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

Abstract

The invention discloses a virtual power plant optimal scheduling method and device, a medium and a product, and relates to the technical field of power plant electric energy resource scheduling and allocation, and the method comprises the steps: obtaining basic data of a virtual power plant; respectively carrying out clustering analysis on the temperature control load data and the electric vehicle data by adopting a density clustering algorithm and a K-means + + algorithm based on an HHACOA algorithm to obtain a clustering result; according to the basic data of the virtual power plant, an internal approximation constraint space integration method is adopted, and adjustable power domain data of the whole temperature control load cluster and adjustable power domain data of the whole electric vehicle cluster are determined; establishing a planning function optimization model according to the adjustable power domain data of the temperature control load cluster, the adjustable power domain data of the electric vehicle cluster and the clustering result; and solving the planning function optimization model to obtain an optimization strategy result of the virtual power plant. The method can improve the adjustment capability of the virtual power plant to the power grid, and guarantees the safety and stability of the power system.

Description

Technical Field

[0001] The present application relates to the technical field of power plant electric energy resource scheduling and allocation, and in particular to a virtual power plant optimization scheduling method, equipment, medium and product. Background Art

[0002] Virtual power plant is a new energy management model that optimizes the scheduling and utilization of distributed energy resources such as wind power, photovoltaic power generation, controllable loads (such as adjustable industrial electricity and smart home devices), energy storage facilities and electric vehicles by integrating and coordinating these resources. This integration method not only mimics the functions of traditional large-scale power plants, but also has higher flexibility and sustainability. In this complex, each component plays a unique and vital role. Among them, temperature control loads and electric vehicles have become key factors in improving the stability of virtual power plants due to their flexible power demand adjustment capabilities.

[0003] Temperature-controlled loads and electric vehicles are important cornerstones of the stability of virtual power plants because they can flexibly adjust electricity demand and alleviate the intermittent and unstable problems of renewable energy generation. Wind and solar power generation are constrained by natural conditions, and power generation fluctuates with time and weather changes, which poses a challenge to the balance of supply and demand in the power grid. Temperature-controlled loads can increase power consumption when there is excess power through intelligent control and reduce loads during peak power demand, thereby helping to balance the supply and demand relationship of the power grid. Electric vehicles can be charged when power demand is low, and feed back power to the power grid through V2G (Vehicle to Grid) technology during peak demand, further enhancing the flexibility and stability of the power grid. In addition, reasonable scheduling of temperature-controlled loads and electric vehicles can also participate in grid ancillary services, such as demand response, further enhancing the peak-shaving and valley-filling capabilities of virtual power plants. Therefore, scientific and reasonable planning and scheduling of temperature-controlled loads and electric vehicle resources are directly related to the stability of the overall operation of virtual power plants, and are one of the important means to ensure the balance of power supply and demand in the power grid and improve the efficiency of renewable energy utilization.

[0004] Although the existing technology has conducted a lot of research on the reasonable dispatching management of temperature control loads and electric vehicles, it is still insufficient from the perspective of virtual power plants, especially considering how to improve their operating stability and peak-shaving and valley-filling capabilities. Based on this, it is necessary to study a virtual power plant optimization dispatching method that considers the aggregation of electric vehicles and temperature control loads to improve the virtual power plant's ability to regulate the power grid and ensure the safety and stability of the power system. Summary of the invention

[0005] The purpose of this application is to provide a virtual power plant optimization scheduling method, equipment, medium and product, which can improve the virtual power plant's ability to regulate the power grid and ensure the safety and stability of the power system.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a virtual power plant optimization scheduling method, the virtual power plant optimization scheduling method comprising the following steps:

[0008] Obtaining basic data of a virtual power plant; the basic data of a virtual power plant includes temperature control load data and electric vehicle data, the temperature control load data includes power consumption behavior data of each temperature control load in the virtual power plant, and the electric vehicle data includes power consumption behavior data of each electric vehicle in the virtual power plant.

[0009] A density clustering algorithm is used to perform cluster analysis on the temperature control load data, and a K-means++ algorithm based on the HHACOA algorithm is used to perform cluster analysis on the electric vehicle data to obtain clustering results; the clustering results include clustering results of the temperature control load data and clustering results of the electric vehicle data.

[0010] According to the basic data of the virtual power plant, the inner approximate constraint space integration method is adopted to determine the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole; the temperature control load cluster is a collection of all temperature control loads, and the adjustable power domain data of the temperature control load cluster as a whole includes the adjustable power domain of the temperature control load cluster as a whole, the power upper limit of the adjustable power domain of the temperature control load cluster as a whole, and the power lower limit of the adjustable power domain of the temperature control load cluster as a whole; the electric vehicle cluster is a collection of all electric vehicles, and the adjustable power domain data of the electric vehicle cluster as a whole includes the adjustable power domain of the electric vehicle cluster as a whole, the power upper limit of the adjustable power domain of the electric vehicle cluster as a whole, and the power lower limit of the adjustable power domain of the electric vehicle cluster as a whole; the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole are used to characterize the overall response characteristics of the temperature control loads and the overall response characteristics of the electric vehicles, respectively.

