Virtual power plant optimal scheduling method, device, equipment, storage medium and product

Abstract

The invention relates to a virtual power plant optimization scheduling method and device, equipment, a storage medium and a product. The method comprises the following steps: constructing a scheduling objective function corresponding to a virtual power plant by taking the maximum response resource of the virtual power plant in a corresponding power environment as an objective; determining constraint conditions of the scheduling objective function; the constraint conditions are used for constraining operation parameters of different power generation equipment in the virtual power plant; according to the scheduling objective function and the constraint condition, determining operation configuration parameters of different power generation equipment in the virtual power plant; and determining an optimal scheduling scheme of the virtual power plant according to the operation configuration parameters of different power generation equipment in the virtual power plant. By adopting the method, the optimal scheduling method of the virtual power plant can be generated, and the operation income of the virtual power plant can be improved based on the optimal scheduling method.

Description

Technical Field

[0001] This application relates to the field of integrated energy systems and multi-energy synergistic optimization technology, and in particular to a virtual power plant optimization scheduling method, device, equipment, storage medium and product. Background Technology

[0002] Against the backdrop of energy transition, integrated energy systems and multi-energy synergistic optimization technologies have become research hotspots, with virtual power plant optimization scheduling being a key component.

[0003] Currently, the proportion of renewable energy sources such as wind power and photovoltaics in the energy structure continues to increase. A large number of small-capacity, widely distributed, and highly volatile distributed resources are constantly being connected to the grid, giving rise to virtual power plants, which integrate these distributed resources to achieve efficient utilization.

[0004] However, the traditional centralized dispatching method faces many challenges in optimizing the dispatching of virtual power plants, which urgently need to be addressed. Summary of the Invention

[0005] Therefore, it is necessary to provide a virtual power plant optimization scheduling method, device, equipment, storage medium, and product to address the above-mentioned technical problems. This method can generate an optimized scheduling method for virtual power plants, thereby improving the operational benefits of virtual power plants.

[0006] Firstly, this application provides a virtual power plant optimized scheduling method, including:

[0007] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0008] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0009] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0010] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0011] In one embodiment, the scheduling objective function includes a first objective function and a second objective function; correspondingly, with the objective of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed, including:

[0012] The first objective function is constructed with the goal of maximizing the power output response resources of the virtual power plant.

[0013] A second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant.

[0014] Based on the first objective function and the second objective function, construct the scheduling objective function corresponding to the virtual power plant.

[0015] In one embodiment, a second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant, including:

[0016] A second objective function is constructed with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

[0017] In one embodiment, a first objective function is constructed with the goal of maximizing the grid power output response resources of the virtual power plant, including:

[0018] Obtain the power output of the virtual power plant at different times, and the corresponding unit power resources for each time period;

[0019] For any given time period, determine the corresponding power output response resources based on the power output and unit power resources for that time period.

[0020] The first objective function is constructed with the goal of maximizing the sum of power output response resources corresponding to each time period.

[0021] In one embodiment, the power generation equipment within the virtual power plant includes wind power generation equipment, solar power generation equipment, and hydrogen-to-electricity conversion equipment; correspondingly, the constraints include:

[0022] The first constraint condition used to constrain the turbine output of wind power generation equipment;

[0023] The second constraint condition used to constrain the photovoltaic output of solar power generation equipment;

[0024] The third constraint condition used to constrain the power generation of the hydrogen-to-electricity conversion device.

[0025] In one embodiment, the operating configuration parameters of different power generation devices within the virtual power plant are determined based on the scheduling objective function and constraints, including:

[0026] Based on the evolutionary reinforcement learning algorithm, the scheduling objective function is solved according to the constraints to determine the operating configuration parameters of different power generation equipment in the virtual power plant.

[0027] Secondly, this application also provides a virtual power plant optimized dispatching device, comprising:

[0028] The function construction module is used to construct the scheduling objective function corresponding to the virtual power plant with the goal of maximizing the response resources of the virtual power plant in the corresponding power environment;

[0029] The constraint determination module is used to determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0030] The parameter determination module is used to determine the operating configuration parameters of different power generation equipment within the virtual power plant based on the scheduling objective function and constraints.

[0031] The scheme determination module is used to determine the optimal scheduling scheme of the virtual power plant based on the operating configuration parameters of different power generation equipment within the virtual power plant.

