capacity consistency solution model based on the PSO particle swarm optimization algorithm, ΔP i ' ,j (t) represents the consistent adjustable capacity calculated based on the combined output results of the PSO particle swarm optimization algorithm.

[0080] S4. A distributed adjustable time consistency control method for virtual power plants based on the LSTM algorithm is proposed. During the virtual power plant control process, when users cannot all meet the time consistency indicators in step S2, the unmet distributed users can be combined to construct a resource combination that satisfies adjustable time consistency. This invention proposes to optimize distributed users based on the LSTM algorithm to find the resource combination with the minimum communication, economic, and reliable time costs. First, a distributed adjustable time consistency control objective function for virtual power plants is constructed, with the goal of minimizing communication, economic, and reliable time costs during the combination process. Constraints include: user participation in adjustable time combination constraints, i.e., users whose adjustable capacity is greater than the adjustable capacity threshold and whose sustainable control time is less than the time threshold can participate in adjustable time combination; and adjustable time combination condition constraints, i.e., the sustainable control time of the combined users should not be less than the adjustable time threshold. Then, this invention proposes a solution method for distributed adjustable time consistency of virtual power plants based on the LSTM algorithm. The method optimizes the combination of each user based on the LSTM algorithm to find the optimal adjustable time combination that meets the constraints. Based on the optimal adjustable time combination result output by the LSTM algorithm, the consistency adjustable time of the distributed user combination is calculated.

[0081] The constructed LSTM-based distributed adjustable time consistency control method for virtual power plants is shown in formulas (15)-(25). During the virtual power plant control process, users who do not meet the adjustable time consistency index in step S2 are grouped together. This invention proposes an LSTM-based method for adjustable time optimization of distributed users, resulting in the optimal adjustable resource combination with the lowest communication, economic, and reliable time costs.

[0082] Formula (15) is the objective function for the distributed adjustable time consistency control of the virtual power plant constructed in this invention. In the combination process, the goal is to minimize communication, economic, and reliable time costs. Its calculation process is shown in Formula (16), which is mainly calculated based on the communication, economic, and reliable time matrices and the time combination matrix.

[0083] Formula (17) is the calculation model for the communication cost matrix of time combination. The element in the i-th row and j-th column of the matrix is ​​calculated according to Formula (17).

[0084] Formula (18) is the economic cost matrix calculation model for time combination. The element in the i-th row and j-th column of the matrix is ​​calculated according to formula (18).

[0085] Formula (19) is the calculation model for the credible time cost matrix. The element in the i-th row and j-th column of the matrix is ​​calculated according to formula (19).

[0086] Formula (20) is a time combination matrix, which is n×n in dimension, where n is the number of users participating in the adjustable time combination, and an element of 1 indicates that the users in the row and column corresponding to that element are combined in time.

[0087] Formula (21) is a constraint on users participating in adjustable time combinations, that is, users whose adjustable capacity is greater than the adjustable capacity threshold and whose adjustable time is less than the time threshold can participate in adjustable time combinations.

[0088] Formula (22) is the adjustable time combination condition constraint, that is, the adjustable time of the user after combination should not be lower than the adjustable time threshold.

[0089] Formulas (23)-(25) are solutions for distributed adjustable time consistency of virtual power plants based on the LSTM algorithm. This invention optimizes the combination of each user based on the LSTM algorithm to find the optimal adjustable time combination that satisfies the constraints.

[0090] Formula (23) is the input sample of the LSTM algorithm, including the adjustable capacity of each user, the sustainable adjustment time, the communication cost, the economic cost, the reliable time cost, the reliable time consistency control objective function, the adjustable capacity threshold, and the time threshold.

[0091] Formula (24) is the training model of the LSTM algorithm. This invention trains the input samples based on the LSTM algorithm and solves the optimal adjustable time combination.

[0092] Formula (25) is a consistency time model based on the LSTM algorithm. The consistency adjustable time of the distributed user combination is calculated based on the optimal adjustable time combination result output by the LSTM algorithm.