[0011] A planning function optimization model is established based on the adjustable power domain data of the temperature-controlled load cluster, the adjustable power domain data of the electric vehicle cluster and the clustering results; the planning function optimization model is a scheduling planning model with multiple constraints established with maximizing the peak-shaving capacity of the virtual power plant as the objective function, and the constraints include temperature-controlled load constraints, electric vehicle power and capacity constraints, virtual power plant internal power balance constraints, virtual power plant power purchase from the power grid constraints and virtual power plant controllable load power constraints.

[0012] The planning function optimization model is solved to obtain an optimization strategy result of the virtual power plant; the optimization strategy result includes the optimal operating state of the virtual power plant and the optimal electric vehicle charging and discharging strategy.

[0013] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the virtual power plant optimization scheduling method described in the first aspect.

[0014] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the virtual power plant optimization scheduling method described in the first aspect.

[0015] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the virtual power plant optimization scheduling method described in the first aspect.

[0016] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0017] The present application provides a virtual power plant optimization scheduling method, equipment, medium and product. Starting from the perspective of electric vehicles and temperature control loads, electric vehicles and temperature control loads are regarded as energy regulators of electric energy. The temperature control loads are clustered by a density clustering algorithm. The electric vehicles are clustered by a K-means++ algorithm based on the HHACOA algorithm. The power consumption behavior of different loads is accurately analyzed. The internal approximate constraint space integration method is combined to determine the overall response characteristics of the temperature control load and the electric vehicle. The differentiated processing of complex individuals is simplified, and the scheduling characteristics are unified, so that the power system can achieve efficient regulation with lower computing and communication burdens. It is particularly suitable for large-scale, distributed load scheduling scenarios, and reduces the load on the power system. A planning function optimization model is established by integrating various data such as the adjustable power domain data of the temperature-controlled load cluster, the adjustable power domain data of the electric vehicle cluster and the clustering results. The optimization goal is to maximize the peak-shaving capacity of the virtual power plant. At the same time, it takes into account various constraints such as the temperature-controlled load constraints, the power and capacity constraints of the electric vehicle, the internal power balance constraints of the virtual power plant, the power constraints of the virtual power plant purchased from the power grid and the power constraints of the controllable loads of the virtual power plant. After solving the planning function optimization model, the optimization strategy results of the virtual power plant can be obtained, so that the charging and discharging time of the electric vehicle and the response of the temperature-controlled load can be flexibly adjusted according to the optimization strategy results of the virtual power plant, so as to maximize the balance of the power grid load, effectively improve the virtual power plant's regulation ability on the power grid, and ensure the safety and stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of a virtual power plant optimization scheduling method provided in accordance with an embodiment of the present application.

[0020] Figure 2 A schematic diagram of a virtual power plant optimization scheduling method provided in one embodiment of the present application.

[0021] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] like Figure 1 As shown, this embodiment proposes a virtual power plant optimization scheduling method, which specifically includes the following steps:

[0024] Step S1, obtaining basic data of the virtual power plant. In this embodiment, the basic data of the virtual power plant includes temperature control load data and electric vehicle data, etc. The temperature control load data includes the power consumption behavior data of each temperature control load in the virtual power plant, and the electric vehicle data includes the power consumption behavior data of each electric vehicle in the virtual power plant.

[0025] Step S2, using a density-based spatial clustering of applications with noise (DBSCAN) algorithm to perform cluster analysis on the temperature control load data, and using a K-means++ (improved K-means clustering) algorithm based on a HHACOA (hyper-inspired ant colony optimization) algorithm to perform cluster analysis on the electric vehicle data to obtain clustering results; the clustering results include clustering results of the temperature control load data and clustering results of the electric vehicle data;

[0026] Step S3, according to the basic data of the virtual power plant, adopt the inner approximate constraint space integration method to respectively determine the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole; the temperature control load cluster is a collection of all temperature control loads, and the adjustable power domain data of the temperature control load cluster as a whole includes the adjustable power domain of the temperature control load cluster as a whole, the upper power limit of the adjustable power domain of the temperature control load cluster as a whole, and the lower power limit of the adjustable power domain of the temperature control load cluster as a whole; the electric vehicle cluster is a collection of all electric vehicles, and the adjustable power domain data of the electric vehicle cluster as a whole includes the adjustable power domain of the electric vehicle cluster as a whole, the upper power limit of the adjustable power domain of the electric vehicle cluster as a whole, and the lower power limit of the adjustable power domain of the electric vehicle cluster as a whole; the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole are used to characterize the overall response characteristics of the temperature control load and the overall response characteristics of the electric vehicle respectively;

[0027] Step S4, establishing a planning function optimization model according to the adjustable power domain data of the temperature-controlled load cluster, the adjustable power domain data of the electric vehicle cluster and the clustering result; the planning function optimization model is a scheduling planning model with multiple constraints established with maximizing the peak-shaving capacity of the virtual power plant as the objective function, and the constraints include temperature-controlled load constraints, electric vehicle power and capacity constraints, virtual power plant internal power balance constraints, virtual power plant power purchase from the power grid constraints and virtual power plant controllable load power constraints;

[0028] Step S5, solving the planning function optimization model to obtain the optimization strategy result of the virtual power plant; the optimization strategy result includes the optimal operating state of the virtual power plant and the optimal electric vehicle charging and discharging strategy.