[0032] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0033] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0034] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0035] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0036] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0039] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0040] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0041] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0042] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0043] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0044] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0045] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0046] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0047] The aforementioned virtual power plant optimization scheduling method, device, equipment, storage medium, and product aim to maximize the response resources of the virtual power plant in the corresponding power environment. They construct a scheduling objective function for the virtual power plant, determine the constraints of this objective function, and use these constraints to constrain the operating parameters of different power generation equipment within the virtual power plant. Based on the scheduling objective function and constraints, they determine the operating configuration parameters of different power generation equipment within the virtual power plant, and finally, based on these parameters, determine the optimized scheduling scheme for the virtual power plant. By constructing a scheduling objective function that maximizes response resources, the virtual power plant can comprehensively consider the operating costs of various power generation equipment, including fuel costs, maintenance costs, and start-up and shutdown costs. Under the premise of meeting electricity demand, the optimized scheduling scheme reduces overall operating costs and improves economic efficiency. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating a virtual power plant optimization scheduling method in one embodiment;

[0050] Figure 2 This is a flowchart illustrating the steps of constructing the scheduling objective function in one embodiment;

[0051] Figure 3 This is a flowchart illustrating the virtual power plant optimization scheduling method in another embodiment;

[0052] Figure 4 This is a structural block diagram of a virtual power plant optimization scheduling device in one embodiment;

[0053] Figure 5 This is a structural block diagram of the virtual power plant optimization scheduling device in another embodiment;

[0054] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0057] Before introducing the embodiments of this application, it should be noted that the optimal scheduling of virtual power plants is a complex problem that is high-dimensional, non-convex, and has many constraints. Traditional methods often suffer from premature convergence when dealing with such problems, that is, they get trapped in local optima too early and fail to find the global optimum. At the same time, the scheduling accuracy will also drop significantly, resulting in a large deviation between the scheduling results and the actual needs. Moreover, the robustness is insufficient and it is difficult to adapt to the strong fluctuation characteristics of distributed resources, which makes the control difficulty increase sharply and fails to meet the requirements of efficient and stable operation of virtual power plants.

[0058] In one exemplary embodiment, such as Figure 1 As shown, a virtual power plant optimization scheduling method is provided, including the following steps:

[0059] S110: With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, construct the scheduling objective function corresponding to the virtual power plant.

[0060] In this context, a virtual power plant can be a virtual power plant with a need for optimized dispatch. The power environment can be understood as the power market.

[0061] A virtual power plant is a coordinated management system that aggregates and optimizes distributed energy resources (DERs) such as distributed power sources (e.g., solar photovoltaic, wind power), energy storage systems (e.g., lithium-ion batteries, flow batteries), controllable loads (e.g., electric vehicle charging stations, smart air conditioners), and microgrids through advanced information and communication technologies and intelligent control algorithms. It breaks down the physical boundaries between power plants and consumers in traditional power systems, simulating the functions of traditional power plants through digital means, and participating in electricity market transactions and grid operation.

[0062] It should be noted that virtual power plants can be used to generate electricity based on solar, wind, and hydropower, and the electricity produced is used to supply production in the region. However, if the power generated by the virtual power plant is insufficient to support the corresponding production needs, electricity must be purchased from the power grid company.

[0063] Based on the above background, it can be understood that, with the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, the scheduling objective function corresponding to the virtual power plant needs to consider the electricity demand, the power generation, and the electricity sales price of the power grid company.

[0064] In one alternative implementation, the electricity demand of the virtual power plant in the short term, such as the daily electricity demand, can be obtained. Based on the daily electricity demand, power generation, and the electricity sales price of the power grid company, a short-term scheduling objective function corresponding to the virtual power plant can be constructed, that is, the scheduling objective function for that day.

[0065] For example, the daily electricity demand, power generation, and the electricity price sold by the power grid company can be input into a pre-trained function building model to generate the scheduling objective function for that day.

[0066] In another alternative implementation, the long-term electricity demand of the virtual power plant can be obtained, such as the annual electricity demand. Based on the annual electricity demand, power generation, and the electricity sales price of the power grid company, a long-term scheduling objective function corresponding to the virtual power plant can be constructed, which is also the scheduling objective function for the current year.

[0067] S120, Determine the constraints of the scheduling objective function.

[0068] Among them, the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0069] In one alternative implementation, the power generation equipment within the virtual power plant includes wind power generation equipment, solar power generation equipment, and hydrogen-to-electricity conversion equipment; correspondingly, the constraints include: a first constraint condition for constraining the wind turbine output of the wind power generation equipment; a second constraint condition for constraining the photovoltaic output of the solar power generation equipment; and a third constraint condition for constraining the power generation capacity of the hydrogen-to-electricity conversion equipment.

[0070] Optionally, a piecewise wind speed-power curve can be created for each wind turbine, compressing the feasible output that varies with wind speed into a hard boundary: power is forced to zero when below the cut-in threshold or above the cut-out threshold, linearly increases between cut-in and rated power, and remains constant at the nameplate value between rated power and cut-out. Simultaneously, the upper and lower limits are locked using operating state variables, ensuring that dispatch commands always fall within the only physically permissible range for the unit. This eliminates the need for redundancy to account for wind power uncertainties and directly provides a rigid resource envelope available to the optimizer. Correspondingly, the first constraint condition can be as follows:

[0071] ;

[0072] In the formula, Represents virtual power plant time period The output of the wind turbine, These are the cut-in and cut-out wind velocities of the wind turbines in the virtual power plant. The rated wind speed of the fan. This refers to the rated power of the fan.

