Multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithm and related equipment
By constructing a multi-regional virtual power plant coordinated optimization scheduling model and using an improved whale optimization algorithm, the problem of coordinated optimization scheduling of multi-regional virtual power plants was solved, achieving efficient scheduling and cost optimization, and improving the stability of the power system and the renewable energy consumption rate.
Patent Information
- Application Number
- CN202511423725.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-30
- Publication Date
- 2026-02-17
AI Technical Summary
Coordinated and optimized scheduling of multi-regional virtual power plants faces challenges such as the difficulty in accurately predicting the randomness and volatility of distributed renewable energy sources, scheduling difficulties caused by differences in energy structures in different regions, and the high computational complexity of traditional algorithms, which are difficult to meet practical needs.
A multi-regional virtual power plant coordinated optimization scheduling method based on optimization algorithms is adopted. By constructing a multi-regional virtual power plant coordinated optimization scheduling model, and introducing an improved whale optimization algorithm with adaptive inertia weight and differential mutation operation for solution, the method optimizes the costs of power generation, power purchase, energy storage and curtailment, sets power balance and equipment output constraints, and achieves efficient scheduling.
It enables efficient coordinated and optimized scheduling of virtual power plants in multiple regions, reduces operating costs, increases the absorption rate of new energy sources, and enhances the stability and economy of the power system.
Smart Images
Figure CN121546708A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] Embodiments of the present application relate to the field of power system dispatching, and in particular to a multi-region virtual power plant coordinated optimization dispatching method based on an optimization algorithm and related equipment. BACKGROUND
[0002] With the growing global demand for clean energy and the promotion of the "double carbon" target, the proportion of distributed new energy in the power system is increasing. As an effective means of integrating distributed energy resources, virtual power plants can achieve coordinated optimization dispatching of distributed power sources, energy storage systems and loads, and improve energy utilization efficiency and economic benefits. However, the coordinated optimization dispatching of multi-region virtual power plants faces many challenges. On the one hand, distributed new energy in virtual power plants has randomness and volatility, such as wind power affected by wind speed and photovoltaic power affected by light intensity, which makes it difficult to accurately predict power output and brings difficulties to the formulation of dispatching plans. On the other hand, virtual power plants in different regions differ in energy structure, load characteristics and other aspects, and how to coordinate energy distribution between regions to achieve overall optimal dispatching is a key problem. At present, in the related technology applied to virtual power plant dispatching, some technologies use traditional mathematical programming methods such as linear programming and mixed integer programming. These methods have high computational complexity and long solution time when dealing with large-scale and complex dispatching models. Some technologies apply intelligent algorithms such as particle swarm optimization and genetic algorithms, which have the advantages of fast convergence speed. However, traditional intelligent algorithms have problems such as being prone to local optimization and insufficient global search capability when dealing with complex problems such as multi-region virtual power plant dispatching, making it difficult to meet actual dispatching needs. Therefore, there is an urgent need for a more effective method to solve the multi-region virtual power plant optimization dispatching problem. SUMMARY
[0003] In view of the deficiencies in the current multi-region virtual power plant dispatching technology, the purpose of the present application is to provide a multi-region virtual power plant coordinated optimization dispatching method based on an optimization algorithm and related equipment.
[0004] In one aspect, embodiments of the present application include a multi-region virtual power plant coordinated optimization dispatching method based on an optimization algorithm, which includes the following steps: A multi-region virtual power plant coordinated optimization dispatching model is established for a multi-region virtual power plant; the multi-region virtual power plant is distributed in multiple regions; An improved whale optimization algorithm is obtained by introducing an adaptive inertia weight and a differential mutation operation; The improved whale optimization algorithm is used to solve the multi-region virtual power plant coordinated optimization dispatching model; The virtual power plant is dispatched according to the solution result.
[0005] Further, the multi-region virtual power plant coordination optimization scheduling model for the multi-region virtual power plant comprises: determining a target function according to an operation cost of the multi-region virtual power plant; setting a constraint condition for the target function.
