Controllable load clustering method and system supporting equilibrium calculation

Abstract

The invention discloses a controllable load clustering method and system supporting equilibrium calculation, and the method comprises the steps: carrying out the processing of a typical controllable load, and building a controllable load physical model for describing the power utilization characteristics; in consideration of time use requirements of power consumers on the controllable load physical model, abstracting power utilization characteristics of the controllable load, and establishing a multi-type controllable load model considering the power utilization characteristics; aiming at the multi-type controllable load model considering the power utilization characteristics, establishing l-dimensional power utilization characteristic data as a clustering object; a k-means algorithm is adopted to perform clustering analysis on the l-dimensional electricity utilization characteristic data of the mass controllable loads; and according to the class controllable loads obtained by clustering, analyzing conditions satisfied when the class controllable loads with the interaction relationship reach an equilibrium state, and using the conditions for subsequent equilibrium calculation. The system comprises a model establishing module, a model processing module, a clustering analysis module and a condition analysis module. The method lays a foundation for bottom mass controllable loads to participate in demand side management.

Description

Technical Field

[0001] The present invention belongs to the field of electric power systems, and in particular relates to a controllable load clustering method and system supporting balanced calculation. Background Art

[0002] Building a new power system under the background of energy transformation faces challenges. The increasing proportion of renewable energy and the rapid growth of new loads such as electric vehicles have further aggravated the maximum daily fluctuation of renewable energy and widened the maximum peak-to-valley difference of load. However, the regulation capacity of conventional power sources is limited, and it is difficult to ensure the safe and stable operation of the power system. To this end, it is necessary to tap the regulation potential of load-side resources and enable users to deeply participate in system balance. Residential loads are large in scale, growing rapidly, and highly intelligent. They are an important supplement to demand response dominated by large industrial and commercial loads, and an important basis for supporting the interaction between supply and demand.

[0003] However, the single capacity of residential controllable loads is small, the number is large, the types are diverse, and the distribution is scattered. There is a problem of random response, which makes it difficult for the dispatch center to obtain its power consumption. Therefore, it is difficult for residential power loads to directly participate in demand-side management. With the development of smart terminals and communication technologies for power users, the power system has a large amount of basic power consumption data for users. Therefore, most existing studies use data mining to cluster power load curves, starting from the overall power consumption data of users, or directly clustering the user load curves, or indirectly using data dimensionality reduction technology and time series analysis to extract key features of load curves based on the high dimensionality of massive user load curves, and further clustering analysis to reflect the power consumption behavior characteristics of users of the same type and realize the classification of power users. However, using statistical methods to analyze the overall power consumption data of users, extending from the space, and considering the power consumption cluster behavior of users, it is impossible to ensure that the physical level meets the controllable load operation when implementing demand response decisions for residential controllable loads. Therefore, in order to ensure the feasibility of the control layer's participation in demand response, a controllable load clustering method that supports balanced calculation is proposed. The controllable load terminal equipment is taken as the research object, and a mathematical model of the power consumption characteristics of typical controllable terminal equipment is constructed. Further, based on the equipment operation characteristics and the characteristics of user usage needs, the controllable characteristics of the terminal equipment are abstracted to form a multi-type controllable load model that takes into account the power consumption characteristics, and a clustering analysis is performed on massive and multi-type controllable loads. Finally, according to the clustering results obtained based on the load characteristics, the equilibrium state finally reached by the same type of controllable loads in the interaction is analyzed, and the equilibrium conditions based on categories are constructed to provide a basis for the subsequent calculation of the equilibrium state.