[0073] Optionally, a light-power elastic boundary can be constructed within the virtual power plant for the photovoltaic array: driven by real-time irradiance, the power remains zero below a threshold, then rises steeply along a piecewise straight line after exceeding the threshold, leveling off in the saturation region. Negative feedback from temperature drift and aging degradation is superimposed throughout, compressing the upper limit of output into a hard cap that fluctuates second-by-second with environmental changes. This allows optimized scheduling to directly utilize the instantaneous available capacity of the photovoltaic array at any given time, without needing to reserve a buffer for irradiance uncertainties. Correspondingly, the second constraint can be as follows:

[0074] ;

[0075] In the formula, Represents virtual power plant time period The output of the photovoltaic array This represents the area of ​​the photovoltaic array in the virtual power plant. Indicates the photovoltaic temperature coefficient. Indicates energy conversion efficiency. and They represent time periods respectively. The actual temperature and the rated temperature of the photovoltaic array, Indicates time period Irradiance.

[0076] In one alternative implementation, the water electrolysis hydrogen production device can be abstracted as an energy hub within an electro-hydrogen synergistic framework. Its core value lies in converting surplus renewable electricity into hydrogen-based chemical energy through high-energy-density, long-term storage. This device possesses millisecond-level power response characteristics and a wide-range load regulation capability, enabling rapid decoupling and high-precision control of the bidirectional energy flow between electricity and hydrogen. This provides zero-carbon, time-shifted flexibility under conditions of dual source-load uncertainty. Its operating boundary is defined by an upper limit constraint on electrical power input, ensuring that the input power at any time does not exceed the device's rated processing capacity, thereby guaranteeing the safety and efficiency of the electro-hydrogen conversion process. Correspondingly, the third constraint includes the constraints corresponding to the water electrolysis hydrogen production device:

[0077] ;

[0078] in, For proton exchange membrane electrolyzers during time periods The injected electrical power, The efficiency of the electro-hydrogen conversion takes into account both Faraday efficiency and heat loss. For time period Hydrogen production mass flow rate.

[0079] ;

[0080] in, This is the rated electrical power.

[0081] In another alternative implementation, hydrogen fuel cells can be defined as peak arbitrage resources in an electric-hydrogen co-operated virtual power plant. Their function is to efficiently convert green hydrogen energy storage into electrical energy through electrochemical reactions under extreme conditions such as real-time electricity price spikes, carbon price surges, or sharp drops in wind and solar power output, thus achieving a secondary enhancement of energy value. This device possesses hourly continuous discharge capability, simultaneously obtaining the dual benefits of peak compensation and carbon emission reduction. Its operating boundary is constrained by both minimum technical output and maximum power generation capacity, ensuring that the output power remains within a safe and feasible range at all times, thereby providing the virtual power plant with flexible support that combines reliability, low carbon footprint, and economy. Correspondingly, the third constraint includes the constraints corresponding to hydrogen fuel cells:

[0082] ;

[0083] in, For hydrogen fuel cells during time periods The hydrogen mass flow rate consumed, together with the hydrogen production flow rate, constitutes the hydrogen mass conservation. The hydrogen-to-electricity conversion efficiency is determined by both the stack polarization loss and the power consumption of the auxiliary system. To determine the power output of a hydrogen fuel cell, the power output must meet upper and lower limits:

[0084] ;

[0085] in, This represents the upper limit of the power generation capacity of hydrogen fuel cells.

[0086] In another alternative embodiment, the hydrogen storage tank can be abstracted as a hydrogen time-shifting storage unit. Its function is to receive and store green hydrogen produced by the water electrolysis hydrogen production unit during periods of surplus renewable electricity and low electricity prices, and to release hydrogen to the hydrogen fuel cell during periods of power shortage or high electricity prices, thus achieving energy migration across time periods. This storage tank possesses high energy self-sufficiency and extremely low self-dissipation rate. Its operating boundary is constrained by both a lower and upper limit of storage capacity, ensuring that the hydrogen inventory in the tank remains within a safe and feasible region at any given time, thereby providing the virtual power plant with stable, controllable, and long-term hydrogen energy buffering and regulation capabilities. Correspondingly, the third constraint condition may include the constraint condition corresponding to the hydrogen storage tank:

[0087] ;

[0088] in, For time period Hydrogen storage capacity and stock. For time period The mass of injected hydrogen, For time period The mass of hydrogen extracted by the fuel cell.

[0089] ;

[0090] in, and These represent the lower and upper limits of hydrogen storage capacity in the hydrogen storage tank, respectively.