[0029] In order to make the technical solution of this embodiment clearer, the above implementation process of this embodiment is described in detail below in the form of examples.

[0030] This embodiment selects gas turbines and photovoltaics as the main power sources, electric vehicles and temperature control loads as energy regulators, and through information sharing among photovoltaic companies, energy storage companies, electric vehicle aggregators, and temperature control load companies, they are synergistically coupled to participate in power system dispatch. The aggregated control of electric vehicles and the demand response of temperature control loads are the key regulating factors of the virtual power plant, and its optimization strategy specifically includes the following steps:

[0031] Step 1: Obtain basic data of virtual power plant.

[0032] In this embodiment, the basic data of the virtual power plant mainly includes temperature control load data and electric vehicle data, and may also include the existing photovoltaic output data and electricity price data of the virtual power plant. Among them, the temperature control load data includes the power consumption behavior data of each temperature control load in the virtual power plant, and the electric vehicle data includes the power consumption behavior data of each electric vehicle in the virtual power plant, specifically including the electric vehicle charging power curve data and the source-load difference curve data. The power consumption behavior includes charging behavior and / or discharging behavior.

[0033] Step 2: Use the density clustering algorithm to cluster the temperature control load. At the same time, use the K-means++ algorithm based on the HHACOA algorithm (an improved K-means clustering algorithm based on hyper-inspired ant colony optimization) to cluster the electric vehicle power consumption behavior. The HHACOA algorithm is used to optimize the clustering process of the K-means++ algorithm.

[0034] 2.1 Clustering process of density clustering algorithm for temperature control load

[0035] In this embodiment, an area with a relatively dense temperature distribution is selected, and the switch state of the temperature control load is determined according to the density of the temperature. The density clustering algorithm can set the density requirement by itself, and does not need to set the number of clustering groups, and the clustering effect is good. The specific steps of the density clustering algorithm are as follows:

[0036] (1) First determine the temperature radius R and the minimum number of points in the group O min , starting from an arbitrary data point that has not been visited, whether the number of points contained in the circle with this point as the center and R as the radius is greater than or equal to O min , if greater than or equal to O min , then the point is marked as the center point.

[0037] In this embodiment, the temperature radius R refers to the radius of the area where the temperature distribution is relatively dense in the density clustering algorithm, and the minimum number of points in the group is O. min It is a parameter in the density clustering algorithm, which is used to determine whether a cluster is valid. Specifically, in the clustering process of the density clustering algorithm, if the number of points in the neighborhood of a point (i.e., the area with a certain radius r as the range) is greater than or equal to O min , then this point is considered as the center point and can be used to form a cluster. min =20 means that within the radius r = 0.1, if there are at least 20 points, this area is considered to be a dense area and can be used as the cluster center.

[0038] (2) If a temperature point exists within a circle with a certain center point as the radius, then this point is marked as an edge point. Repeat (1) until all points have been visited.

[0039] In this embodiment, taking a certain center point as the radius means that in the density clustering algorithm, once a center point is determined, a circle is drawn with the center point as the center and a preset radius r. All points within the range of this circle are not within the condition of the center point (i.e., the number of points in the neighborhood is less than 0). min ), these points will be marked as edge points.

[0040] According to the state judgment results of the temperature control load in the dense area, the response group is divided. The temperature node can divide the load group into i temperature control load response groups, and each response group is controlled by a temperature setting value. The temperature control load response group and the temperature setting value are one-to-one corresponding, and the temperature control load response group R is obtained. g = {R g,1 ,R g,2 ,…,R g,i}, and its corresponding temperature setting value T s ={T s,1 ,T s,2 ,…,T s,i}.

[0041] 2.2 Clustering process of electric vehicle power consumption behavior using K-means++ algorithm based on HHACOA algorithm

[0042] In this embodiment, the electric vehicle charging power curve data and the source-load difference data in the basic data of the virtual power plant are selected as the characteristic variables of clustering, and the K-means++ algorithm is used to cluster the data sets of the electric vehicle charging power and the source-load difference. In order to further improve the accuracy of clustering, this embodiment combines the HHACOA algorithm with the K-means++ algorithm to form a K-means++ algorithm based on the HHACOA algorithm. The HHACOA algorithm combines the robustness, global search capability and adaptive learning characteristics of the ant colony algorithm, and optimizes the process of cluster center selection and update in the K-means++ algorithm. The robustness of the HHACOA algorithm enables it to maintain high performance when dealing with complex and dynamically changing problems, thereby coping with diverse optimization problems and uncertainties. Through the optimization of the HHACOA algorithm, the K-means++ algorithm can be more accurate in selecting the initial cluster center, thereby improving the quality of the clustering results. According to the optimized clustering results, the data sets corresponding to the electric vehicle charging power curve and the source-load difference curve can be divided into six typical periods: valley period, flat period, early peak period, early peak period, late peak period, and late peak period. The clustering results of electric vehicle charging behavior and virtual power plant source-load difference are further compared, and the electricity consumption period is divided into three periods: overlapping valley period (t1-t2), overlapping peak period (t3-t4) and non-overlapping period (t5-t6). Among them, t1 is the start time of the overlapping valley period, t2 is the end time of the overlapping valley period, t3 is the start time of the overlapping peak period, t4 is the end time of the overlapping peak period, t5 is the start time of the non-overlapping period, and t6 is the end time of the non-overlapping period.

