Charging and discharging intelligent scheduling management system based on regional power distribution network

Abstract

The invention discloses a charging and discharging intelligent scheduling management system based on a regional power distribution network, and relates to the technical field of charging and discharging management, and the system comprises a power distribution network sensing and monitoring module which is used for constructing a power distribution network distributed sensing node set of the regional power distribution network, and monitoring and obtaining a power distribution network node sensing data flow set; the charging and discharging demand prediction module is used for carrying out charging and discharging demand prediction; the optimal scheduling module is used for carrying out electric energy analysis on the power distribution network node sensing data flow set, carrying out scheduling analysis and determining a charging and discharging scheduling parameter scheme; and the execution control module is used for carrying out charging and discharging scheduling control. The technical problem that in the prior art, flexible interaction between the power distribution network and the power utilization end cannot be achieved, and consequently the accuracy and the refinement degree of a scheduling decision are insufficient is solved, the accuracy and the refinement degree of charging and discharging scheduling are improved in combination with power distribution network information monitoring and charging and discharging demand prediction, and the scheduling efficiency is improved. The technical effect of efficient and stable operation of the power distribution network is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of charge and discharge management, and in particular to a charge and discharge intelligent dispatching and management system based on a regional distribution network. Background Art

[0002] With the rapid development of my country's industry, the demand for electricity is also increasing. The traditional distribution model can no longer meet the needs of current large-scale industrial production, so realizing the intelligent dispatching of distribution networks has become an important development direction for the power industry. However, the development of intelligent dispatching technology started late, and some technologies are still imperfect. For example, in the dispatching decision-making process, it is impossible to fully consider the distribution characteristics of the distribution network itself and realize flexible interaction with various power sources and loads connected to the smart grid. In addition, the data collection, processing and analysis capabilities are limited, resulting in insufficient accuracy and refinement of dispatching decisions, affecting the stability of distribution network operation. Summary of the invention

[0003] The present application provides a charging and discharging intelligent dispatching and management system based on a regional distribution network, which is used to solve the technical problem that the prior art cannot achieve flexible interaction between the distribution network and the power consumption end, resulting in insufficient accuracy and refinement of dispatching decisions.

[0004] The present application provides a charging and discharging intelligent dispatching and management system based on a regional distribution network, the system comprising: a distribution network perception monitoring module, used to collect and obtain a distribution characteristic data set of a regional distribution network, perform node architecture division and sensor deployment based on the distribution characteristic data set, obtain a set of distributed perception nodes of the distribution network, and obtain a set of distribution network node perception data streams through monitoring the distributed perception node set of the distribution network; a charging and discharging demand prediction module, used to perform demand prediction on the electric vehicle user data set and the power grid load data set according to the electric vehicle user data set and the power grid load data set, and obtain charging and discharging demand prediction parameter information; an optimization scheduling module, used to perform electric energy analysis on the distribution network node perception data stream set based on the distributed perception node set of the distribution network, obtain a set of distribution network node power supply parameters, encrypt and transmit the distribution network node power supply parameter set and the charging and discharging demand prediction parameter information to a cloud control center for scheduling analysis, and determine a charging and discharging scheduling parameter plan; an execution control module, used to perform charging and discharging scheduling and control of electric vehicles based on the charging and discharging scheduling parameter plan through charging and discharging terminal equipment.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The charging and discharging intelligent dispatching and management system based on the regional distribution network provided by the present application relates to the technical field of charging and discharging management. Through the distribution characteristic data set of the regional distribution network, the distribution network node perception data stream set is monitored and obtained. Through electric energy analysis, the distribution network node power supply parameter set is obtained. The dispatching analysis is combined with the charging and discharging demand prediction parameter information to determine the charging and discharging dispatching parameter plan, and the charging and discharging dispatching management and control are carried out. The technical problem that the flexible interaction between the distribution network and the power consumption end cannot be achieved in the prior art, resulting in insufficient accuracy and refinement of the dispatching decision, is solved. The distribution network information monitoring and charging and discharging demand prediction are combined to improve the accuracy and refinement of the charging and discharging dispatching, and achieve the technical effect of efficient and stable operation of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of the structure of a charging and discharging intelligent dispatching and management system based on a regional distribution network provided in an embodiment of the present application;