[0091] Furthermore, adjustable loads with demand response potential within the virtual power plant are abstracted as virtual generation resources. Price-based or incentive-based demand response mechanisms guide users to adjust their electricity consumption behavior, achieving the transformation of rigid loads into flexible capacity within a framework that ensures basic energy needs and user comfort. This capacity is constrained by multiple factors such as equipment operating limits, user tolerance ranges, and incentive levels, possessing bidirectional adjustment capabilities. It can participate in the joint optimization and clearing of the energy market and ancillary service market as positive or negative reserves, thereby enhancing the flexible adjustment capabilities of the virtual power plant in scenarios with high proportions of renewable energy integration, and improving the economic efficiency and reliability of system operation. Correspondingly, the constraints can also include constraints on the operation of adjustable loads.

[0092] ;

[0093] in, For time period No. The actual power consumption of the adjustable load. For time period No. A preset power consumption for an adjustable load. For the first time in the scheduling cycle The maximum allowable adjustable energy for an adjustable load:

[0094] ;

[0095] in, For time period No. The minimum acceptable power consumption of an adjustable load.

[0096] Alternatively, the traditional synchronous generating units within a virtual power plant can be defined as dispatchable power generation resources within a multi-energy complementary architecture. Their functional positioning has shifted from being the primary baseload supplier to dynamic balancing nodes with rapid response capabilities. These units provide auxiliary services in power regulation, inertia compensation, and voltage support, and assume peak capacity responsibility when renewable energy output fluctuates drastically. Their operating boundaries are jointly constituted by minimum technical output, maximum power generation capacity, and ramp rate per unit time, ensuring the physical feasibility of dispatch commands and thus supporting the synergistic optimization of economy, low carbon emissions, and reliability in virtual power plants under scenarios with high renewable energy penetration. Correspondingly, constraints can also include constraints on the operation of conventional units.

[0097] ;

[0098] in, For conventional units in a virtual power plant during time periods Power generation capacity, This represents the upper limit of the generating capacity of conventional units in a virtual power plant. This represents the lower limit of the power generation capacity of conventional units in a virtual power plant. This represents the ramp-up rate of conventional units in a virtual power plant.

[0099] S130: Determine the operating configuration parameters of different power generation equipment within the virtual power plant based on the scheduling objective function and constraints.

[0100] In one alternative implementation, the scheduling objective function can be solved based on constraints, and the solution can be used as the operating configuration parameters for different power generation equipment within the virtual power plant.

[0101] For example, the scheduling objective function and corresponding constraints can be input into a pre-trained solution model to obtain the operating configuration parameters of different power generation equipment inside the virtual power plant.

[0102] In another alternative implementation, an evolutionary reinforcement learning algorithm can be used to solve the scheduling objective function based on constraints, thereby determining the operating configuration parameters of different power generation equipment within the virtual power plant.

[0103] Optionally, the agent update method in the evolutionary reinforcement learning algorithm can adopt an actor-critic update strategy. Specifically, the upgrade of the policy individual follows an "actor-evaluator" collaborative update paradigm. The evaluator sub-network consists of multiple stacked convolutional units, responsible for scoring the value of state-action pairs, thereby providing gradient guidance for the actor's decision-making.

[0104] ;

[0105] In the formula, It is an evaluation value; It is a state-action pair Input the output value of the critic network; This represents the structure and parameters of the critic network. Furthermore, The true evaluation value can be expressed as:

[0106] ;

[0107] In the formula, For subsequent state-action pairs Evaluation value; It is the reward value obtained instantly; It is the coefficient for the decline in long-term returns.

[0108] As far as the critics' network is concerned, Parameter adjustment target and The distance is compressed to a minimum, that is, the single-step timing difference is controlled within a neighborhood approaching zero. This difference is quantitatively written as:

[0109] ;

[0110] In the formula, This represents the timing difference in a single step.

[0111] The actor network, composed of stacked convolutional layers, is responsible for generating decision vectors to be implemented based on current observations. Its mapping process can be described as follows:

[0112] ;

[0113] In the formula, This represents the current input state. Characterize the convolutional structure and learnable parameters of the actor network; This represents the distribution of random policies instantiated from the network.

[0114] Regarding actor networks, when a specific state When input, its learnable parameters By maximizing expectations And the update, at this point, if the critic network... With the input state fixed, It can be expressed as about The composite function is specifically expressed as:

[0115] ;

[0116] In the formula, For the objective function with respect to parameters The policy network iterates its parameters along the gradient's ascending direction.

[0117] After obtaining the initial population using the actor critic algorithm, the small-scale archerfish algorithm is used to make scheduling decisions. When the "detection radius" is much larger than the range where prey may exist, the algorithm automatically widens the scanning bandwidth to capture any potential extreme points with an extremely low probability of omission. This mechanism gives the system sufficient global exploration capability in the early stage, and it decays linearly with the number of iterations, smoothly completing the switch from "wide-area search to fine mining".

[0118] ;

[0119] in, This represents the current iteration number. The maximum number of iterations, To discover the coefficient.