[0043] Step 3: Use the method of inner approximate constraint space integration to describe the overall response characteristics of temperature control load and electric vehicles in the form of constraint space. The integration process mainly includes three steps: benchmark setting, inner approximation and cluster integration. Considering that the averaging method is simple and easy to implement and has a good approximation effect, the benchmark setting is as follows:

[0044]

[0045] Among them, m is the number of individuals, and individuals refer to resource individuals; M i is the parameter matrix and vector of the temperature control load, L i are the parameter matrix and vector of the electric vehicle; M0 and L0 represent the temperature control load and the benchmark value of the electric vehicle in the constraint space, respectively, which are used to characterize the initial constraints or states of the flexibility resources.

[0046] The internal approximation stage mainly achieves the benchmark representation of the differentiated constraint space by translation and scaling. Based on the benchmark setting, the constraint space of different individuals is approximated as follows:

[0047] ψ i = {Y i ∣L0(Y i -θ i )≤ρ i M0}

[0048]

[0049] W i L0=L i

[0050] W i M0≤M i χ i +L i γ i

[0051] Among them, χ i is the scaling factor, χ i =1 / ρ i , ρ i is the scaling factor of individual i; γ i is the translation coefficient, γ i =-x i θ i ,θ i is the translation factor of individual i; ψ i is the approximate constraint space of individual i; Y i is the decision variable of individual i, and the decision variable can represent the charging and discharging power, flexible adjustment capacity, etc. of resources in different time periods. In this embodiment, Y i A collection of state or control variables used to characterize flexibility resources such as electric vehicles or temperature-controlled loads. i is the constraint condition of individual i, usually in the form of a matrix or vector. i It is used to define the constraints of flexible resources in response, including power upper and lower limits, energy storage capacity, ramp rate limit, etc. These constraints limit the dispatch range of resources. i The scaling operation under ,can standardize the constraint space of each resource, which is convenient for ,the subsequent cluster response strategy integration. i Used to adjust the constraint space position of the asset to ensure it is aligned with the base constraint space.

[0052] After completing the inner approximation, the shapes of all individual constraint spaces are the same, so their Minkowski sums can be calculated by direct addition. The mathematical expression is as follows:

[0053]

[0054] Among them, ψ agg Constrained space for temperature-controlled loads or adjustable power for electric vehicles.

[0055] According to the above-used inner approximate constraint space integration method, the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole can be calculated respectively, which can be expressed as:

[0056]

[0057] in, The adjustable power domain of the entire temperature control load cluster, is the adjustable power domain of the i-th category in the temperature control load density clustering result, The lower power limit of the adjustable power domain of the entire temperature control load cluster. It is the upper limit of the power of the adjustable power domain of the entire temperature-controlled load cluster. The adjustable power domain of the entire electric vehicle cluster, is the lower power limit of the adjustable power domain of the entire electric vehicle cluster, It is the power upper limit of the adjustable power domain of the entire electric vehicle cluster.

[0058] Step 4: Establish a planning function optimization model. The model involves the problem of temperature control load and electric vehicles participating in the virtual power plant's aggregate response power, as well as the problem of virtual power plants participating in the day-ahead market's peak load regulation.

[0059] 4.1 Establishing a planning function optimization model

[0060] In this embodiment, the planning function optimization model takes the maximization of the peak-shaving capacity of the virtual power plant as the optimization goal. Since the main members of the virtual power plant, photovoltaic, gas turbine, and energy storage, have been determined, the optimization goals of the planning function optimization model include the maximum peak-shaving capacity after the temperature control load is aggregated, the maximum peak-shaving capacity after the electric vehicle is aggregated and controlled, and the difference between the supply and demand power of the virtual power plant in the day-ahead market. The specific objective function is expressed as:

[0061] minF=F T,t +F ev,t +F m,t

[0062] Among them, F T,t Indicates the maximum peak load regulation capacity after temperature control load aggregation; F ev,t represents the maximum peak load regulation capacity after electric vehicles are aggregated and controlled; F m,t It is the difference between the power supply and demand of the virtual power plant in the day-ahead market.

[0063] (1) Maximum peak load regulation capacity after temperature control load aggregation

[0064] According to existing literature, the maximum peak load regulation capacity of temperature-controlled load operation participating in virtual power plant aggregation can be expressed by the following calculation formula:

[0065]

[0066] Among them, F T,t The maximum peak-shaving capacity after the temperature-controlled loads are aggregated. Specifically, it refers to the maximum peak-shaving capacity after the temperature-controlled loads participate in the aggregate response of the virtual power plant, that is, the peak-to-valley difference. is the lower power limit of the overall adjustable power range of the temperature control load, It is the upper limit of the power of the overall adjustable power range of the temperature control load.