[0004] In summary, cluster analysis of power loads is the basis for demand-side management and energy efficiency management of future new power systems. However, most existing studies focus on data mining, which is often separated from the control layer of controllable loads and cannot determine the power consumption behavior of the underlying controllable loads participating in demand response. Summary of the invention

[0005] The purpose of the present invention is to address the problem of separation between the existing clustering methods and the control layer of controllable loads. Starting from the physical operating characteristics of typical controllable loads, a mathematical model that describes their power consumption characteristics is constructed, and the controllable characteristics of massive equipment are further abstracted to form a multi-type controllable load model. In order to support efficient modeling of massive controllable load resources, a controllable load clustering method and system that supports balanced calculation is provided to describe the power consumption characteristics of controllable loads of the same type, laying the foundation for the underlying massive controllable loads to participate in demand-side management.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A controllable load clustering method supporting balanced computing includes: Process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics; Considering the time requirements of power users for the physical model of controllable loads, the power consumption characteristics of controllable loads are abstracted, and multi-type controllable load models taking into account power consumption characteristics are established; A multi-type controllable load model considering power consumption characteristics is established. l The characteristic data of electricity consumption is used as the clustering object; use k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; According to the controllable load categories obtained by clustering, the conditions satisfied when the controllable loads of the same category with interactive relationships reach a balanced state are analyzed for subsequent balanced calculations.

[0007] A further improvement of the present invention is to process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics, including: Electricity users have a variety of controllable loads. For electric vehicles, the user's arrival time, departure time, upper and lower limits of charging power, and total power consumption are considered. (1) in, H represents the full computation cycle; H e is the allowed charging time of the electric vehicle, outside which the charging power of the electric vehicle is 0; p e,h Indicates electric vehicle e exist h The power consumption at time [ p e,min , p e,max ] is the charging power range of electric vehicles, p e,minrepresents the minimum charging power of electric vehicles, p e,max Indicates the maximum charging power of the electric vehicle; [ E e,min , E e,max ] is the total power consumption range of electric vehicles, E e,min represents the minimum power consumption of electric vehicles, E e,max Indicates the maximum power consumption of an electric vehicle.

[0008] A further improvement of the present invention is that, considering the time usage requirements of power users for the controllable load physical model, the power consumption characteristics of the controllable load are abstracted, and a multi-type controllable load model taking into account the power consumption characteristics is established, including: (2) (3) (4) in, Indicates electric vehicle e In time h The state variable represents whether the electric vehicle is allowed to charge; Further abstract the electric vehicle power consumption characteristics to obtain the power consumption characteristic data to be clustered. (5) in For electric vehicles e State variables during the full computation cycle; For electric vehicles e The minimum power state sequence; For electric vehicles e Maximum power state sequence.

[0009] A further improvement of the present invention is to establish a multi-type controllable load model taking into account power consumption characteristics. l The power consumption characteristic data is used as clustering objects, including: (6) Using a partition-based clustering algorithm k-means Algorithm for massive controllable loads l Cluster analysis is performed on the power consumption characteristic data to select different load clusters according to the size of the controllable load. K , K <N , find a partition ( S k ) 1≤k≤K Divide the load into K cluster (7) in Represents load cluster S k The cluster center after clustering k Power consumption characteristics of load types ; N is the number of controllable loads.

[0010] A further improvement of the present invention is that, according to the controllable load categories obtained by clustering, the conditions satisfied when the controllable loads of the same category with interactive relationships reach a balanced state are analyzed for subsequent balanced calculations, including: (8) (9) in is the indicator function, when hour, ,otherwise ; It represents the feasible operation domain of the load generated by the power consumption feature mapping, that is, each controllable load must meet the requirements of its category. k The feasible operating domain; represents the electricity price function mapped from load behavior; Indicates controllable load a electricity costs; When equilibrium exists and is achieved, the electricity cost of each load reaches the minimum, that is, no load can further optimize its results by changing its own electricity strategy, satisfying the following equilibrium conditions, (10) (11) (12) in Indicates controllable load a The optimal electricity consumption plan under equilibrium state; yes k The set of optimal power consumption plans under the controllable load balancing state is a finite set; yes k Type of controllable load selection j The electricity cost of each electricity consumption plan; express k Type of controllable load selection j Number of electricity use options; express k The number of controllable loads.