[0009] Figure 2 A schematic diagram of a process for obtaining a set of distributed sensing nodes of a distribution network in a charging and discharging intelligent dispatching and management system based on a regional distribution network provided in an embodiment of the present application;

[0010] Figure 3 A schematic diagram of a process for obtaining a set of distributed node power characteristic information in a charging and discharging intelligent dispatching and management system based on a regional distribution network provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: distribution network sensing and monitoring module 11 , charging and discharging demand prediction module 12 , optimization and scheduling module 13 , execution control module 14 . DETAILED DESCRIPTION

[0012] The present application provides a charging and discharging intelligent dispatching and management system based on a regional distribution network, which is used to solve the technical problem that the prior art cannot achieve flexible interaction between the distribution network and the power consumption end, resulting in insufficient accuracy and refinement of dispatching decisions.

[0013] 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, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0015] Embodiment 1

[0016] like Figure 1 As shown, the present application provides a charging and discharging intelligent dispatching and management system based on a regional distribution network, the system comprising:

[0017] The distribution network perception monitoring module 11 is used to collect and obtain the distribution characteristic data set of the regional distribution network, divide the node architecture and deploy sensors based on the distribution characteristic data set, obtain the distribution network distributed perception node set, and obtain the distribution network node perception data stream set through the distribution network distributed perception node set monitoring.

[0018] It should be understood that the distribution network perception monitoring module 11 of the present application is mainly responsible for collecting and acquiring the distribution characteristic data set of the regional distribution network, and the distribution characteristic data set includes but is not limited to electrical parameters, such as voltage, current, power factor, etc. Environmental parameters, such as temperature, humidity, wind speed, etc. Equipment status, such as the operating status and health status of equipment such as transformers, switches, cables, etc. Based on the distribution characteristic data set, node architecture division and sensor deployment are performed. Exemplarily, the node architecture division includes dividing the distribution network into several nodes or regions according to the topological structure and operating characteristics of the distribution network, and each node or region represents an independent part of the distribution network, with relatively independent operating status and characteristics. On the basis of the node architecture division, select the appropriate sensor type and deployment location to obtain the distribution network distributed perception node set. Through the distribution network distributed perception node set, the sensor should be able to accurately monitor the operating status and parameter changes of the node or region, and transmit the monitoring data to the distribution network perception monitoring module 11 in real time to obtain the distribution network node perception data stream set. The distribution network node perception data stream set contains the real-time operating data and status information of each node of the distribution network, providing an important basis for the intelligent management and decision-making of the distribution network.

[0019] Further, such as Figure 2 As shown, the distribution network sensing and monitoring module 11 is also used to perform the following steps:

[0020] P11: Divide the distribution characteristic data set into regions to obtain a distribution area set of the distribution network; P12: Obtain architecture deployment factor information, which includes charging pile distribution density, regional power capacity and power load demand; P13: Perform node architecture division analysis on the distribution area set of the distribution network based on the architecture deployment factor information to obtain distribution network distribution node architecture information; P14: Deploy sensor modules on the distribution network distribution node architecture information to obtain the distribution network distributed perception node set.

[0021] Specifically, the specific process of obtaining the set of distributed sensing nodes of the distribution network can be, firstly, using the geographic information system (GIS) technology and the distribution characteristic data set of the distribution network (such as voltage level, line length, substation location, etc.), the distribution network is divided into several areas with clear boundaries, and a distribution network distribution area set is formed. These areas may be divided based on factors such as geographical location, voltage level, power supply range, etc.

[0022] Further, information on architecture deployment factors is obtained, including the distribution density of charging piles, regional power capacity, and power load demand. Among them, the distribution density of charging piles can reflect the spatial distribution of electric vehicle charging demand. In areas where charging piles are densely distributed, a node may need to control more charging piles to meet the demand, while in areas where charging piles are sparsely distributed, each node may control fewer charging piles. The regional power capacity represents the power supply capacity of the regional power grid. The power capacity of different nodes is different, which determines the number and total power of charging piles they can carry. Nodes with larger power capacity can control more charging piles or higher-power charging piles. The power load demand represents the actual power load of the regional power grid. The power load demand of the node is also an important factor in determining the number of charging piles it controls. In periods or areas with high power load, nodes need to reasonably allocate power resources to ensure the normal operation of charging piles and the stability of power supply.