[0006] Further, the determining a target function according to an operation cost of the multi-region virtual power plant comprises: determining a generation cost according to a formula
[0007] determining a generation cost according to a formula is a generation power of the multi-region virtual power plant in the i-th region in the t-th time period, r is a set of generation devices in the i-th region, is a generation power of the i-th generation device of the multi-region virtual power plant in the i-th region in the t-th time period, t is a generation power of the i-th generation device of the multi-region virtual power plant in the i-th region in the t-th time period, r , i , , is a generation device cost coefficient; determining a generation cost according to a formula
[0008] determining a purchase cost according to a formula is a purchase power of the multi-region virtual power plant in the i-th region in the t-th time period, t is a purchase power of the multi-region virtual power plant in the i-th region in the t-th time period, r is a price of the i-th region in the t-th time period; determining a purchase cost according to a formula r t
[0009] determining an energy abandonment penalty cost according to a formula is a charge-discharge power of a storage device of the multi-region virtual power plant in the i-th region in the t-th time period, t is a storage power of the storage device of the multi-region virtual power plant in the i-th region in the t-th time period, r is a storage power of the storage device of the multi-region virtual power plant in the i-th region in the t-th time period, is a storage power of the storage device of the multi-region virtual power plant in the i-th region in the t-th time period, t is a storage power of the storage device of the multi-region virtual power plant in the i-th region in the t-th time period, r is a storage power of the storage device of the multi-region virtual power plant in the i-th region in the t-th time period, α is a storage cost coefficient; β determining an energy abandonment penalty cost according to a formula
[0010] determining an energy abandonment penalty cost according to a formula is a charge-discharge power of a storage device of the multi-region virtual power plant in the i-th region in the t-th time period, t is a charge-discharge power of a storage device of the multi-region virtual power plant in the i-th region in the t-th time period, r the abandoned energy power in the region, gamma is the abandoned energy penalty coefficient; According to the formula
[0011] determining the objective function.
[0012] Further, the constraint condition is set to the objective function, including: According to the formula +
[0013] Setting a power balance constraint; wherein, is the load power in the region t in the time period r region; According to the formula
[0014] Setting a power generation equipment output constraint; wherein, is the minimum power generation power of the nth power generation equipment in the region r in the region; i is the maximum power generation power of the nth power generation equipment in the region in the region; r i According to the formula
[0015]
[0016]
[0017]
[0018] Setting a storage system constraint; wherein, is the maximum charging and discharging power of the storage, is the minimum power of the storage, is the maximum power of the storage, is the charging efficiency of the storage, is the discharging efficiency of the storage, is the length of the scheduling period; According to the formula
[0019] Setting an inter-regional power transmission constraint; wherein, is the power transmitted from the region t to the region in the time period, This represents the maximum permissible transmission power between regions.
[0020] Furthermore, the step of solving the multi-region virtual power plant coordinated optimization scheduling model using the improved whale optimization algorithm includes: Establish multiple individual whales to obtain a whale population; The whale population is initialized; The process involves multiple iterations until a termination condition is met, at which point the solution result of the final iteration is output. The termination condition includes the number of iterations already performed reaching the maximum number of iterations. K Alternatively, the global optimal solution obtained by continuously executing the iterative process multiple times converges; any round of the iterative process includes the following steps: The location information of each individual whale is substituted into the objective function for calculation to obtain the fitness value corresponding to each individual whale. Calculate the adaptive inertia weights corresponding to the individual whales; According to the formula
[0021] Update the speed of each individual whale; where, In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The speed before the dimension update. In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The speed of dimension updates In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The position before the dimension update. For the first i The historical best position of the aforementioned individual whale. This represents the globally optimal position for all the aforementioned individual whales. , As a learning factor, , A random number between [0,1] For the first i The adaptive inertia weights corresponding to each individual whale; According to the formula
[0022] Update the position of each of the aforementioned individual whales; wherein, In the firstk In the iteration process described in the round, the first i The aforementioned individual whales d The updated position of the dimension; Boundary processing is performed on the whale individuals whose positions exceed the range of values for the decision variables after the position is updated; If the mutation triggering condition is met, perform the differential mutation operation; otherwise, terminate the iteration process described in this round.
[0023] Further, the calculation of the adaptive inertia weight corresponding to the individual whale includes: According to the formula
[0024] Calculate the adaptive inertia weights; wherein, The inertial weight, The maximum value of the inertia weight. This is the minimum value of the inertia weight. To calculate the fitness value of the individual whale for which the adaptive inertia weights need to be calculated, This represents the maximum fitness level of the current whale population. This represents the minimum fitness level of the current whale population.
[0025] Further, the execution of the differential mutation operation includes: According to the formula
[0026] New individuals are generated; among them, The location of the whale individual obtained after the differential mutation operation. For the best individual in the current population Dimension value, and For two different individuals randomly selected from the population, Dimension value, It is the difference variation factor; According to the formula
[0027]
[0028]
[0029]
[0030] Update the location of individual whales; among which, For the first The updated location of each individual whale. is the position of the i-th whale individual before updating, is a control parameter linearly decreasing from 2 to 0, is a random number between [0, 1], is the j-th component of a randomly selected whale individual, is the i-th component of the i-th whale individual, denotes the adaptive inertia weight of the i-th whale individual in the current iteration round, obtains the optimal position in the updated positions of all whale individuals in the population; according to the formula updates the velocity of the whale individual; wherein, is the updated velocity of the i-th whale individual, is the velocity of the i-th whale individual before updating, is the j-th component of the historical optimal position of the i-th whale individual,
[0031] is the j-th component of the optimal position in the population, is a learning factor, is a random number between [0, 1]. Further, the initialization of the whale population comprises: determining the size of the whale population , the dimension of the whale individual , and the maximum number of iterations ; setting the value range of each decision variable , wherein =1, 2, …, ; for the i-th whale individual, within the value range of the decision variable, the initial position and the initial velocity
[0032] of the whale individual are randomly generated by the formula N D K d D i
[0033]
[0034] is the i-th whale individual,i the initial position of the decision variable of the i-th whale individual in the j-th iteration, the initial position of the decision variable of the i-th whale individual in the j-th iteration, the initial position of the decision variable of the i-th whale individual in the j-th iteration, i the initial position of the decision variable of the i-th whale individual in the j-th iteration, the initial position of the decision variable of the i-th whale individual in the j-th iteration, to generate a random number between 0 and 1, and the velocity boundary.