[0067] (2) Maximum peak load-shaving capacity after electric vehicle aggregation control

[0068] In this embodiment, according to the comparative clustering results of the data set of the electric vehicle charging power curve and the source-load difference curve in step 2, the power consumption period is divided into three periods: overlapping valley period (t1-t2), overlapping peak period (t3-t4) and non-overlapping period (t5-t6). For the overlapping valley period (t1-t2), overlapping peak period (t3-t4) and non-overlapping period (t5-t6), the charging and discharging behavior of the electric vehicle is guided by introducing the time-of-use electricity price signal as a whole. The charging power formula of the electric vehicle under the time-of-use electricity price is as follows:

[0069]

[0070] Among them, P ev,t Indicates the charging power of electric vehicles; C t represents the time-of-use electricity price for electric vehicle charging; C p Represents the electricity price during non-overlapping periods.

[0071] This embodiment takes into account that a certain degree of orderly charging can be achieved through price incentives. However, not all car owners will take this initiative. Some electric car owners may not have the flexibility or willingness to change charging modes according to price fluctuations, which limits the effectiveness of price incentives. Therefore, it is necessary to combine V2G technology to control the overlapping peak period and encourage electric vehicles to discharge reversely to the grid during this period.

[0072] This embodiment uses time-of-use electricity prices to provide price incentives to electric vehicle owners, and combines V2G technology. According to the electricity prices of electric vehicles at different times, the maximum peak load-shaving capacity after the aggregate control of electric vehicles can be obtained as follows:

[0073]

[0074] Among them, F ev,t represents the maximum peak-shaving capacity after the electric vehicle aggregation control; C1 is the charging and discharging power price of electric vehicles during overlapping valley periods; C2 is the charging and discharging power price of electric vehicles during overlapping peak periods; P ev,4Reverse charging power for electric vehicles during overlapping peak periods.

[0075] (3) The difference between the power supply and demand of the virtual power plant in the day-ahead market

[0076] The difference between the power supply and demand of the virtual power plant in the day-ahead market can be expressed as the power purchased by the virtual power plant minus the power sold by the virtual power plant. The mathematical expression for the difference between the power supply and demand of the virtual power plant in the day-ahead market is:

[0077]

[0078] Among them, F m,t P represents the difference between the power supply and demand of the virtual power plant in the day-ahead market. b,t P represents the power purchased by the virtual power plant from the grid during the dispatch period t; s,t Represents the power sold by the virtual power plant to the grid during the scheduling period t.

[0079] 4.2 Constraints

[0080] (1) Temperature control load constraints

[0081] In this embodiment, the indoor temperature constraint can be expressed as:

[0082] T min ≤T in ≤T max

[0083] Among them, T in is the indoor temperature at time t; T min is the minimum allowable value of indoor temperature; T max It is the maximum allowable value of indoor temperature.

[0084] In this embodiment, the cooling balance equation can be expressed as:

[0085] Cd t =Cd m,t -Cd s,t +Cd d,t

[0086] Among them, Cd t is the cooling demand at time t; Cd m,t Cd is the cooling capacity of the refrigeration unit at time t; s,t is the cooling capacity at time t; Cd d,t is the cooling amount at time t.

[0087] In this embodiment, the air conditioner is selected as the temperature control load, and the cold storage tank refers to the cold storage tank in the air conditioner, which is a key component for storing and releasing cold energy. The air conditioner is used as the temperature control load, and the cold energy is generated by the chiller of the air conditioner, and the excess cold energy is stored in the cold storage tank.

[0088] In this embodiment, the cold storage tank capacity update equation can be expressed as:

[0089]

[0090] Among them, S T,t is the capacity of the cold storage tank at time t; S T,t-1 is the cold storage tank capacity at time t-1; ε s is the efficiency of the cold storage process, and its value range is [0, 1]; ε d is the efficiency of the cooling process, and its value range is [0, 1].

[0091] In this embodiment, the temperature control load power consumption equation can be expressed as:

[0092]

[0093] Among them, P T,t is the temperature control load power at time t; m is the refrigeration efficiency of the refrigeration unit; s is the unit power consumption of cold storage; d The unit power consumption for cooling.

[0094] (2) Electric vehicle power and capacity constraints

[0095] In this embodiment, the electric vehicle power and capacity constraints can be expressed as:

[0096]

[0097] Among them, S ev,t S is the battery capacity of the electric vehicle at time t; ev,t-1 is the battery capacity of the electric vehicle at time t-1; and are the maximum charging power and maximum discharging power of electric vehicles respectively; c and d are the charging efficiency and discharging efficiency of electric vehicles, respectively, with a value range of [0, 1]; d ev is the driving distance of the electric vehicle; ev is the battery loss coefficient of electric vehicles; represents the discharge power of electric vehicles in the virtual power plant during the dispatch period t; Represents the charging power of electric vehicles in the virtual power plant during the scheduling period t.