[0120] When the target is located in the "mid-range" interval, the archerfish instantaneously adjusts the pressure inside the cavity, calibrating the jet into a "sniper water line" with low divergence and high hit rate. Applying Cauchy-type perturbation near the global extremum, searching only the neighborhood of the current optimal solution, significantly improves the local mining resolution.

[0121] ;

[0122] in, This is the water jet coefficient.

[0123] When prey is struck by a water jet, it is impacted by a random force and derails from its original trajectory. In algorithm terms, this corresponds to injecting random perturbations into the current optimal position within the solution space, causing unpredictable, minute displacements in individuals, helping the population escape local optima and maintain diversity.

[0124] ;

[0125] in, It is the amplitude of the disturbance.

[0126] Fish sweep across the water surface with a cosine-like head swing, using periodic large swings to expand their field of vision to a wider area, thereby increasing the probability of finding prey. In terms of algorithms: a cosine kernel is used to generate a wide-step probe, which guides individuals to complete periodic large-span cruises in the solution space, significantly expanding the early global exploration coverage.

[0127] ;

[0128] in, This represents the current individual's location. Two different individuals were randomly selected; It is a random number; This represents multiplication by dimension.

[0129] The small-scaled archerfish adjusts its tongue-palatine angle and oral pressure in real time based on the prey's suspended height and horizontal offset, ensuring the water jet trajectory always points towards the target's center, thus maximizing the hit probability. In algorithm terms: using the current globally optimal individual... As the gravitational core, a Cauchy perturbation is superimposed, allowing the search particles to perform precise reconnaissance by alternating long-range jumps and dense point shots in the "optimal vicinity," thus locking onto high-quality areas while retaining the mobility to break out of local traps at any time.

[0130] ;

[0131] in, It is a standard Cauchy random vector.

[0132] Once prey falls into the water, its landing location is randomly distributed due to factors such as airflow and posture. The small-scaled archerfish immediately turns its body and dashes towards the unpredictable landing point to devour it. Mapped to the algorithm: even towards the end of the iteration process, a one-dimensional "micro-amplitude random drift" term is retained in the update formula, continuously generating millimeter-level perturbations around the optimal solution, forcing the population to maintain gene flow, and completely blocking the path to premature convergence.

[0133] ;

[0134] in, These are the upper and lower bound vectors for the search, respectively.

[0135] Fish swarms write the coordinates of the most food locations into their collective memory and broadcast this information instantly via lateral radio waves: whoever discovers a high-value landing point becomes the temporary navigator, and the rest of the fish immediately turn around and follow. In algorithmic terms: a hard-filter update rule is designed so that only when the target value of a new solution is strictly better than the population mean is it allowed to be written into the public knowledge base, triggering a full-scale location synchronization; inferior information is directly discarded. In this way, the entire population is constantly pulled by the gravitational pull of better options, sliding along the steep slope of the objective function, resulting in an exponentially increasing convergence speed.

[0136] ;

[0137] in, The fitness function (objective function value) is used. Finally, the optimal small-scaled archerfish individual is output, whose internal decision variables represent the operating configuration parameters of different power generation equipment in the virtual power plant.

[0138] In the above process, the degree of constraint violation is used as the reward function to obtain the initial population of the Small Scale Shooterfish algorithm. The Small Scale Shooterfish algorithm is used to solve the model: the optimization span is adaptively compressed by detecting the gain factor to approach the extreme point in a spiral manner; the weight of global-detail exploration is coordinated by relying on cosine wide-area traversal; neighborhood perturbation is applied by Cauchy spike pulse to escape suboptimal traps; random drift shooting is used to add micro-jitter to the solution vector to continuously activate population differences; then, an elite replication and communication strategy is used to quickly filter low-quality individuals and amplify high-quality genes, and iteratively obtain the optimal day-ahead scheduling scheme to solve the resource allocation imbalance and power oscillation problems caused by insufficient convergence due to high-dimensional nonlinearity, multiple time scales and strong random coupling characteristics in the optimization scheduling of virtual power plants in existing evolutionary reinforcement learning methods.

[0139] S140: Determine the optimal scheduling scheme for the virtual power plant based on the operating configuration parameters of different power generation equipment within the virtual power plant.

[0140] For example, the operating configuration parameters of different power generation equipment within a virtual power plant are integrated to obtain an optimized scheduling scheme for the virtual power plant.

[0141] In the aforementioned virtual power plant optimization scheduling method, the objective function for the virtual power plant is constructed with the goal of maximizing the response resources of the virtual power plant in the corresponding power environment. Constraints on the objective function are then determined, which are used to constrain the operating parameters of different power generation equipment within the virtual power plant. Based on the objective function and constraints, the operating configuration parameters of different power generation equipment within the virtual power plant are determined. Finally, based on these operating configuration parameters, an optimized scheduling scheme for the virtual power plant is determined. By constructing a scheduling objective function that maximizes response resources, the virtual power plant can comprehensively consider the operating costs of various power generation equipment, including fuel costs, maintenance costs, and start-up and shutdown costs. Under the premise of meeting electricity demand, the overall operating cost is reduced and economic efficiency is improved through optimized scheduling.