[0035] In another aspect, embodiments of the present application further include a computer device comprising a memory and a processor, the memory being configured to store at least one program, and the processor being configured to load the at least one program to execute the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm in the embodiments.
[0036] In another aspect, embodiments of the present application further include a computer program product comprising a computer program, which, when executed by a processor, implements the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm in the embodiments.
[0037] The beneficial effects of embodiments of the present application are that the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm in the embodiments, by constructing a multi-region virtual power plant coordinated optimization scheduling model considering the characteristics of multi-region and new energy, and combining the improved whale optimization algorithm for solving, realizes efficient coordinated optimization scheduling of multi-region virtual power plants, reduces operation cost, improves new energy consumption rate, enhances the adaptability of scheduling strategy to different regions and new energy fluctuations, thereby enhancing the stability and economy of the power system. BRIEF DESCRIPTION OF DRAWINGS
[0038] Figure 1 is a schematic diagram of a virtual power plant system to which the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm in the embodiments can be applied; Figure 2 is a schematic diagram of the steps of the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm in the embodiments. DETAILED DESCRIPTION
[0039] In the present embodiment, in view of the problem that the existing scheduling model does not fully consider the coordination of multiple types of energy storage, a virtual power plant system model containing multiple energy storage technologies is constructed, and for the scheduling problem of such a virtual power plant system model, a multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm is provided, which can be applied to the virtual power plant system shown in Figure 1 Figure 1 The virtual power plant system includes multiple distributed power sources such as distributed power source 1, distributed power source 2, etc., multiple energy storage devices such as energy storage device 1, energy storage device 2, etc., and multiple controllable loads such as controllable load 1, controllable load 2, etc. Controllable loads include electrical equipment, etc.
[0040] Reference Figure 1 The virtual power plant system is distributed across multiple regions, such as region 1, region 2, ... region r. Each region can contain its own distributed power sources, energy storage devices, and controllable loads.
[0041] Reference Figure 2 The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms includes the following steps: S1. Establish a multi-regional virtual power plant coordination and optimization scheduling model for multi-regional virtual power plants; S2. An improved whale optimization algorithm is obtained by introducing adaptive inertia weights and differential mutation operations; S3. Solve the multi-region virtual power plant coordinated optimization scheduling model using the improved whale optimization algorithm; S4. Schedule the virtual power plant based on the solution results.
[0042] In this embodiment, steps S1-S4 can be executed by a computer.
[0043] Step S1 involves modeling distributed power sources (such as photovoltaic power generation equipment and wind power generation equipment), various types of energy storage equipment (battery energy storage, flywheel energy storage, pumped hydro storage, etc.), and controllable loads within the multi-region virtual power plant. When performing step S1, which is the step of establishing a coordinated optimization scheduling model for the multi-region virtual power plant, the following steps can be executed: S101. Determine the objective function based on the operating costs of the multi-regional virtual power plant; S102. Set constraints for the objective function.
[0044] In step S101, considering operating costs such as power generation cost, power purchase cost, energy storage cost, and energy curtailment penalty cost, the overall operating cost of the multi-regional virtual power plant is calculated, and the objective function is determined with the goal of minimizing the operating cost of the multi-regional virtual power plant. Specifically, the formula for calculating the operating cost of the multi-regional virtual power plant, i.e., the objective function, is as follows: (1) in, This represents the number of regions where the multi-region virtual power plant is located. Number of scheduling periods for r area t Time-of-use electricity generation cost forr area t Electricity purchase cost during specific time periods for r area t Time-of-use energy storage costs for r area t Time-based energy curtailment penalty costs. In this embodiment, the operating costs of a multi-regional virtual power plant consist of generation costs, electricity purchase costs, energy storage costs, and energy curtailment penalty costs. Specifically: The formula for calculating the cost of electricity generation is: (2) in, for r Regional power generation equipment collection, for r area t Time period i Equipment power generation capacity, , , This represents the cost coefficient for power generation equipment. In this embodiment, , , All are constants.
[0045] The formula for calculating electricity purchase cost is: (3) in, for r area t Power purchased during specific time periods for r area t Electricity pricing for specific time periods.