[0023] Furthermore, mathematical models, optimization algorithms and other technical means are used to comprehensively consider factors such as charging pile distribution density, regional power capacity and power load demand, and analyze the node architecture division of the distribution area of ​​the distribution network. Through analysis, the number and location of nodes to be set in each area and the connection relationship between them are determined to form the distribution node architecture information of the distribution network.

[0024] Furthermore, according to the information of the distribution node architecture of the distribution network, sensor modules are installed at the corresponding node positions. These sensor modules should have the characteristics of high precision, high reliability and real-time performance, and can accurately monitor key parameters such as voltage, current and power. By deploying sensor modules, a distributed sensing node set of the distribution network is formed to achieve comprehensive and accurate monitoring of the distribution network status, providing strong data support for subsequent charging and discharging demand prediction, optimized scheduling and execution control.

[0025] The charging and discharging demand prediction module 12 is used to perform demand prediction on the electric vehicle user data set and the power grid load data set according to the electric vehicle user data set and the power grid load data set to obtain charging and discharging demand prediction parameter information.

[0026] Furthermore, the charging and discharging demand prediction module 12 is also used to perform the following steps:

[0027] P21: Obtain a historical charging and discharging data set of electric vehicles, parse the historical charging and discharging data set of electric vehicles, and determine the historical data of electric vehicle users and the corresponding charging and discharging record data; P22: Use a deep neural network structure to perform predictive training on the historical data of electric vehicle users and the corresponding charging and discharging record data to obtain a first charging and discharging demand prediction model; P23: Obtain a historical data set of power grid loads, perform supervised training on the historical data set of power grid loads, and generate a second charging and discharging demand prediction model; P24: Merge the first charging and discharging demand prediction model and the second charging and discharging demand prediction model to obtain a distribution network charging and discharging demand prediction model; P25: Perform demand prediction on the electric vehicle user data set and the power grid load data set based on the distribution network charging and discharging demand prediction model to obtain the charging and discharging demand prediction parameter information.

[0028] Optionally, the charging and discharging demand prediction module 12 of the present application is responsible for predicting future charging and discharging demand by analyzing the current electric vehicle user data set and the power grid load data set, and providing key parameter information for optimizing scheduling. Specifically, first retrieve the electric vehicle historical charging and discharging data set from the database, including charging and discharging record data such as charging time, charging amount, discharging time, and discharging amount. At the same time, it is also necessary to obtain the electric vehicle user historical data related to the user, such as mileage, charging habits, etc. These data are parsed and converted into the format required for model training.

[0029] Furthermore, an appropriate deep neural network structure (such as a recurrent neural network RNN, a long short-term memory network LSTM, etc.) is selected, and the electric vehicle user historical data and the corresponding charging and discharging record data are used as input to perform model training. By adjusting network parameters, optimizing algorithms, etc., the model can accurately predict the charging and discharging demand of the electric vehicle, and obtain a first charging and discharging demand prediction model.

[0030] Furthermore, a historical data set of power grid load is collected, including historical load values, load change trends, etc. A supervised learning method is used to train the model with the historical power grid load data as input and the predicted power grid load value as output. A second charging and discharging demand prediction model is generated, which can predict the future load of the power grid, thereby evaluating the power grid's capacity to accommodate the charging and discharging of electric vehicles.

[0031] Furthermore, the first charging and discharging demand prediction model and the second charging and discharging demand prediction model are merged to obtain a distribution network charging and discharging demand prediction model. The merging process can be achieved in a variety of ways, such as weighted averaging the prediction results of the two models, or using an integrated learning method. The merged model can simultaneously consider the charging and discharging demand of electric vehicles and the load of the power grid, thereby more accurately predicting future charging and discharging demand.