[0142] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the scheduling objective function includes a first objective function and a second objective function. In this case, the process of constructing the scheduling objective function corresponding to the virtual power plant with the objective of maximizing the response resources of the virtual power plant in the corresponding power environment is refined.

[0143] See Figure 2 The steps for constructing the scheduling objective function shown include:

[0144] S210, with the goal of maximizing the power output response resources of the virtual power plant, constructs the first objective function.

[0145] In one alternative implementation, the power output of the virtual power plant at different time periods and the unit power resources corresponding to the corresponding time periods can be obtained; for any time period, the power output response resources corresponding to the time period are determined based on the power output power and unit power resources corresponding to the time period; and a first objective function is constructed with the goal of maximizing the sum of the power output response resources corresponding to each time period.

[0146] Among them, power output can be understood as electricity sales power; unit power resources can be understood as electricity sales price per unit.

[0147] In one alternative implementation, the first objective function can be as follows:

[0148] ;

[0149] In the formula, A represents the revenue from electricity sales; This represents the unit of electricity resources corresponding to time period t; This represents the power output during time period t.

[0150] S220 constructs a second objective function with the goal of minimizing the power-related resource requirements of the virtual power plant.

[0151] Among these, electricity-related demand resources can be understood as electricity costs under different dimensions.

[0152] In one alternative implementation, a second objective function can be constructed with the goal of minimizing the sum of the virtual power plant's power input response resources, power generation demand resources, and carbon emission demand resources.

[0153] For example, the second objective function can be as follows:

[0154] ;

[0155] In the formula, B represents the electricity-related demand resources; is the electricity purchase cost for the first hour; is the power generation cost of the conventional unit for the first hour; is the cost of electricity-to-hydrogen conversion for the first hour; is the cost of hydrogen-to-electricity conversion for the first hour; and is the carbon emission cost of the virtual power plant operating for the first hour.

[0156] in, ;

[0157] In the formula, For the first The daytime market electricity price for the hour. For the first The daytime market purchase price of electricity for the hour. For the first The daily market electricity sales volume for the past hour. For the first The daily market power purchase volume for the hour. For the first The power generation capacity of conventional generating units during each time period For the power of electro-hydrogen conversion, The power converted from hydrogen to electricity, and These are the friction cost coefficients for the electrolyzer and the hydrogen fuel cell, respectively. This is the cost coefficient for conventional generating units. and These are the carbon emission coefficient and carbon penalty cost coefficient for conventional units, respectively.

[0158] S230, construct the scheduling objective function corresponding to the virtual power plant based on the first objective function and the second objective function.

[0159] Specifically, in this embodiment, the difference between the first objective function and the second objective function can be used as the scheduling objective function corresponding to the virtual power plant. For example, the scheduling objective function can be as follows:

[0160] ;

[0161] ;

[0162] In the formula, For the first Revenue from selling electricity to the grid every hour For the first The cost of purchasing electricity per hour For the first The hourly power generation cost of a conventional generating unit. For the first The cost of converting electricity to hydrogen per hour No. The cost of converting hydrogen to electricity in one hour For the operation of virtual power plants The carbon emission cost per hour For the first The daytime market electricity price for the hour. For the first The daytime market purchase price of electricity for the hour. For the first The daily market electricity sales volume for the past hour. For the first The daily market power purchase volume for the hour. For the first The power generation capacity of conventional generating units during each time period For the power of electro-hydrogen conversion, The power converted from hydrogen to electricity, and These are the friction cost coefficients for the electrolyzer and the hydrogen fuel cell, respectively. This is the cost coefficient for conventional generating units. and These are the carbon emission coefficient and carbon penalty cost coefficient for conventional units, respectively.

[0163] The above embodiments provide a specific method for constructing the objective function, making the construction process of the objective function clearer.

[0164] Based on the technical solutions of the above embodiments, this application also provides an optional embodiment. In this optional embodiment, the virtual power plant optimized scheduling method provided by this application is summarized.

[0165] See Figure 3 The virtual power plant optimization scheduling method shown includes:

[0166] S310 establishes operational constraint models for wind turbines, photovoltaic arrays, conventional units, adjustable loads, and hydrogen-to-electricity conversion equipment within a virtual power plant, respectively characterizing power upper and lower limits, ramp-up and ramp-down conditions, state of charge, and reduction boundaries.

[0167] S320 aims to maximize the expected revenue of virtual power plants in the day-ahead electricity market. It unifies the dimensions of electricity sales revenue, electricity purchase cost, friction cost of hydrogen-to-electricity conversion equipment, power generation cost, and carbon emission trading cost to construct an optimization model.