[0011] A controllable load clustering system supporting balanced computing, comprising: The first model building module processes typical controllable loads and builds a controllable load physical model that describes power consumption characteristics; The second model building module considers the time usage requirements of the controllable load physical model by the power users, abstracts the power consumption characteristics of the controllable load, and builds a multi-type controllable load model taking into account the power consumption characteristics; Model processing module, for multi-type controllable load models taking into account power consumption characteristics, establish l The characteristic data of electricity consumption is used as the clustering object; Cluster analysis module, using k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; The condition analysis module analyzes the conditions that are satisfied when similar controllable loads with interactive relationships reach a balanced state based on the controllable load categories obtained by clustering, which is used for subsequent balanced calculations.

[0012] A further improvement of the present invention is to process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics, including: Electricity users have a variety of controllable loads. For electric vehicles, the user's arrival time, departure time, upper and lower limits of charging power, and total power consumption are considered. (1) in, H represents the full computation cycle; H e is the allowed charging time of the electric vehicle, outside which the charging power of the electric vehicle is 0; p e,h Indicates electric vehicle e exist h The power consumption at time [ p e,min , p e,max ] is the charging power range of electric vehicles, p e,min represents the minimum charging power of electric vehicles, p e,max Indicates the maximum charging power of the electric vehicle; [ E e,min , E e,max ] is the total power consumption range of electric vehicles, E e,min represents the minimum power consumption of electric vehicles, E e,max Indicates the maximum power consumption of an electric vehicle.

[0013] A further improvement of the present invention is that, considering the time usage requirements of power users for the controllable load physical model, the power consumption characteristics of the controllable load are abstracted, and a multi-type controllable load model taking into account the power consumption characteristics is established, including: (2) (3) (4) in, Indicates electric vehicle e In time h The state variable represents whether the electric vehicle is allowed to charge; Further abstract the electric vehicle power consumption characteristics to obtain the power consumption characteristic data to be clustered. (5) in For electric vehicles e State variables during the full computation cycle; For electric vehicles e The minimum power state sequence; For electric vehicles e Maximum power state sequence.

[0014] A further improvement of the present invention is to establish a multi-type controllable load model taking into account power consumption characteristics. l The power consumption characteristic data is used as clustering objects, including: (6) Using a partition-based clustering algorithm k-means Algorithm for massive controllable loads l Cluster analysis is performed on the power consumption characteristic data to select different load clusters according to the size of the controllable load. K , K <N , find a partition ( S k ) 1≤k≤K Divide the load into K cluster (7) in Represents load cluster S k The cluster center after clustering k Power consumption characteristics of load types ; N is the number of controllable loads.

[0015] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of a controllable load clustering method supporting balanced calculation.

[0016] Compared with the prior art, the present invention has at least the following beneficial technical effects: The present invention starts from the operating characteristics of controllable loads and user usage requirements. First, by considering the physical characteristics of load operation, a controllable load physical model describing the operating characteristics is established. Further, considering the usage requirements of controllable loads, a multi-type controllable load model is established. Finally, power consumption feature data is extracted as a clustering object. k-means The algorithm implements cluster analysis of multiple types of controllable loads, and the obtained clustering results can be used to construct class-based equilibrium conditions. Compared with the existing traditional load clustering methods based on big data, the present invention solves the problem that the traditional controllable load clustering method is separated from the control layer of the controllable load, cannot consider the operating characteristics of the controllable load, and has high computational complexity, and provides an effective quantitative reference for the next step of considering the impact of load response on electricity prices. The equilibrium state calculation of massive controllable loads provides an effective quantitative reference. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a controllable load clustering method supporting balanced calculation according to the present invention; Figure 2 is the relationship diagram between the effectiveness index and the number of clusters; Figure 3 This is a structural block diagram of a controllable load clustering system supporting balanced calculations according to the present invention. DETAILED DESCRIPTION

[0018] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0019] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0020] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0021] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0022] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0023] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Example 1 like Figure 1 As shown, the present invention provides a controllable load clustering method supporting balanced calculation, including: Step 1: Process typical controllable loads and establish a controllable load physical model that describes power consumption characteristics; Step 2: Consider the time usage requirements of power users for the physical model of controllable loads, abstract the power consumption characteristics of controllable loads, and establish a multi-type controllable load model taking into account the power consumption characteristics; Step 3: Establish a multi-type controllable load model taking into account power consumption characteristics l The characteristic data of electricity consumption is used as the clustering object; Step 4: Adoption k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; Step 5: According to the controllable load categories obtained by clustering, analyze the conditions that the controllable loads of the same category with interactive relationships meet when they reach a balanced state, which will be used for subsequent balanced calculations.