[0032] Furthermore, the electric vehicle user data set and the power grid load data set of the current period are used as input and input into the distribution network charging and discharging demand prediction model to perform charging and discharging demand prediction, and output future charging and discharging demand prediction parameter information, including charging time, charging amount, discharging time, discharging amount, etc., for subsequent optimization scheduling decisions.

[0033] The optimization scheduling module 13 is used to perform power analysis on the distribution network node perception data stream set based on the distribution network distributed perception node set, obtain the distribution network node power supply parameter set, encrypt the distribution network node power supply parameter set and the charging and discharging demand prediction parameter information and transmit them to the cloud control center for scheduling analysis, and determine the charging and discharging scheduling parameter plan.

[0034] Furthermore, the optimization scheduling module 13 is also used to perform the following steps:

[0035] P31: Allocate computing resources to the distribution network distributed perception node set based on the distribution network node perception data stream set to obtain node computing resource allocation information; P32: Configure the distribution network distributed perception node set according to the node computing resource allocation information to obtain a distributed edge computing node set; P33: Perform feature extraction on the distribution network node perception data stream set based on the distributed edge computing node set to obtain a distributed node power feature information set; P34: Perform power supply analysis on the distributed node power feature information set to obtain the distribution network node power supply parameter set.

[0036] In a possible embodiment of the present application, the optimization scheduling module 13 of the present application is responsible for formulating the optimal charging and discharging scheduling plan according to the actual operating status of the distribution network and the predicted charging and discharging demand. First, in order to more effectively utilize the computing resources of the distributed sensing nodes of the distribution network, it is necessary to reasonably allocate the computing resources of these nodes according to the real-time situation of the distribution network node perception data flow set. Exemplarily, the computing power requirements of each sensing node are evaluated by analyzing the size, complexity and real-time requirements of the data flow. Then, based on the evaluation results, a computing resource allocation strategy is formulated to ensure that high-load nodes can obtain more computing resources, while low-load nodes can appropriately reduce resource occupancy, thereby achieving balanced utilization of computing resources, generating node computing resource allocation information, and providing a basis for subsequent node configuration.

[0037] Furthermore, according to the computing resource allocation information, the distributed perception nodes of the distribution network are configured to form a distributed edge computing node set to improve the efficiency of data processing and analysis. Specifically, according to the node computing resource allocation information, the configuration of the distributed perception nodes of the distribution network is adjusted accordingly, including adjusting the computing task priority of the node, optimizing the task scheduling strategy, increasing or decreasing the computing resources of the node, etc. After the configuration is completed, these nodes will act as distributed edge computing nodes and jointly participate in the processing and analysis of the distribution network node perception data flow to form a distributed edge computing node set.

[0038] Furthermore, feature extraction is performed on the distribution network node perception data stream set based on the distributed edge computing node set. Exemplarily, a large amount of data in the distribution network node perception data stream set is processed in parallel through the distributed edge computing node set, and machine learning, data mining, etc. are applied to automatically identify and extract key feature information in the data, such as voltage fluctuations, current peaks, power factor changes, etc., and integrate them into a distributed node power feature information set.

[0039] Furthermore, based on the distributed node power characteristic information set, the power supply situation of each node in the distribution network is deeply analyzed. For example, by analyzing indicators such as voltage stability, current balance, and power factor, the power supply capacity and quality of each node in the distribution network are evaluated, and a set of power supply parameters for the distribution network nodes is generated. These parameters will serve as an important basis for formulating charging and discharging scheduling parameter plans.

[0040] Further, such as Figure 3 As shown, step P33 of the embodiment of the present application also includes:

[0041] P33-1: Based on the distributed edge computing node set, the distribution network node perception data stream set is standardized to obtain a standard data stream set of distribution network nodes; P33-2: The distribution network node standard data stream set is decentralized to obtain a covariance matrix, and the covariance matrix is ​​solved and calculated to obtain eigenvalues ​​and eigenvectors; P33-3: According to the eigenvalue selection, principal component information is obtained, and based on the principal component information, the standard data stream set of the distribution network node is projected onto the eigenvector to obtain the distributed node electric energy characteristic information set.