[0098] (3) Internal power balance constraints of virtual power plants

[0099] In this embodiment, the internal power balance constraint of the virtual power plant can be expressed as:

[0100]

[0101] Among them, P pv,t represents the output power of photovoltaic power in the virtual power plant during the scheduling period t; represents the discharge power of the energy storage in the virtual power plant during the dispatch period t; represents the discharge power of electric vehicles in the virtual power plant during the dispatch period t; P gt,t represents the output power of photovoltaic power in the virtual power plant during the scheduling period t; represents the charging power of the energy storage in the virtual power plant during the scheduling period t; represents the charging power of electric vehicles in the virtual power plant during the scheduling period t; is the power of the controllable load in the dispatching period t, represents the demand response power of the controllable load in the dispatch period t; P b,t P represents the power purchased by the virtual power plant from the grid during the dispatch period t; s,t P represents the power sold by the virtual power plant to the grid during the dispatch period t; T,t is the temperature control load power at time t.

[0102] (4) Constraints on the power purchased by virtual power plants from the grid

[0103] In this embodiment, the power constraint of the virtual power plant purchased from the power grid can be expressed as:

[0104]

[0105] in, is the maximum power purchased from the grid during the virtual power plant dispatch period t, P b,t It represents the power purchased by the virtual power plant from the power grid during the dispatch period t.

[0106] (5) Power Constraints for Controllable Loads in Virtual Power Plants

[0107] In this embodiment, the power consumption constraint of the controllable load of the virtual power plant can be expressed as:

[0108]

[0109] in, is the power of the controllable load in the dispatching period t; and are the minimum power and maximum power of the controllable load in the scheduling period t respectively.

[0110] Step 5: Plan the solution of the function optimization model.

[0111] This embodiment establishes a planning function optimization model with maximizing the peak-shaving capacity of the virtual power plant as the objective function, and uses the GUROBI (a new generation of large-scale mathematical programming optimizer developed by GUROBI) solver to solve the planning function optimization model. Before solving the planning function optimization model, the density clustering algorithm is first used to cluster the temperature control load to generate multiple response clusters, and the K-means++ algorithm based on the HHACOA algorithm is used to cluster the charging power and source-load difference of the electric vehicle to generate the charging and discharging behavior of different time periods; secondly, the method of internal approximate constraint space integration is used to integrate the power response domain of the temperature control load and the electric vehicle to unify the response characteristics; finally, the GUROBI solver is used to solve the planning function optimization model. When the optimization process reaches the maximum number of iterations, that is, the number of iterations j = J max When , the optimal operating state of the virtual power plant and the optimal electric vehicle charging and discharging strategy can be solved. The optimal operating state refers to the optimal operating state of each temperature control load and other equipment in the virtual power plant. The optimal electric vehicle charging and discharging strategy refers to the optimal strategy for each electric vehicle in the virtual power plant to charge or discharge at different times. The process is as follows Figure 2 shown.

[0112] Due to the rapid development of new energy, the large-scale access of wind power and photovoltaics has challenged the balancing capacity of the power grid. How to better play the role of regulation with the help of the coordinated coupling of energy storage devices and controllable loads is a problem that must be solved to meet the peak-shaving demand. This embodiment aims at the characteristics of the large number, small capacity and wide distribution of temperature-controlled loads and electric vehicles in virtual power plants, and separate regulation will generate a lot of communication and computing burden problems. A large number of temperature-controlled loads and electric vehicles are clustered according to their indicators, and the inner approximate constraint space integration method is used to aggregate them according to the clustering results. When participating in power dispatching, the virtual power plant optimizes the dispatch of two resources (temperature-controlled loads and electric vehicles) by introducing time-of-use electricity price signals and the aggregation feasible domain range, and establishes a planning function optimization model that takes into account the aggregation of electric vehicles and temperature-controlled loads for virtual power plant peak-shaving optimization dispatching.

[0113] As virtual power plants gradually become a key element in the development of future power grids, they have shown great potential in promoting energy transformation and achieving green and low-carbon goals. In virtual power plants, temperature-controlled loads and electric vehicles, as important controllable resources, can improve the stability of virtual power plants by flexibly adjusting power demand. However, the current scheduling and management of these resources has the problem of excessive communication and computing burdens, especially in the case of wide distribution and small capacity, it is difficult to achieve efficient operation of the system by separate regulation. This embodiment optimizes the aggregate scheduling of resources, improves the peak-shaving and valley-filling capabilities of virtual power plants and the grid regulation capabilities, and ensures that virtual power plants play a greater role in balancing grid supply and demand and stabilizing grid operation, thereby enhancing the safety and sustainability of the power system.