[0046] The formula for calculating energy storage costs is: (4) in, for r area t Time-of-use energy storage charging and discharging power, for r area t Energy storage capacity during specific time periods α , β This represents the energy storage cost coefficient. In this embodiment, α , β It is a constant.
[0047] The formula for calculating the cost of energy curtailment penalty is: (5) in, for r areat The amount of energy wasted during a given period gamma This represents the energy curtailment penalty coefficient. In this embodiment, gamma It is a constant.
[0048] In step S102, constraints are set for the objective function, including power balance constraints, power generation equipment output constraints, energy storage system constraints, and inter-regional power transmission constraints. Specifically: (1) Power balance constraint: This constraint ensures the power balance between power generation, power purchase, energy storage charging and discharging and load demand in each region at each time period.
[0049] + (6) in, for r area t Load power during a given time period.
[0050] (2) Output constraints of power generation equipment: Limit the power generation of power generation equipment to within its allowable minimum and maximum power range.
[0051] (7) in, , They are respectively r area i The minimum and maximum power output of the power generation equipment.
[0052] (3) Constraints of energy storage system: including limits on energy storage charging and discharging power, limits on upper and lower limits of energy storage capacity, and constraints on energy storage charging and discharging efficiency.
[0053] (8) (9) (10) (11) in, For maximum charge and discharge power of energy storage, , These represent the minimum and maximum energy storage capacities, respectively. , These refer to energy storage charging and discharging efficiency, respectively. This refers to the duration of the scheduling period.
[0054] (4) Inter-regional power transmission constraints: Limit the maximum value of inter-regional power transmission to ensure the safe and stable operation of the power grid.
[0055] (12) in, for t Time period Regional Power of regional transmission, This represents the maximum permissible transmission power between regions.
[0056] In step S3, an improved whale optimization algorithm is established. In this embodiment, the improved whale optimization algorithm introduces adaptive inertia weights and differential mutation operations, thereby achieving superior performance compared to the conventional whale optimization algorithm. Specifically, the content of the improved whale optimization algorithm will be reflected during execution in step S4.
[0057] In this implementation, when performing step S4, which is to solve the multi-region virtual power plant coordinated optimization scheduling model using the improved whale optimization algorithm, the following steps can be performed: S401. Establish multiple individual whales to obtain a whale population; S402. Initialize the whale population; S403. Execute multiple iterations until the termination condition is met, then output the solution result of the last iteration. The termination condition includes reaching the maximum number of iterations. K Alternatively, the globally optimal solution obtained by performing multiple iterations converges. Any round of iteration includes the following steps: S40301. For the location information of each individual whale, substitute it into the objective function to calculate and obtain the fitness value corresponding to each individual whale; S40302. Calculate the adaptive inertia weights corresponding to individual whales; S40303. According to the formula (13) Update the speed of each individual whale; among them, In the first k The first round of iteration i Individual whales d The speed before the dimension update. In the first k The first round of iteration i Individual whales d The speed of dimension updates In the first k The first round of iteration i Individual whales d The position before the dimension update. For the first i The historical best position of an individual whale. This represents the globally optimal position for all individual whales. , As a learning factor, , A random number between [0,1] For the first i The adaptive inertia weights corresponding to each individual whale; S40304. According to the formula (14) Update the location of each individual whale; among them, In the first k The first round of iteration i Individual whales d The updated position of the dimension; S40305. Perform boundary processing on whale individuals whose positions exceed the range of values for the decision variables after the position update; S40306. When the mutation triggering condition is met, perform the differential mutation operation; otherwise, terminate the iteration process described in this round.
[0058] In step S401, the size of the whale population (how many individual whales it contains), the individual dimensions, and the maximum number of iterations are determined. K Parameters such as these.
[0059] By executing step S401, a whale population is formed from multiple individual whales. Each individual whale has a corresponding position vector representing its location. This position vector includes multiple components (the number of components equals the individual dimension). Each component represents a decision variable in the multi-regional virtual power plant coordinated optimization scheduling model, such as the power generation and purchase power in each region and time period, which are variables related to the scheduling of the multi-regional virtual power plant. Therefore, the individual dimension represents the number of decision variables in the multi-regional virtual power plant coordinated optimization scheduling model contained in the position vector of an individual whale.
[0060] Since the position vector of each individual whale corresponds to a set of decision variables such as power generation, power purchase, and energy storage charging and discharging power in each region and time period, the position vector of each individual whale corresponds to a set of scheduling schemes. For example, the coordinated optimization scheduling model of controlling the virtual power plants in multiple regions can achieve the corresponding specific values for power generation, power purchase, and energy storage charging and discharging power in each time period and region.