[0042] Specifically, the specific process of extracting the distributed node power feature information from the distribution network node perception data stream set may be, first, since the distribution network node perception data stream set may come from different perception nodes, and the measurement scale and range of each node may be different, it is necessary to standardize the data stream to eliminate these differences and make the data comparable. For example, the distribution network node perception data stream set is preprocessed by data cleaning, and the preprocessed data is standardized to make its mean 0 and standard deviation 1 to eliminate the dimensional differences between different features.

[0043] Furthermore, the standard data stream set of the distribution network nodes is decentralized, that is, the deviation of each data item from the center of the data set is calculated, and then the covariance matrix is ​​calculated using these decentralized data. The matrix reflects the covariance relationship between the data items, and then the covariance matrix is ​​eigenvalue decomposed to obtain the eigenvalue and the corresponding eigenvector. The size of the eigenvalue reflects the degree of data change in the direction of the corresponding eigenvector, so the principal component information, that is, the main direction of change in the data, can be selected according to the size of the eigenvalue.

[0044] Furthermore, according to the eigenvalues ​​and eigenvectors, the eigenvector with the larger eigenvalue is selected as the principal component, and then the principal component information is obtained. Based on the principal component information, the standard data stream set of the distribution network node is projected onto the selected eigenvector to obtain the projection value on each principal component. And these projection values ​​constitute a distributed node power characteristic information set, which represents the most representative power characteristic information in the data and will be used in subsequent power supply analysis and optimization scheduling decisions.

[0045] Furthermore, the optimization scheduling module 13 is also used to perform the following steps:

[0046] P35: Match and optimize the charging and discharging demand prediction parameter information with the distribution network node power supply parameter set to determine the target scheduling distribution network node; P36: Call the charging and discharging data of the target scheduling distribution network node through the cloud control center to obtain the node charging and discharging parameter space; P37: Perform scheduling threshold analysis on the node charging and discharging parameter space based on the charging and discharging demand prediction parameter information to obtain the charging and discharging parameter selection threshold; P38: Construct a charging and discharging effect fitness function, use the charging and discharging effect fitness function to perform global optimization within the charging and discharging parameter selection threshold, and determine the charging and discharging scheduling parameter plan.

[0047] Optionally, the power supply parameter set of the distribution network node and the charge and discharge demand prediction parameter information are encrypted and transmitted to the cloud control center for scheduling analysis to determine the charge and discharge scheduling parameter plan. The specific process is as follows: first, the charge and discharge demand prediction parameter information is compared with the power supply parameter set of the distribution network node. Through algorithm matching, the distribution network nodes that meet the charge and discharge demand and have sufficient power supply capacity are selected as the target scheduling distribution network nodes.

[0048] Furthermore, the cloud control center calls and collects the historical charging and discharging data and real-time status information of the target dispatching distribution network node according to the instructions of the optimization dispatching module 13 to form the node charging and discharging parameter space. Then, according to the charging and discharging demand prediction parameter information (such as the charging demand time window and charging power demand of electric vehicles), combined with the historical data and real-time status in the node charging and discharging parameter space, statistical analysis, machine learning and other methods are used to parse out the reasonable charging and discharging parameter selection threshold as a constraint condition in the subsequent global optimization process.

[0049] Furthermore, according to the scheduling objectives, such as maximizing power supply efficiency, minimizing costs, balancing grid loads, etc., a charging and discharging effect fitness function is constructed. Then, a heuristic algorithm (such as a genetic algorithm, a particle swarm optimization algorithm, etc.) or a deterministic optimization method is used to perform a global search within the charging and discharging parameter selection threshold to find the charging and discharging scheduling parameter combination that makes the fitness function reach the optimal value. Finally, the optimal charging and discharging scheduling parameter scheme is determined, and the optimal charging and discharging scheduling parameter scheme will be used to guide the actual charging and discharging scheduling process to achieve the optimal matching and efficient operation between the distribution network and electric vehicles.