[0168] S330 uses an evolutionary reinforcement learning algorithm to obtain the optimal day-ahead scheduling scheme.

[0169] For example, using the actor-critic reinforcement learning algorithm with the degree of constraint violation as the reward function, the initial population of the small-scale archerfish algorithm is obtained. The small-scale archerfish algorithm is used to solve the model: the optimization span is adaptively compressed by detecting the gain factor to approach the extreme point in a spiral manner; the weight of global-detail exploration is coordinated by relying on cosine wide-area traversal; neighborhood perturbation is applied by Cauchy spike pulse to escape suboptimal traps; random drifting is used to add micro-jitter to the solution vector to continuously activate the population difference; and an elite replication and communication strategy is used to quickly filter low-quality individuals and amplify high-quality genes, iteratively obtaining the optimal day-ahead scheduling scheme.

[0170] S340 sends the output instructions for each time period of the optimal solution to the corresponding distributed resources, tracks and executes them in real time, and completes the optimized scheduling of the virtual power plant.

[0171] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0172] Based on the same inventive concept, this application also provides a virtual power plant optimization scheduling device for implementing the virtual power plant optimization scheduling method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more virtual power plant optimization scheduling device embodiments provided below can be found in the limitations of the virtual power plant optimization scheduling method described above, and will not be repeated here.

[0173] In one exemplary embodiment, such as Figure 4As shown, a virtual power plant optimization scheduling device is provided, including: a function construction module 410, a constraint determination module 420, a parameter determination module 430, and a scheme determination module 440, wherein:

[0174] The function construction module 410 is used to construct the scheduling objective function corresponding to the virtual power plant with the goal of maximizing the response resources of the virtual power plant in the corresponding power environment.

[0175] The constraint determination module 420 is used to determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0176] The parameter determination module 430 is used to determine the operating configuration parameters of different power generation equipment inside the virtual power plant based on the scheduling objective function and constraints.

[0177] The scheme determination module 440 is used to determine the optimal scheduling scheme of the virtual power plant based on the operating configuration parameters of different power generation equipment inside the virtual power plant.

[0178] In one embodiment, the scheduling objective function includes a first objective function and a second objective function; correspondingly, such as Figure 5 As shown, the function construction module 410 includes a first construction unit 4101, which is used to construct a first objective function with the goal of maximizing the power output response resources of the virtual power plant; a second construction unit 4102, which is used to construct a second objective function with the goal of minimizing the power-related demand resources of the virtual power plant; and a third construction unit 4103, which is used to construct a scheduling objective function corresponding to the virtual power plant based on the first objective function and the second objective function.

[0179] In one embodiment, the second building unit is specifically used to construct a second objective function with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

[0180] In one embodiment, the first construction unit includes an acquisition subunit for acquiring the power output of the virtual power plant at different time periods and the unit power resources corresponding to the corresponding time periods; a determination subunit for determining the power output response resources corresponding to any time period based on the power output and unit power resources corresponding to the time period; and a construction subunit for constructing a first objective function with the goal of maximizing the sum of the power output response resources corresponding to each time period.

[0181] In one embodiment, the power generation equipment within the virtual power plant includes wind power generation equipment, solar power generation equipment, and hydrogen-to-electricity conversion equipment; correspondingly, the constraints include: a first constraint for constraining the wind turbine output of the wind power generation equipment; a second constraint for constraining the photovoltaic output of the solar power generation equipment; and a third constraint for constraining the power generation capacity of the hydrogen-to-electricity conversion equipment.

[0182] In one embodiment, the scheme determination module 440 is specifically used to solve the scheduling objective function based on the evolutionary reinforcement learning algorithm and according to the constraints, and determine the operating configuration parameters of different power generation equipment inside the virtual power plant.

[0183] Each module in the aforementioned virtual power plant optimization dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0184] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a virtual power plant optimization scheduling method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0185] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0186] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0187] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0188] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0189] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0190] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0191] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0192] The first objective function is constructed with the goal of maximizing the power output response resources of the virtual power plant.

[0193] A second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant.

[0194] Based on the first objective function and the second objective function, construct the scheduling objective function corresponding to the virtual power plant.

[0195] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0196] A second objective function is constructed with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

[0197] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0198] Obtain the power output of the virtual power plant at different times, and the corresponding unit power resources for each time period;

[0199] For any given time period, determine the corresponding power output response resources based on the power output and unit power resources for that time period.

[0200] The first objective function is constructed with the goal of maximizing the sum of power output response resources corresponding to each time period.

[0201] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0202] Based on the evolutionary reinforcement learning algorithm, the scheduling objective function is solved according to the constraints to determine the operating configuration parameters of different power generation equipment in the virtual power plant.

[0203] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0204] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0205] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0206] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0207] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0208] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0209] The first objective function is constructed with the goal of maximizing the power output response resources of the virtual power plant.