[0061] Before using the improved whale optimization algorithm to solve the multi-region virtual power plant coordinated optimization scheduling model, step S402 can be performed to initialize the whale population. The specific steps are as follows: (1) Determine parameters: Determine the size of the whale population. N The value is typically chosen based on the complexity of the problem and available computing resources, generally ranging from 20 to 100; determining the individual dimension.D Individual dimensions correspond to decision variables in the scheduling model (equal to the number of variables to be optimized in the scheduling model), such as power generation, power purchase, and energy storage charging and discharging power in different regions and time periods; determine the maximum number of iterations. K This is used to control the termination condition of the algorithm.
[0062] The range of values for each decision variable ,in d =1,2,⋯, D。
[0063] (2) Randomly generate initial position and velocity: for each whale particle i ( i =1,2,⋯, N The initial position of the decision variable is randomly generated within the range of values. ( d =1,2,⋯, D ) and initial velocity The range of initial velocity values is usually set based on the range of decision variables and experience. For example, the range of initial velocity values can be set as a certain proportion of the range of decision variables.
[0064] (15) (16) in, Let be the initial position of the i-th individual whale in the d-th dimension of the decision variable. Let be the initial velocity of the i-th individual whale in the d-th dimension of the decision variable. To generate random numbers between 0 and 1, and The velocity boundary is usually set as a certain proportion of the position boundary.
[0065] In step S403, multiple rounds of iterative processes consisting of steps S40301-S40306 are executed. After each round of iterative processes, it is determined whether the termination condition is met. In this embodiment, the termination condition includes the number of rounds of the executed iterative process reaching the maximum number of iterations. K or execute continuously n The global optimal solution obtained in each iteration converges (e.g., the difference between each pair of global optimal solutions obtained in each iteration is less than a threshold). If the termination condition is met after one round of iteration, then the next round of iteration will not be executed, and the solution result of the last round of iteration will be output as the solution result of the multi-region virtual power plant coordinated optimization scheduling model; otherwise, steps S40301-S40306 corresponding to the next round of iteration will be executed.
[0066] In this embodiment, one round (the first) The iterative process of (round) will be used as an example for explanation.
[0067] In step S40301, since the location information of each individual whale determines the values of decision variables such as power generation, power purchase, and energy storage charging and discharging power in each region and time period, for any individual whale, its location information can be substituted into the objective function shown in formula (1) under the constraints of the multi-region virtual power plant coordinated optimization scheduling model to calculate the corresponding value. This serves as the fitness value for this individual whale.
[0068] The fitness value reflects the quality of the scheduling scheme represented by the individual whale. The goal of this invention is to minimize the overall operating cost of multi-region virtual power plants. Therefore, the smaller the fitness value, the better the scheduling scheme represented by the individual whale.
[0069] Next, step S40302 is executed to calculate the adaptive inertia weights corresponding to individual whales.
[0070] In the traditional whale optimization algorithm, the fixed weight factor makes it difficult to achieve a good balance between global and local search during the optimization process. When the weight factor is large, the individual whale has a strong global search ability, but may skip the optimal solution; when the weight factor is small, the individual whale's local search ability is enhanced, but it is prone to getting trapped in local optima.
[0071] To address this issue, this embodiment employs an adaptive inertia weight strategy during step S40302. The adaptive inertia weight dynamically adjusts based on the particle's fitness value, enabling the algorithm to possess strong global search capabilities in the initial search phase and gradually enhance its local search capabilities as iterations progress.
[0072] Specifically, for any individual whale, the formula for calculating the adaptive inertia weight is: (17) in, For adaptive inertia weights, , These are the maximum and minimum values of the inertia weight, respectively. This represents the current fitness value of an individual whale. , These represent the maximum and minimum fitness values in the current whale population, respectively. In this embodiment, since the fitness value of each individual whale generally increases with the execution rounds of the iteration process... k The adaptive inertia weights will also change as the number changes. kThe adaptive inertia weights change with the changes in the system, and therefore can also be calculated using formula (17). Recorded as .
[0073] In step S40303, according to the formula (18) Update the speed of each individual whale; among them, In the first k The first round of iteration i Individual whales d The speed before the dimension update. In the first k The first round of iteration i Individual whales d The speed of dimension updates In the first k The first round of iteration i Individual whales d The position before the dimension update. For the first i The historical best position of an individual whale. This represents the globally optimal position for all individual whales. , The learning factor is typically set to 2. , A random number between [0,1] For the first i The adaptive inertia weights corresponding to each individual whale.
[0074] In step S40304, according to the formula (19) Update the location of each individual whale; among them, In the first k The first round of iteration i Individual whales d The updated position of the dimension.
[0075] In step S40305, if the updated position of a whale exceeds the range of the decision variable, boundary processing is performed to bring it back into the feasible region. For example, the following method can be used: when the position of a whale is less than the minimum value of the decision variable, it is set to the minimum value; when the position of a whale is greater than the maximum value of the decision variable, it is set to the maximum value.