[0093] min F T (15)

[0094]

[0095] ψ T (i,j)=ψ i (t)+ψ j (t) (18)

[0096]

[0097] △T i (t)+△T j (t)≥△T min (twenty two)

[0098]

[0099] δ' T =f LSTM (X T (t)) (24)

[0100] △T i ' ,j (t)=△T i (t)+△T j (t),δ' T (i,j)=1 (25) where: F T The objective is to achieve distributed, adjustable time consistency control for virtual power plants. Let ψ be the communication cost matrix for time combination. T Let λ be the economic cost matrix for time combinations. T For the reliable time cost matrix, δ T This is a time combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix for time combination. T (i,j) represents the element in the i-th row and j-th column of the economic cost matrix of time combinations, λ T (i,j) is the element in the i-th row and j-th column of the reliable time cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t. Let t be the time-based reliable cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the time reliability cost of user j collected at time t. Let n be the number of users participating in the adjustable time combination, and ΔP be the time reliability cost. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min This is an adjustable time threshold. X T (t) represents the input sample of the LSTM algorithm, δ' T δ' is the adjustable-time user combination matrix output by the LSTM algorithm. T (i,j) are the elements of the adjustable-time user combination matrix output by the LSTM model, f LSTM () A distributed adjustable time consistency solution model for virtual power plants based on the LSTM algorithm, ΔT i ' ,j(t) represents the consistency adjustable time calculated based on the combined output results of the LSTM algorithm.

[0101] Through the above steps, consistent control of the adjustable capacity and adjustable time of each user within the virtual power plant can be achieved, creating a resource combination that meets consistency indicators at the lowest cost, thereby improving the effectiveness of virtual power plant control.

[0102] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for consistent control of distributed adjustable capacity and time in a virtual power plant, characterized in that, Includes the following steps: Step S1: Collect consistency control information of internal resources of the virtual power plant. The consistency control information includes the adjustable capacity, sustainable adjustment time, user communication cost, user economic cost, user capacity trusted cost, and user time trusted cost of each user. Step S2: Based on consistency control information, construct a consistency index for the participation of distributed resources in the virtual power plant in regulation. This consistency index stipulates that a user can participate in the regulation of the virtual power plant only when the user's adjustable capacity is greater than a preset capacity threshold and the sustainable adjustment time is greater than a preset time threshold. The consistency index includes an adjustable capacity consistency index and an adjustable time consistency index. Step S3: During the virtual power plant control process, when some users fail to meet the adjustable capacity consistency index in Step S2, a distributed adjustable capacity consistency control method based on particle swarm optimization algorithm is proposed for the virtual power plant: A distributed adjustable capacity consistency control objective function for the virtual power plant is constructed, with the goal of minimizing communication, economic, and reliable capacity costs, and constraints are set; based on the particle swarm optimization algorithm, the distributed users are combined for optimization to find the optimal adjustable capacity combination that satisfies the constraints, and the consistent adjustable capacity of the distributed user combination is calculated based on the optimal adjustable capacity combination; Step S4: In the virtual power plant control process, when some users cannot meet the adjustable time consistency index in step S2, a distributed adjustable time consistency control method for virtual power plants based on the Long Short-Term Memory (LSTM) network algorithm is proposed: A distributed adjustable time consistency control objective function for virtual power plants is constructed, aiming to minimize communication, economic, and reliable time costs, and constraints are set; Based on the LSM network algorithm, the distributed users are combined and optimized to find the optimal adjustable time combination that satisfies the constraints, and the consistency adjustable time of the distributed user combination is calculated based on the optimal adjustable time combination.

2. The method for consistent control of distributed adjustable capacity and time in a virtual power plant according to claim 1, characterized in that, In step S1, the consistency control information of the internal resources of the virtual power plant collected is shown in the following formula: In the formula: X i (t) represents the consistency control information of virtual power plant user i collected at time t; △P i (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t, and λ i C (t) represents the capacity reliability cost of user i collected at time t, and λ i T (t) represents the time reliability cost of user i collected at time t.

3. The method for consistent control of distributed adjustable capacity and time in a virtual power plant according to claim 1, characterized in that, In step S2, the consistency index for the participation of distributed resources in the control within the virtual power plant is constructed as shown in the following formula: △P i (t)≥△P min (2) △T i (t)≥△T min (3) Where: △P i (t) represents the adjustable capacity of user i collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min For adjustable time thresholds, only adjustable capacity ΔP is available. i (t) is greater than the adjustable capacity threshold ΔP min And the adjustment time △T can be sustained i (t) is greater than the adjustable time threshold ΔT min Only users with certain qualifications can participate in the virtual power plant control.