[0050] Furthermore, step P35 of the embodiment of the present application also includes:

[0051] P35-1: Obtain the charge and discharge matching factor information, which includes supply and demand balance, charge and discharge efficiency, charge and discharge stability and safety; P35-2: Construct a charge and discharge node optimization coordinate system based on the charge and discharge matching factor information; P35-3: Based on the charge and discharge node optimization coordinate system, evaluate and map the charge and discharge demand prediction parameter information and the distribution network node power supply parameter set to obtain a distribution network node matching vector set; P35-4: Optimize the distribution network nodes based on the modulus of the distribution network node matching vector set to determine the target scheduling distribution network node.

[0052] It should be understood that the specific process of determining the target dispatching distribution network node may be, first, obtaining the charge and discharge matching factor information including supply and demand balance, charge and discharge efficiency, charge and discharge stability and safety. These factors directly affect the selection of distribution network nodes and the effect of charge and discharge scheduling, and are an important basis for formulating the optimization strategy. Furthermore, a multidimensional charge and discharge node optimization coordinate system is constructed with the charge and discharge matching factor information as the dimension of the coordinate system. Each dimension represents a matching factor, and each factor can be converted into a comparable value or index through quantitative processing.

[0053] Furthermore, the charging and discharging demand prediction parameter information and the power supply parameter set of the distribution network node are mapped to the charging and discharging node optimization coordinate system for evaluation and mapping. The corresponding matching vector is generated by calculating the score or position of each distribution network node in each dimension of the coordinate system. These matching vectors combine the comprehensive performance of the distribution network nodes in terms of supply and demand balance, charging and discharging efficiency, charging and discharging stability, and safety, and constitute a distribution network node matching vector set.

[0054] Furthermore, according to the modulus (or other comprehensive evaluation index) of the distribution network node matching vector set, the distribution network nodes are optimized to calculate the modulus of each vector in the distribution network node matching vector set, that is, the vector length or comprehensive score, which can reflect the comprehensive performance of the distribution network nodes in the charging and discharging matching factors. The distribution network nodes are sorted or screened according to the size of the modulus, and the nodes with larger modulus values ​​(that is, better comprehensive performance) are selected as the target scheduling distribution network nodes. The target scheduling distribution network nodes will be the focus of subsequent charging and discharging scheduling to achieve optimal matching and efficient operation between the distribution network and electric vehicles.

[0055] Furthermore, step P38 of the embodiment of the present application also includes:

[0056] P38-1: Randomly generate multiple charge and discharge control parameters within the charge and discharge parameter selection threshold, use the charge and discharge effect fitness function to calculate and evaluate the multiple charge and discharge control parameters, and obtain multiple parameter charge and discharge effect fitness; P38-2: Based on the multiple parameter charge and discharge effect fitness, perform cross-mutation expansion on the multiple charge and discharge control parameters to obtain a charge and discharge control parameter population; P38-3: Perform iterative optimization within the charge and discharge control parameter population until a preset number of iterations is reached to determine the charge and discharge scheduling parameter plan.

[0057] Optionally, the specific process of determining the charging and discharging scheduling parameter scheme by global optimization may be, first, randomly generating one or more groups of charging and discharging control parameters within the charging and discharging parameter selection threshold range, these parameters may include charging start time, charging power, discharging start time, discharging power, etc. Further, the charging and discharging effect fitness function is used to calculate and evaluate the multiple charging and discharging control parameters to obtain the charging and discharging effect fitness value corresponding to each parameter combination, that is, to obtain multiple parameter charging and discharging effect fitness.

[0058] Furthermore, based on the fitness of the charge and discharge effects of the multiple parameters, the multiple charge and discharge control parameters are cross-mutated and expanded through genetic algorithms such as cross-mutation. Exemplarily, according to the fitness values ​​of the charge and discharge effects of the multiple parameters obtained by preliminary evaluation, parameter combinations with higher fitness are selected as excellent individuals. Then, these excellent individuals are cross-operated (i.e., exchanging some genes of different individuals) and mutated (i.e., randomly changing the values ​​of certain genes in the individuals) to generate new parameter combinations. The newly generated parameter combination and the original excellent individuals together constitute a charge and discharge control parameter population, so as to increase the diversity of the search space and improve the possibility of finding the global optimal solution.