[0114] On the one hand, this embodiment clusters the temperature control load through the density clustering algorithm, and clusters the charging power of electric vehicles and the source-load difference through the K-means++ algorithm based on the HHACOA algorithm, accurately analyzes the power consumption behavior of different loads, and reasonably divides the power use period. By introducing the time-of-use electricity price incentive mechanism, car owners are encouraged to charge during the off-peak period, and by increasing the electricity price during the peak period, combined with V2G technology, the reverse discharge of electric vehicles is realized, helping the power grid to reduce the peak load, and the off-peak power resources can be utilized, and the load of the power grid at peak time is balanced, effectively improving the flexibility and stability of the power grid. Compared with the traditional scheduling scheme, it greatly optimizes the overall operation efficiency of the power grid and solves the problem of imbalance between power supply and demand. On the other hand, this embodiment classifies the dispersed electric vehicles and temperature control loads according to the response capability through the aggregation scheduling strategy, and adopts the unified group control, which reduces the complexity of individual control and the real-time communication volume. Combined with the inner approximate constraint space integration method, the differentiated processing of complex individuals is further simplified, and the scheduling characteristics are unified, so that the power system can achieve efficient control with lower computing and communication burdens, which is particularly suitable for large-scale, distributed load scheduling scenarios, reducing the load on the power system. On the other hand, this embodiment optimizes the dispatching strategy of the virtual power plant, by flexibly adjusting the charging and discharging time of electric vehicles and the response of temperature-controlled loads, balancing the load of the power grid to the maximum extent, making full use of the energy storage and V2G technology of electric vehicles, discharging during peak power demand periods to reduce loads, and charging during valley periods to smooth the load curve. The coordinated dispatching of temperature-controlled loads and electric vehicles further improves the stability and flexibility of the power grid, and effectively addresses the volatility of renewable energy generation.

[0115] This embodiment is applicable to a virtual power plant environment including multiple electric vehicles and temperature-controlled loads. By constructing a front-to-back joint planning model, the clustering of temperature-controlled loads and electric vehicles and the solution of the power response domain are solved, and a basis is provided for the subsequent peak-shaving and valley-filling scheduling. By determining the optimal control strategy of the virtual power plant combined with the temperature-controlled load and electric vehicles under a given response domain, the peak-shaving and valley-filling capacity of the virtual power plant is maximized, which not only meets the needs of temperature-controlled loads and electric vehicle users, but also provides a scientific basis for the efficient operation of the virtual power plant. By introducing the K-means++ algorithm and combining it with the HHACOA algorithm to optimize the clustering process of the K-means++ algorithm, a K-means++ algorithm based on the HHACOA algorithm is formed to identify the charging power curve of the electric vehicle and the power consumption behavior of the electric vehicle in the source-load difference of the virtual power plant. The HHACOA algorithm optimizes the initial clustering center selection and update process in the clustering of the K-means++ algorithm, thereby improving the accuracy of the clustering results. The clustering results divide the charging behavior of electric vehicles into six typical periods: valley period, flat period, early peak period, early peak period, late peak period and late peak period. The clustering results of the charging curve of electric vehicles and the source-load difference curve of the virtual power plant are compared on the same time scale, and further classified into overlapping valley period, overlapping peak period, non-overlapping period and other periods. This improved clustering analysis provides a more accurate basis for subsequent time-of-use electricity price strategies and peak-shaving and valley-filling scheduling schemes. Compared with the traditional method of identifying electricity consumption behavior, this embodiment can more accurately characterize the charging mode of electric vehicles, improve the regulation efficiency of the charging and discharging behavior of electric vehicles, and reduce the computational complexity, ensuring the flexibility and reliability of the scheduling strategy.

[0116] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and an input / output interface connected through a system bus, and a communication interface is connected to the system bus through an input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store virtual power plant optimization scheduling data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a virtual power plant optimization scheduling method is implemented.

[0117] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0118] In an exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned virtual power plant optimization scheduling method are implemented.

[0119] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the steps in the above-mentioned virtual power plant optimization scheduling method.

[0120] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the steps in the above-mentioned virtual power plant optimization scheduling method when executed by a processor.

[0121] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0122] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile 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 may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0123] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0125] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A virtual power plant optimization scheduling method, characterized in that: The virtual power plant optimization scheduling method comprises: Acquire basic data of a virtual power plant; the basic data of the virtual power plant includes temperature control load data and electric vehicle data, the temperature control load data includes power consumption behavior data of each temperature control load in the virtual power plant, and the electric vehicle data includes power consumption behavior data of each electric vehicle in the virtual power plant; A density clustering algorithm is used to perform cluster analysis on the temperature control load data, and a K-means++ algorithm based on the HHACOA algorithm is used to perform cluster analysis on the electric vehicle data to obtain clustering results; the clustering results include clustering results of the temperature control load data and clustering results of the electric vehicle data; According to the basic data of the virtual power plant, the inner approximate constraint space integration method is adopted to respectively determine the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole; the temperature control load cluster is a collection of all temperature control loads, and the adjustable power domain data of the temperature control load cluster as a whole includes the adjustable power domain of the temperature control load cluster as a whole, the upper power limit of the adjustable power domain of the temperature control load cluster as a whole, and the lower power limit of the adjustable power domain of the temperature control load cluster as a whole; the electric vehicle cluster is a collection of all electric vehicles, and the adjustable power domain data of the electric vehicle cluster as a whole includes the adjustable power domain of the electric vehicle cluster as a whole, the upper power limit of the adjustable power domain of the electric vehicle cluster as a whole, and the lower power limit of the adjustable power domain of the electric vehicle cluster as a whole; the adjustable power domain data of the temperature control load cluster as a whole and the adjustable power domain data of the electric vehicle cluster as a whole are used to characterize the overall response characteristics of the temperature control load and the overall response characteristics of the electric vehicle respectively; A planning function optimization model is established according to the adjustable power domain data of the temperature-controlled load cluster, the adjustable power domain data of the electric vehicle cluster and the clustering result; the planning function optimization model is a scheduling planning model with multiple constraints established with maximizing the peak-shaving capacity of the virtual power plant as the objective function, and the constraints include temperature-controlled load constraints, electric vehicle power and capacity constraints, virtual power plant internal power balance constraints, virtual power plant power purchase from the power grid constraints and virtual power plant controllable load power constraints; The planning function optimization model is solved to obtain an optimization strategy result of the virtual power plant; the optimization strategy result includes the optimal operating state of the virtual power plant and the optimal electric vehicle charging and discharging strategy.