[0076] In the later iterations of the whale optimization algorithm, individual whales often cluster near local optima, causing the algorithm to get trapped in local optima. Therefore, in the... kDuring the iteration process, after executing steps S40301-S40305, it is determined whether the mutation triggering condition is met. Specifically, the computer can detect whether each individual whale has met the mutation triggering condition in the previous iteration. k-m+ Round 1 to Round 2 k This round of continuous m The fitness value obtained in each iteration of the rounds, if there are whale individuals whose fitness values in previous iterations have not improved (e.g., consecutive iterations), m If the fitness value obtained in the round of iteration does not continuously decrease (e.g., multiple fitness values do not decrease monotonically, or the decrease is less than the threshold), then the mutation triggering condition is satisfied; otherwise, the mutation triggering condition is not satisfied.
[0077] In the k During each iteration, if the mutation triggering condition is not met, the differential mutation operation is not performed in this iteration, and the iteration process ends. If the mutation triggering condition is met, step S40306 is executed, i.e., the differential mutation operation is performed.
[0078] In this embodiment, by performing a differential mutation operation, a new whale individual can be generated, and its position can be perturbed. Specifically, the differential mutation operation includes the following steps: S4030601. According to the formula
[0079] New individuals are generated; among them, This represents the location of the whale individual obtained after differential mutation. For the best individual in the current population Dimension value, and For two different individuals randomly selected from the population, Dimension value, It is the difference variation factor; S4030602. According to the formula
[0080]
[0081]
[0082]
[0083] Update the location of individual whales; among which, For the first The updated location of each individual whale. For the first The position of each individual whale before the update. The control parameter decreases linearly from 2 to 0. and A random number between [0,1]. For a randomly selected individual whale, the first dimensional components, Indicates the first The number of individual whales in the current [number] [number] [year] Adaptive inertia weights in the second iteration of the round; S4030603. Obtain the optimal position among the updated positions of all individual whales in the population; S4030604. According to the formula
[0084] Update the speed of individual whales; among them, For the first The updated speed of each individual whale. For the first The rate of change for each individual whale before the update. For the first The historical best position of the [number] individual whales dimensional components, The optimal position in the population is the first dimensional components, and As a learning factor, and It is a random number between [0,1].
[0085] Differential mutation has strong global search capabilities and the ability to escape local optima. The specific operation is as follows: In each iteration, for whale individuals whose fitness values have not improved consecutively, step S4030601 is executed to generate new individuals using differential mutation. The formula for generating new individuals using differential mutation is: (14) in, This represents the value of the best individual in the current population in dimension d. and Let F be the value of two different individuals randomly selected from the population in dimension d, and let F be the difference variation factor used to control the magnitude of the variation.
[0086] In step S4030602, the following position update mechanism is applied: combining adaptive weights and differential mutation, the position of the individual whale is updated, and the position update formula is: (15) (16) (17) (18) Where 'a' is a control parameter that decreases linearly from 2 to 0. and A random number between [0,1]. Let d be the d-th dimension component of a randomly selected individual whale.
[0087] According to the following formula: (19) The rate at which individual whales are updated; among which, For the first The historical best position of the [number] individual whales dimensional components, The position of the global optimum dimensional components, and The learning factor (usually 2.0) and It is a random number between [0,1].
[0088] In the k During the iteration process, if step S40306 is selected to be executed, after step S40306 is completed, that is, after the first iteration is completed... k In each iteration, it can be determined whether the termination condition is met, and thus whether to execute the next iteration.
[0089] In this embodiment, it is assumed that the first k If this is the last iteration, then we obtain the results from round 1 to round 2. k The globally optimal position among all the position vectors of individual whales updated in each iteration process is the position vector that minimizes the objective function represented by formula (1) among all the position vectors updated after each iteration process. Finally, the globally optimal position is output as the solution result of the multi-region virtual power plant coordinated optimization scheduling model.
[0090] After performing step S3, the obtained global optimal location corresponds to the specific values of decision variables such as power generation, power purchase, and energy storage charging / discharging power for each region and time period. These specific values of decision variables minimize the operating cost of the multi-region virtual power plant. Therefore, the solution obtained in step S3 corresponds to a set of optimal scheduling schemes. When performing step S4, the multi-region virtual power plant can be scheduled based on this global optimal location. For example, the distributed power sources, energy storage devices, and controllable loads in each region of the multi-region virtual power plant can be adjusted to the corresponding power generation, power purchase, and energy storage charging / discharging power for the corresponding time periods.