[0025] In this embodiment, in step 1, there are multiple controllable loads for power users. For electric vehicles, the user's arrival time, departure time, upper and lower limits of charging power, and total power consumption are considered. (1) in,H represents the full computation cycle; H e is the allowed charging time of the electric vehicle, outside which the charging power of the electric vehicle is 0; p e,h Indicates electric vehicle e exist h The power consumption at time [ p e,min , p e,max ] is the charging power range of electric vehicles, p e,min represents the minimum charging power of electric vehicles, p e,max Indicates the maximum charging power of the electric vehicle; [ E e,min , E e,max ] is the total power consumption range of electric vehicles, E e,min represents the minimum power consumption of electric vehicles, E e,max Indicates the maximum power consumption of an electric vehicle.

[0026] In this embodiment, step 2, taking an electric car as an example, includes: (2) (3) (4) in, Indicates electric vehicle e In time h The state variable represents whether the electric vehicle is allowed to charge; Further abstract the electric vehicle power consumption characteristics to obtain the power consumption characteristic data to be clustered. (5) in For electric vehicles e State variables during the full computation cycle; For electric vehicles e The minimum power state sequence; For electric vehicles e Maximum power state sequence.

[0027] Step three specifically includes: (6) Using a partition-based clustering algorithm k-means Algorithm for massive controllable loads lCluster analysis is performed on the power consumption characteristic data to select different load clusters according to the size of the controllable load. K ( K <N ), find a partition ( S k ) 1≤k≤K Divide the load into K cluster (7) in Represents load cluster S k The cluster center after clustering k Power consumption characteristics of load types .

[0028] Step 5: Specifically include: According to the clustering results, the equilibrium condition based on the category is constructed. Considering the impact of load response on electricity price, the controllable load forms a game relationship in order to pursue the lowest electricity cost. (8) (9) in is the indicator function, when hour, ,otherwise ; It represents the feasible operation domain of the load generated by the power consumption feature mapping, that is, each controllable load must meet the requirements of its category. k The feasible operating domain; represents the electricity price function mapped from load behavior; Indicates controllable load a electricity cost.

[0029] When equilibrium exists and is achieved, the electricity cost of each load reaches the minimum, that is, no load can further optimize its results by changing its own electricity strategy, satisfying the following equilibrium conditions, (10) (11) (12) in Indicates controllable load a The optimal electricity consumption plan under equilibrium state; yes k The set of optimal power consumption plans under the controllable load balancing state is a finite set; yes k Type of controllable load selection j The electricity cost of each electricity consumption plan; express k Type of controllable load selection j Number of electricity use options; express k The number of controllable loads.

[0030] Example 2 Get the controllable load data to be clustered N , preprocessed to obtain l The preprocessing is to describe the physical characteristics of the controllable load and establish a multi-type controllable load model based on the load usage requirements. k-means Clustering step: Setting the number of clusters n and convergence criteria, and randomly select n indivual l The characteristic data of electricity consumption is taken as the cluster center, denoted as .set up t = 0, 1, 2, … is the number of iterations, repeat the following steps until the convergence criterion is met: 1) For each l Dimensional electricity consumption feature data, calculate the Euclidean distance to all cluster centers, and assign it to the nearest center ,in Indicates i The class to which the samples belong, each The value range is 1 to n ; 2) For each class n , recalculate the cluster center of this class .

[0031] The sum of squared error (SSE) is used to judge the effectiveness of the clustering method. SSE Represents the sum of the Euclidean distances of all samples to the cluster center of their class: (13) As the number of clusters increases, SSE will gradually decrease, and after the inflection point SSE The reduction becomes smaller, so the inflection point is selected as the optimal number of clusters.