2. The virtual power plant optimization scheduling method according to claim 1 is characterized in that: The following formula is used to represent the adjustable power domain data of the entire temperature control load cluster: in, The adjustable power domain of the entire temperature control load cluster, is the adjustable power domain of the i-th category in the temperature control load density clustering result, The lower power limit of the adjustable power domain of the entire temperature control load cluster. The power upper limit of the adjustable power domain of the entire temperature control load cluster; The following formula is used to represent the adjustable power domain data of the entire electric vehicle cluster: in, The adjustable power domain of the entire electric vehicle cluster, is the lower power limit of the adjustable power domain of the entire electric vehicle cluster, It is the power upper limit of the adjustable power domain of the entire electric vehicle cluster.

3. The virtual power plant optimization scheduling method according to claim 1, characterized in that: The objective function of the planning function optimization model is: minF=F T,t +F ev,t +F m,t ; Among them, F T,t Indicates the maximum peak load regulation capacity after temperature control load aggregation; F ev,t represents the maximum peak load regulation capacity after electric vehicles are aggregated and controlled; F m,t It is the difference between the power supply and demand of the virtual power plant in the day-ahead market.

4. The virtual power plant optimization scheduling method according to claim 1, characterized in that: The expression of the temperature control load constraint is: T min ≤T in ≤T max ; CD t =Cd m,t -Cd s,t +Cd d,t ; Among them, T in is the indoor temperature at time t; T min is the minimum allowable value of indoor temperature; T max is the maximum allowable value of indoor temperature; Cd t is the cooling demand at time t; Cd m,t Cd is the cooling capacity of the refrigeration unit at time t; s,t is the cooling capacity at time t; Cd d,t is the cooling capacity at time t, S T,t is the capacity of the cold storage tank at time t; S T,t-1 is the cold storage tank capacity at time t-1; ε s is the efficiency of the cold storage process; d is the efficiency of the cooling process; P T,t is the temperature control load power at time t; m is the refrigeration efficiency of the refrigeration unit; s is the unit power consumption of cold storage; d The unit power consumption for cooling.

5. The virtual power plant optimization scheduling method according to claim 1, characterized in that: The expression of the electric vehicle power and capacity constraints is: Among them, S ev,t S is the battery capacity of the electric vehicle at time t; ev,t-1 is the battery capacity of the electric vehicle at time t-1; and are the maximum charging power and maximum discharging power of electric vehicles respectively; c and d are the charging and discharging efficiency of electric vehicles respectively; d ev is the driving distance of the electric vehicle; ev is the electric vehicle battery loss coefficient; represents the discharge power of electric vehicles in the virtual power plant during the dispatch period t; Represents the charging power of electric vehicles in the virtual power plant during the scheduling period t.

6. The virtual power plant optimization scheduling method according to claim 1, characterized in that: The expression of the internal power balance constraint of the virtual power plant is: Among them, P pv,t represents the output power of photovoltaic power in the virtual power plant during the scheduling period t; represents the discharge power of the energy storage in the virtual power plant during the dispatch period t; represents the discharge power of electric vehicles in the virtual power plant during the dispatch period t; P gt,t represents the output power of photovoltaic power in the virtual power plant during the scheduling period t; represents the charging power of the energy storage in the virtual power plant during the scheduling period t; represents the charging power of electric vehicles in the virtual power plant during the scheduling period t; is the power of the controllable load in the dispatching period t, represents the demand response power of the controllable load in the dispatch period t; P b,t P represents the power purchased by the virtual power plant from the grid during the dispatch period t; s,t P represents the power sold by the virtual power plant to the grid during the dispatch period t; T,t is the temperature control load power at time t.

7. The virtual power plant optimization scheduling method according to claim 1, characterized in that: The expression of the power constraint of the virtual power plant purchased from the power grid is: in, is the maximum power purchased from the grid during the virtual power plant dispatch period t, P b,t represents the power purchased by the virtual power plant from the grid during the dispatch period t; The expression of the power consumption constraint of the controllable load of the virtual power plant is: in, is the power of the controllable load in the dispatching period t; and are the minimum power and maximum power of the controllable load in the scheduling period t respectively.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the virtual power plant optimization scheduling method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the virtual power plant optimization scheduling method described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the virtual power plant optimization scheduling method described in any one of claims 1 to 7 is implemented.

Images