[0210] A second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant.

[0211] Based on the first objective function and the second objective function, construct the scheduling objective function corresponding to the virtual power plant.

[0212] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0213] A second objective function is constructed with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

[0214] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0215] Obtain the power output of the virtual power plant at different times, and the corresponding unit power resources for each time period;

[0216] For any given time period, determine the corresponding power output response resources based on the power output and unit power resources for that time period.

[0217] The first objective function is constructed with the goal of maximizing the sum of power output response resources corresponding to each time period.

[0218] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0219] Based on the evolutionary reinforcement learning algorithm, the scheduling objective function is solved according to the constraints to determine the operating configuration parameters of different power generation equipment in the virtual power plant.

[0220] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0221] With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed.

[0222] Determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant.

[0223] Based on the scheduling objective function and constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant;

[0224] Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

[0225] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0226] The first objective function is constructed with the goal of maximizing the power output response resources of the virtual power plant.

[0227] A second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant.

[0228] Based on the first objective function and the second objective function, construct the scheduling objective function corresponding to the virtual power plant.

[0229] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0230] A second objective function is constructed with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

[0231] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0232] Obtain the power output of the virtual power plant at different times, and the corresponding unit power resources for each time period;

[0233] For any given time period, determine the corresponding power output response resources based on the power output and unit power resources for that time period.

[0234] The first objective function is constructed with the goal of maximizing the sum of power output response resources corresponding to each time period.

[0235] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0236] Based on the evolutionary reinforcement learning algorithm, the scheduling objective function is solved according to the constraints to determine the operating configuration parameters of different power generation equipment in the virtual power plant.

[0237] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0238] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0239] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0240] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A virtual power plant optimized scheduling method, characterized in that, The method includes: With the goal of maximizing the response resources of the virtual power plant in the corresponding power environment, a scheduling objective function corresponding to the virtual power plant is constructed. The constraints of the scheduling objective function are determined; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant. Based on the scheduling objective function and the constraints, determine the operating configuration parameters of different power generation equipment within the virtual power plant; Based on the operating configuration parameters of different power generation equipment within the virtual power plant, an optimized scheduling scheme for the virtual power plant is determined.

2. The method according to claim 1, characterized in that, The scheduling objective function includes a first objective function and a second objective function; correspondingly, constructing the scheduling objective function corresponding to the virtual power plant, with the objective of maximizing the response resources of the virtual power plant in the corresponding power environment, includes: The first objective function is constructed with the goal of maximizing the power output response resources of the virtual power plant. The second objective function is constructed with the goal of minimizing the power-related resource requirements of the virtual power plant. Based on the first objective function and the second objective function, construct the scheduling objective function corresponding to the virtual power plant.

3. The method according to claim 2, characterized in that, The second objective function, which aims to minimize the power-related resource requirements of the virtual power plant, includes: The second objective function is constructed with the goal of minimizing the sum of the power input response resources, power generation demand resources, and carbon emission demand resources of the virtual power plant.

4. The method according to claim 2, characterized in that, The first objective function, which aims to maximize the grid power output response resources of the virtual power plant, is constructed as follows: Obtain the power output of the virtual power plant at different times, and the corresponding unit power resources for each time period; For any given time period, the power output response resources corresponding to that time period are determined based on the power output power and unit power resources for that time period. The first objective function is constructed with the goal of maximizing the sum of power output response resources corresponding to each time period.

5. The method according to any one of claims 1-4, characterized in that, The power generation equipment within the virtual power plant includes wind power generation equipment, solar power generation equipment, and hydrogen-to-electricity conversion equipment; correspondingly, the constraints include: A first constraint condition for constraining the wind turbine output of the wind power generation equipment; A second constraint condition for constraining the photovoltaic output of the solar power generation equipment; A third constraint condition used to constrain the power generation of the hydrogen-to-electricity conversion device.

6. The method according to any one of claims 1-4, characterized in that, The step of determining the operating configuration parameters of different power generation equipment within the virtual power plant based on the scheduling objective function and the constraints includes: Based on the evolutionary reinforcement learning algorithm, the scheduling objective function is solved according to the constraints to determine the operating configuration parameters of different power generation equipment inside the virtual power plant.

7. A virtual power plant optimization dispatching device, characterized in that, The device includes: The function construction module is used to construct the scheduling objective function corresponding to the virtual power plant with the goal of maximizing the response resources of the virtual power plant in the corresponding power environment; The constraint determination module is used to determine the constraints of the scheduling objective function; the constraints are used to constrain the operating parameters of different power generation equipment within the virtual power plant. The parameter determination module is used to determine the operating configuration parameters of different power generation equipment inside the virtual power plant based on the scheduling objective function and the constraints. The scheme determination module is used to determine the optimal scheduling scheme of the virtual power plant based on the operating configuration parameters of different power generation equipment within the virtual power plant.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-6.

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

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

Images