[0032] Considering 2000 controllable load data, the number of clusters is set from 5 to 25. SSE Indicators such as Figure 1 As shown. Figure 2 It can be seen that the number of clusters n =19 is the inflection point of the SSE curve, so the optimal number of clusters is 19. Furthermore, the class-based equilibrium condition can be constructed according to the clustering results.

[0033] Example 3 like Figure 3 As shown, the present invention provides a controllable load clustering system supporting balanced computing, including: The first model building module processes typical controllable loads and builds a controllable load physical model that describes power consumption characteristics; The second model building module considers the time usage requirements of the controllable load physical model by the power users, abstracts the power consumption characteristics of the controllable load, and builds a multi-type controllable load model taking into account the power consumption characteristics; Model processing module, for multi-type controllable load models taking into account power consumption characteristics, establish l The characteristic data of electricity consumption is used as the clustering object; Cluster analysis module, using k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; The condition analysis module analyzes the conditions that are satisfied when similar controllable loads with interactive relationships reach a balanced state based on the controllable load categories obtained by clustering, which is used for subsequent balanced calculations.

[0034] Example 4 The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the controllable load clustering method supporting balanced calculation are implemented.

[0035] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0036] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0037] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0038] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0039] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0040] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A controllable load clustering method supporting balanced computing, characterized in that: include: Process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics; Considering the time requirements of power users for the physical model of controllable loads, the power consumption characteristics of controllable loads are abstracted, and multi-type controllable load models taking into account power consumption characteristics are established; A multi-type controllable load model considering power consumption characteristics is established. l The characteristic data of electricity consumption is used as the clustering object; use k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; According to the controllable load categories obtained by clustering, the conditions satisfied when the controllable loads of the same category with interactive relationships reach a balanced state are analyzed for subsequent balanced calculations.

2. A controllable load clustering method supporting balanced calculation according to claim 1, characterized in that: Process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics, including: Electricity users have a variety of controllable loads. For electric vehicles, the user's arrival time, departure time, upper and lower limits of charging power, and total power consumption are considered. (1) in, H represents the full computation cycle; H e is the allowed charging time of the electric vehicle, outside which the charging power of the electric vehicle is 0; p e,h Indicates electric vehicle e exist h The power consumption at time [ p e,min , p e,max ] is the charging power range of electric vehicles, p e,min represents the minimum charging power of electric vehicles, p e,max Indicates the maximum charging power of the electric vehicle; [ E e,min , E e,max ] is the total power consumption range of electric vehicles, E e,min represents the minimum power consumption of electric vehicles, E e,max Indicates the maximum power consumption of an electric vehicle.

3. A controllable load clustering method supporting balanced calculation according to claim 2, characterized in that: Considering the time requirements of power users for the physical model of controllable loads, the power consumption characteristics of controllable loads are abstracted, and multi-type controllable load models taking into account power consumption characteristics are established, including: (2) (3) (4) in, Indicates electric vehicle e In time h The state variable represents whether the electric vehicle is allowed to charge; Further abstract the electric vehicle power consumption characteristics to obtain the power consumption characteristic data to be clustered. (5) in For electric vehicles e State variables during the full computation cycle; For electric vehicles e The minimum power state sequence; For electric vehicles e Maximum power state sequence.

4. A controllable load clustering method supporting balanced calculation according to claim 3, characterized in that: A multi-type controllable load model considering power consumption characteristics is established. l The power consumption characteristic data is used as clustering objects, including: (6) Using a partition-based clustering algorithm k-means Algorithm for massive controllable loads l Cluster analysis is performed on the power consumption characteristic data to select different load clusters according to the size of the controllable load. K , K <N , find a partition ( S k ) 1≤k≤K Divide the load into K cluster (7) in Represents load cluster S k The cluster center after clustering k Power consumption characteristics of load types ; N is the number of controllable loads.