[0059] Furthermore, an iterative optimization is performed within the population of charge and discharge control parameters, and operations such as evaluation, selection, crossover and mutation are repeated to form a new population. After each iteration, the individuals in the population are evaluated according to the fitness function of the charge and discharge effect, and the individuals with higher fitness are retained to enter the next generation population. As the number of iterations increases, the individuals in the population will gradually approach the global optimal solution. When the preset number of iterations is reached or other stop conditions are met, the iterative process is stopped, and the individual with the highest fitness is selected from the current population as the final charge and discharge scheduling parameter scheme. The charge and discharge scheduling parameter scheme will serve as a guiding basis for actual charge and discharge scheduling to achieve optimal matching and efficient operation between the distribution network and electric vehicles.

[0060] The execution control module 14 is used to perform charge and discharge scheduling control on the electric vehicle based on the charge and discharge scheduling parameter scheme through the charge and discharge terminal equipment.

[0061] Specifically, the execution control module 14 of the present application is responsible for receiving the charging and discharging scheduling parameter scheme from the optimization scheduling module 13, and performing actual charging and discharging scheduling control on the electric vehicle through the charging and discharging terminal equipment. Exemplarily, the execution control module 14 first receives the charging and discharging scheduling parameter scheme from the optimization scheduling module 13 through the network or other communication methods, and parses and processes it, converts the parameter scheme into a control instruction format that can be recognized by the charging and discharging terminal equipment, and sends it to the corresponding charging and discharging terminal equipment, such as a charging pile, a battery management system, or other equipment related to the charging and discharging of electric vehicles. And the actual charging and discharging scheduling control of electric vehicles is performed through the charging and discharging terminal equipment to ensure the smooth progress of the charging process of electric vehicles.

[0062] In summary, the embodiments of the present application have at least the following technical effects:

[0063] This application uses the distribution characteristic data set of the regional distribution network to monitor and obtain the distribution network node perception data stream set, obtains the distribution network node power supply parameter set through power analysis, performs scheduling analysis in combination with the charging and discharging demand prediction parameter information, determines the charging and discharging scheduling parameter plan, and performs charging and discharging scheduling control.

[0064] The technical effect of combining distribution network information monitoring and charging and discharging demand forecasting, improving the accuracy and refinement of charging and discharging scheduling, and achieving efficient and stable operation of the distribution network has been achieved.

[0065] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0067] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Intelligent dispatching and management system for charging and discharging based on regional distribution network, characterized in that: The system comprises: The distribution network perception monitoring module is used to collect and obtain the distribution characteristic data set of the regional distribution network, perform node architecture division and sensor deployment based on the distribution characteristic data set, obtain the distribution network distributed perception node set, and obtain the distribution network node perception data stream set through the distribution network distributed perception node set monitoring; A charging and discharging demand prediction module is used to perform demand prediction on the electric vehicle user data set and the power grid load data set according to the electric vehicle user data set and the power grid load data set to obtain charging and discharging demand prediction parameter information; An optimization scheduling module is used to perform power analysis on the distribution network node perception data stream set based on the distribution network distributed perception node set, obtain the distribution network node power supply parameter set, encrypt and transmit the distribution network node power supply parameter set and the charging and discharging demand prediction parameter information to the cloud control center for scheduling analysis, and determine the charging and discharging scheduling parameter plan; The execution control module is used to perform charge and discharge scheduling control on the electric vehicle based on the charge and discharge scheduling parameter scheme through the charge and discharge terminal equipment.

2. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 1, characterized in that: The step of obtaining a set of distributed sensing nodes in the distribution network includes: Dividing the distribution characteristic data set into regions to obtain a distribution area set of the distribution network; Acquiring architecture deployment factor information, wherein the architecture deployment factor information includes charging pile distribution density, regional power capacity, and power load demand; Based on the architecture deployment factor information, a node architecture division analysis is performed on the distribution area set of the distribution network to obtain distribution network distribution node architecture information; The sensor modules are deployed on the distribution node architecture information of the distribution network to obtain the distributed sensing node set of the distribution network.

3. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 1 is characterized in that: The obtaining of charging and discharging demand prediction parameter information includes: Acquire a historical charging and discharging data set of an electric vehicle, parse the historical charging and discharging data set of the electric vehicle, and determine the electric vehicle user historical data and corresponding charging and discharging record data; Use a deep neural network structure to perform prediction training on the electric vehicle user historical data and corresponding charging and discharging record data to obtain a first charging and discharging demand prediction model; Acquire a historical data set of power grid load, perform supervised training on the historical data set of power grid load, and generate a second charging and discharging demand prediction model; The first charging and discharging demand forecasting model and the second charging and discharging demand forecasting model are combined to obtain a distribution network charging and discharging demand forecasting model; Based on the distribution network charge and discharge demand prediction model, demand prediction is performed on the electric vehicle user data set and the power grid load data set to obtain the charge and discharge demand prediction parameter information.

4. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 1, characterized in that: The obtaining of a set of power supply parameters of a distribution network node includes: Allocate computing resources to the distributed sensing node set of the distribution network based on the set of distribution network node sensing data streams to obtain node computing resource allocation information; The distributed sensing node set of the distribution network is configured according to the node computing resource allocation information to obtain a distributed edge computing node set; Based on the distributed edge computing node set, feature extraction is performed on the distribution network node perception data stream set to obtain a distributed node power feature information set; Power supply analysis is performed on the distributed node power energy feature information set to obtain the distribution network node power supply parameter set.

5. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 4, characterized in that: The step of obtaining a distributed node power characteristic information set includes: Based on the distributed edge computing node set, the distribution network node perception data stream set is standardized to obtain a distribution network node standard data stream set; Decentralizing the set of standard data streams of the distribution network nodes to obtain a covariance matrix, and solving and calculating the covariance matrix to obtain eigenvalues ​​and eigenvectors; The principal component information is obtained according to the eigenvalue selection, and the standard data stream set of the distribution network node is projected onto the eigenvector based on the principal component information to obtain the distributed node electric energy characteristic information set.

6. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 1, characterized in that: The scheme for determining charging and discharging scheduling parameters includes: The charging and discharging demand prediction parameter information is matched and optimized with the power supply parameter set of the distribution network node to determine the target dispatching distribution network node; The charging and discharging data of the target dispatching distribution network node are called by the cloud control center to obtain the node charging and discharging parameter space; Based on the charge and discharge demand prediction parameter information, the node charge and discharge parameter space is subjected to scheduling threshold analysis to obtain a charge and discharge parameter selection threshold; A charging and discharging effect fitness function is constructed, and the charging and discharging effect fitness function is used to perform global optimization within the charging and discharging parameter selection threshold to determine the charging and discharging scheduling parameter scheme.

7. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 6, characterized in that: The determining of the target dispatching distribution network node comprises: Acquiring charge-discharge matching factor information, wherein the charge-discharge matching factor information includes supply-demand balance, charge-discharge efficiency, charge-discharge stability, and safety; Constructing an optimal coordinate system of charging and discharging nodes according to the charging and discharging matching factor information; Based on the preferred coordinate system of the charging and discharging node, the charging and discharging demand prediction parameter information and the power supply parameter set of the distribution network node are evaluated and mapped to obtain a distribution network node matching vector set; Distribution network nodes are optimized based on the modulus of the distribution network node matching vector set to determine the target scheduling distribution network node.

8. The charging and discharging intelligent dispatching and management system based on the regional distribution network according to claim 6, characterized in that: The determining of the charging and discharging scheduling parameter scheme includes: Randomly generate multiple charge and discharge control parameters within the charge and discharge parameter selection threshold, and use the charge and discharge effect fitness function to calculate and evaluate the multiple charge and discharge control parameters to obtain multiple parameter charge and discharge effect fitness; Based on the fitness of the multiple parameter charging and discharging effects, the multiple charging and discharging control parameters are cross-mutated and expanded to obtain a charging and discharging control parameter population; An iterative optimization is performed within the charge and discharge control parameter population until a preset number of iterations is reached to determine the charge and discharge scheduling parameter scheme.

Images