4. The method for consistent control of distributed adjustable capacity and time in a virtual power plant according to claim 1, characterized in that, In step S3, during the virtual power plant control process, when some users fail to meet the adjustable capacity consistency index in step S2, a distributed adjustable capacity consistency control method for virtual power plants based on particle swarm optimization algorithm is proposed; this method is expressed by the following formula: my F C (4) △P i (t)+△P j (t)≥△P min (11) δ' C =f PSO (X C (t)) (13) △P i ' ,j (t)=△P i (t)+△P j (t),δ' C (i,j)=1 (14) where: F C The objective is to achieve consistent control of the distributed adjustable capacity of a virtual power plant. Let ψ be the communication cost matrix for capacity combinations. C Let λ be the economic cost matrix of capacity combinations. C For the reliable capacity cost matrix, δ C It is a capacity combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix. C (i,j) is the element in the i-th row and j-th column of the economic cost matrix, λ C (i,j) is the element in the i-th row and j-th column of the reliable capacity cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t, and λ i C (t) represents the capacity reliability cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the capacity reliability cost of user j collected at time t, m be the number of users participating in the adjustable capacity combination, and ΔP be the value of P. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min Adjustable time threshold; X C (t) represents the input sample for the particle swarm optimization algorithm, δ' C δ' is the adjustable capacity user combination matrix output by the particle swarm optimization algorithm. C (i,j) are the elements of the adjustable capacity user combination matrix output by the particle swarm optimization algorithm, f PSO () represents the distributed adjustable capacity consistency solution model for a virtual power plant based on the particle swarm optimization algorithm, where △P i ' ,j (t) represents the consistent adjustable capacity calculated based on the combined output results of the particle swarm optimization algorithm.

5. The method for consistent control of distributed adjustable capacity and time in a virtual power plant according to claim 1, characterized in that, In step S3, during the virtual power plant control process, when a user fails to meet the adjustable time consistency index in step S2, a distributed adjustable time consistency control method for virtual power plants based on LSTM is proposed. This method is expressed by the following formula: my F T (15) ψ T (i,j)=ψ i (t)+ψ j (t) (18) △T i (t)+△T j (t)≥△T min (22) δ' T =f LSTM (X T (t)) (24) △T i ' ,j (t)=△T i (t)+△T j (t),δ' T (i,j)=1 (25) where: F T The objective is to achieve distributed, adjustable time consistency control for virtual power plants. Let ψ be the communication cost matrix for time combination. T Let λ be the economic cost matrix for time combinations. T For the reliable time cost matrix, δ T This is a time combination matrix. Let ψ be the element in the i-th row and j-th column of the communication cost matrix for time combination. T (i,j) represents the element in the i-th row and j-th column of the economic cost matrix of time combinations, λ T (i,j) is the element in the i-th row and j-th column of the reliable time cost matrix. Let ψ be the communication cost of user i collected at time t. i (t) represents the economic cost of user i collected at time t, and λ i T (t) represents the time-based reliable cost of user i collected at time t. Let ψ be the communication cost of user j collected at time t. j (t) represents the economic cost of user j collected at time t. Let P be the time reliability cost of user j collected at time t, n be the number of users participating in the adjustable time combination, and ΔP. i (t) represents the adjustable capacity of user i collected at time t, ΔP j (t) represents the adjustable capacity of user j collected at time t, ΔT i (t) represents the sustainable adjustment time of user i collected at time t, ΔP min For adjustable capacity threshold, △T min For an adjustable time threshold, X T (t) represents the input sample for the Long Short-Term Memory (LSTM) network algorithm, δ' T δ' is the adjustable-time user combination matrix output by the Long Short-Term Memory (LSTM) network algorithm. T (i,j) are the elements of the adjustable-time user combination matrix output by the Long Short-Term Memory (LSTM) network algorithm, f LSTM () represents the distributed adjustable time consistency solution model for a virtual power plant based on the Long Short-Term Memory (LSTM) network algorithm, where ΔT i ' ,j (t) is the consistency adjustable time calculated based on the LSTM output combination result.

Images