5. A controllable load clustering method supporting balanced calculation according to claim 4, characterized in that: According to the controllable load categories obtained by clustering, the conditions that the controllable loads of the same category with interactive relationships meet when they reach a balanced state are analyzed for subsequent balanced calculations, including: (8) (9) in is the indicator function, when hour, ,otherwise ; It represents the feasible operation domain of the load generated by the power consumption feature mapping, that is, each controllable load must meet the requirements of its category. k The feasible operating domain; represents the electricity price function mapped from load behavior; Indicates controllable load a electricity costs; When equilibrium exists and is achieved, the electricity cost of each load reaches the minimum, that is, no load can further optimize its results by changing its own electricity strategy, satisfying the following equilibrium conditions, (10) (11) (12) in Indicates controllable load a The optimal electricity consumption plan under equilibrium state; yes k The set of optimal power consumption plans under the controllable load balancing state is a finite set; yes k Type of controllable load selection j The electricity cost of each electricity consumption plan; express k Type of controllable load selection j Number of electricity use options; express k The number of controllable loads.

6. A controllable load clustering system supporting balanced computing, characterized in that: include: The first model building module processes typical controllable loads and builds a controllable load physical model that describes power consumption characteristics; The second model building module considers the time usage requirements of the controllable load physical model by the power users, abstracts the power consumption characteristics of the controllable load, and builds a multi-type controllable load model taking into account the power consumption characteristics; Model processing module, for multi-type controllable load models taking into account power consumption characteristics, establish l The characteristic data of electricity consumption is used as the clustering object; Cluster analysis module, using k-means Algorithm for massive controllable loads l Cluster analysis of electricity consumption characteristic data; The condition analysis module analyzes the conditions that are satisfied when similar controllable loads with interactive relationships reach a balanced state based on the controllable load categories obtained by clustering, which is used for subsequent balanced calculations.

7. A controllable load clustering system supporting balanced computing according to claim 6, characterized in that: Process typical controllable loads and establish a controllable load physical model that describes the power consumption characteristics, including: Electricity users have a variety of controllable loads. For electric vehicles, the user's arrival time, departure time, upper and lower limits of charging power, and total power consumption are considered. (1) in, H represents the full computation cycle; H e is the allowed charging time of the electric vehicle, outside which the charging power of the electric vehicle is 0; p e,h Indicates electric vehicle e exist h The power consumption at time [ p e,min , p e,max ] is the charging power range of electric vehicles, p e,min represents the minimum charging power of electric vehicles, p e,max Indicates the maximum charging power of the electric vehicle; [ E e,min , E e,max ] is the total power consumption range of electric vehicles, E e,min represents the minimum power consumption of electric vehicles, E e,max Indicates the maximum power consumption of an electric vehicle.

8. A controllable load clustering system supporting balanced computing according to claim 7, characterized in that: Considering the time requirements of power users for the physical model of controllable loads, the power consumption characteristics of controllable loads are abstracted, and multi-type controllable load models taking into account power consumption characteristics are established, including: (2) (3) (4) in, Indicates electric vehicle e In time h The state variable represents whether the electric vehicle is allowed to charge; Further abstract the electric vehicle power consumption characteristics to obtain the power consumption characteristic data to be clustered. (5) in For electric vehicles e State variables during the full computation cycle; For electric vehicles e The minimum power state sequence; For electric vehicles e Maximum power state sequence.

9. A controllable load clustering system supporting balanced computing according to claim 8, characterized in that: A multi-type controllable load model considering power consumption characteristics is established. l The power consumption characteristic data is used as clustering objects, including: (6) Using a partition-based clustering algorithm k-means Algorithm for massive controllable loads l Cluster analysis is performed on the power consumption characteristic data to select different load clusters according to the size of the controllable load. K , K <N , find a partition ( S k ) 1≤k≤K Divide the load into K cluster (7) in Represents load cluster S k The cluster center after clustering k Power consumption characteristics of load types ; N is the number of controllable loads.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of a controllable load clustering method for supporting balanced computing according to any one of claims 1 to 6.

Images