[0091] In this embodiment, by executing a multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms, including steps S1-S4, the following effects can be achieved: (1) Model comprehensiveness and cost optimization: The multi-regional virtual power plant coordinated optimization scheduling model comprehensively considers various cost factors such as power generation, power purchase, energy storage, and energy curtailment, as well as constraints such as power balance, equipment output, energy storage system and inter-regional power transmission. It can more accurately reflect the actual scheduling situation and effectively reduce the overall operating cost of the virtual power plant. (2) Algorithm effectiveness and optimization ability: The improved whale optimization algorithm enhances the global search ability of the algorithm by introducing adaptive weight factors and differential mutation operations, avoids getting trapped in local optima, improves the solution accuracy and convergence speed, and can quickly find the optimal solution of the multi-region virtual power plant scheduling model. (3) System adaptability and stability: The multi-region virtual power plant coordination optimization scheduling method based on optimization algorithm fully considers the characteristics of multi-region virtual power plants and the randomness and volatility of new energy. The optimized scheduling scheme can better adapt to the changes in energy structure and load demand in different regions, improve the new energy absorption rate, and enhance the stability and reliability of the power system.
[0092] In summary, the multi-regional virtual power plant coordinated optimization scheduling method based on optimization algorithms in this embodiment constructs a multi-regional virtual power plant coordinated optimization scheduling model that considers the characteristics of multiple regions and new energy sources. This model is then solved using an improved whale optimization algorithm, achieving efficient coordinated optimization scheduling of multi-regional virtual power plants. This reduces operating costs, increases the absorption rate of new energy sources, and enhances the adaptability of scheduling strategies to fluctuations in different regions and new energy sources, thereby improving the stability and economy of the power system.
[0093] In this embodiment, a computer device can be used, including a memory and a processor. The memory is used to store at least one program, and the processor is used to load at least one program to execute a multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm, thereby obtaining the effect of the multi-region virtual power plant coordinated optimization scheduling method based on an optimization algorithm.
[0094] In this embodiment, a computer program product, including a computer program, can be used. When the computer program is executed by a processor, it implements the multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms in this embodiment.
[0095] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. Furthermore, the descriptions of "upper," "lower," "left," and "right" used in this disclosure are only relative to the relative positional relationships of the components of this disclosure in the accompanying drawings. The singular forms "a" and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. Moreover, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this embodiment specification is only for describing specific embodiments and is not intended to limit the embodiments of the invention. The term "and / or" as used in this embodiment includes any combination of one or more of the associated listed items.
[0096] It should be understood that although the terms first, second, third, etc., may be used to describe various elements in this disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element without departing from the scope of this disclosure, and similarly, a second element may also be referred to as a first element. The use of any and all instances or exemplary language (“e.g.,” “such as,” etc.) provided in this embodiment is intended only to better illustrate embodiments of the invention and, unless otherwise required, does not impose a limitation on the scope of embodiments of the invention.
[0097] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).
[0098] Furthermore, the procedures described in this embodiment can be performed in any suitable order unless otherwise indicated by this embodiment or otherwise obviously contradict the context. The procedures (or variations and / or combinations thereof) described in this embodiment can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. A computer program includes a plurality of instructions executable by one or more processors.
[0099] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices, etc. Aspects of embodiments of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention of this embodiment includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps above in conjunction with a microprocessor or other data processor. Embodiments of the invention also include the computer itself when programmed according to the methods and techniques of embodiments of the invention.
[0100] A computer program can be applied to input data to perform the functions of this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including a specific visual depiction of physical and tangible objects generated on the display.
[0101] The above are merely preferred embodiments of the present invention. The embodiments of the present invention are not limited to the above-described implementations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the embodiments of the present invention, as long as they achieve the same technical effects, should be included within the scope of protection of the embodiments of the present invention. Within the scope of protection of the embodiments of the present invention, the technical solutions and / or implementation methods can have various modifications and variations.
Claims
1. A multi-regional virtual power plant coordinated optimization scheduling method based on optimization algorithms, characterized in that, The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms includes: A multi-regional virtual power plant coordination and optimization scheduling model is established for the multi-regional virtual power plants, which are distributed across multiple regions. An improved whale optimization algorithm is obtained by introducing adaptive inertia weights and differential mutation operations; The improved whale optimization algorithm is used to solve the multi-region virtual power plant coordinated optimization scheduling model; The virtual power plant is scheduled based on the solution results.
2. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 1, characterized in that, The establishment of a multi-regional virtual power plant coordinated optimization scheduling model includes: The objective function is determined based on the operating costs of the multi-regional virtual power plants; Set constraints on the objective function.
3. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 2, characterized in that, The step of determining the objective function based on the operating costs of the multi-regional virtual power plants includes: According to the formula Determine the cost of electricity generation; among which, For the multi-region virtual power plant in r A collection of power generation equipment in the region. In order to be in t During the time period, the virtual power plants in the multiple regions mentioned above r The first in the region i The power generation capacity of each power generation device , , This is the cost coefficient for power generation equipment; According to the formula Determine the cost of electricity purchase; among which, For the multi-region virtual power plant in t Within the time period r Electricity purchase capacity in the region for r The area is t Electricity price during the specified time period; According to the formula Determine the cost of energy storage; among which, In order to be in t During the time period, the virtual power plants in the multiple regions mentioned above r The charging and discharging power of energy storage devices in the region, In order to be in t During the time period, the virtual power plants in the multiple regions mentioned above r The energy storage capacity of the energy storage devices in the region, α , β This is the energy storage cost coefficient; According to the formula Determine the cost of energy curtailment penalties; among which, In order to be in t During the period r The amount of abandoned energy in the region, γ This is the energy curtailment penalty coefficient; According to the formula Determine the objective function.
4. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 3, characterized in that, The constraint conditions set for the objective function include: According to the formula + Set power balance constraints; where, In order to be in t During the period r Load power in the area; According to the formula Set output constraints for power generation equipment; among which, In order to be in r The first in the region i Minimum power output of each power generation device In order to be in r The first in the region i The maximum power output of each power generation device; According to the formula Set constraints for the energy storage system; among which, For maximum charge and discharge power of energy storage, To store the minimum amount of energy, To store the maximum amount of energy, For energy storage charging efficiency, For energy storage and discharge efficiency, The duration of the scheduling period; According to the formula Set inter-regional power transfer constraints; where, In order to be in t During the period Regional Power of regional transmission, This represents the maximum permissible transmission power between regions.
5. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claims 1-4, characterized in that, The step of solving the multi-region virtual power plant coordinated optimization scheduling model using the improved whale optimization algorithm includes: Establish multiple individual whales to obtain a whale population; The whale population is initialized; The process involves multiple iterations until a termination condition is met, at which point the solution result of the final iteration is output. The termination condition includes the number of iterations already performed reaching the maximum number of iterations. K Alternatively, the global optimal solution obtained by continuously executing the iterative process multiple times converges; any round of the iterative process includes the following steps: The location information of each individual whale is substituted into the objective function for calculation to obtain the fitness value corresponding to each individual whale. Calculate the adaptive inertia weights corresponding to the individual whales; According to the formula Update the speed of each individual whale; where, In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The speed before the dimension update. In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The speed of dimension updates In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The position before the dimension update. For the first i The historical best position of the aforementioned individual whale. This represents the globally optimal position for all the aforementioned individual whales. , As a learning factor, , A random number between [0,1] For the first i The adaptive inertia weights corresponding to each individual whale; According to the formula Update the position of each of the aforementioned individual whales; wherein, In the first k In the iteration process described in the round, the first i The aforementioned individual whales d The updated position of the dimension; Boundary processing is performed on the whale individuals whose positions exceed the range of values for the decision variables after the position is updated; If the mutation triggering condition is met, perform the differential mutation operation; otherwise, terminate the iteration process described in this round.
6. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 5, characterized in that, The calculation of the adaptive inertia weight corresponding to the individual whale includes: According to the formula Calculate the adaptive inertia weights; wherein, The inertial weight, The maximum value of the inertia weight. This is the minimum value of the inertia weight. To calculate the fitness value of the individual whale for which the adaptive inertia weights need to be calculated, This represents the maximum fitness level of the current whale population. This represents the minimum fitness level of the current whale population.
7. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 6, characterized in that, The differential mutation operation includes: According to the formula New individuals are generated; among them, The location of the whale individual obtained after the differential mutation operation. For the best individual in the current population Dimension value, and For two different individuals randomly selected from the population, Dimension value, It is the difference variation factor; According to the formula Update the location of individual whales; among which, For the first The updated location of each individual whale. For the first The position of each individual whale before the update. The control parameter decreases linearly from 2 to 0. and A random number between [0,1]. For a randomly selected individual whale, the first dimensional components, Indicates the first The number of individual whales in the current [number] [number] [year] The adaptive inertia weights in the iterative process described above; Obtain the optimal position among the updated positions of all individual whales in the population; According to the formula Update the speed of individual whales; among them, For the first The updated speed of an individual whale. For the first The rate of change for each individual whale before the update. For the first The historical best position of the [number] individual whales dimensional components, The optimal position in the population is the first dimensional components, and As a learning factor, and It is a random number between [0,1].
8. The multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms according to claim 5, characterized in that, The initialization of the whale population includes: Determine the size of whale populations N Dimensions of an individual whale D and maximum number of iterations K ; Define the range of values for each decision variable. ,in d =1,2,⋯, D ; For the i For each individual whale, within the range of values for the decision variable, the formula is used. The initial position of the individual whale is randomly generated. and initial velocity ;in, For the first i The whale individual mentioned in the first The initial position of the decision variable. For the first i The whale individual mentioned in the first The initial velocity of the decision variable. To generate random numbers between 0 and 1, and This represents the velocity boundary.
9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory is used to store at least one program and the processor is used to load at least one program to execute the multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms as described in any one of claims 1-8.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the multi-region virtual power plant coordinated optimization scheduling method based on optimization algorithms as described in any one of claims 1-8.