Artificial intelligence-based power distribution network source-load-storage resource configuration method, device and medium

Abstract

The application relates to a power distribution network source-load-storage resource configuration method and device based on artificial intelligence and a medium, the method comprises the following steps: constructing a power distribution network system model containing a battery energy storage, an electric vehicle charging station and a distributed power supply; constructing a distributed resource configuration optimization model with the optimization target of minimizing power loss of the power distribution network based on the model; and solving the configuration optimization model by adopting a power flow calculation model combined with a real number coding genetic algorithm to obtain an optimal configuration scheme of the distributed resource. Compared with the prior art, the application has the advantages of considering system stability, renewable energy consumption and power grid benefits and the like.

Description

Technical Field

[0001] This invention relates to the field of power generation, load and energy storage technology in distribution networks, and in particular to a method, apparatus and medium for allocating power generation, load and energy storage resources in distribution networks based on artificial intelligence. Background Technology

[0002] Battery energy storage systems, as a key technology for improving grid reliability, have significant potential in promoting the high-proportion consumption of renewable energy, enabling load regulation and optimizing power quality. Meanwhile, electric vehicles, as an important vehicle for decarbonizing the transportation sector, bring new challenges to distribution network operation with their large-scale application. Plug-in electric vehicles, in particular, require grid connection for battery charging; without orderly management, this can lead to stability issues such as line overload, voltage fluctuations, and widening peak-valley differences. Furthermore, the scale of distributed generation continues to grow, primarily driven by renewable energy sources such as solar photovoltaic and wind power; however, the intermittency, volatility, and uncertainty of wind and solar power output can also cause system operational problems.

[0003] Against this backdrop, achieving coordinated and optimized configuration of battery storage, electric vehicle charging stations, and distributed power sources to mitigate adverse effects and maximize the benefits of the power distribution system is particularly important. However, existing power distribution network planning methods lack a systematic framework for these three types of resources, making it difficult to balance system stability, renewable energy consumption, and grid efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide an artificial intelligence-based method for allocating power grid resources based on power generation, load and storage, in order to balance system stability, renewable energy consumption and grid efficiency.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] An artificial intelligence-based method for allocating power generation, load, and energy storage resources in a distribution network, comprising the following steps:

[0007] Construct a power distribution network system model that includes battery energy storage, electric vehicle charging stations, and distributed power sources;

[0008] Based on the model, a distributed resource allocation optimization model is constructed with the goal of minimizing power loss in the distribution network;

[0009] The optimal configuration scheme for distributed resources is obtained by combining a power flow calculation model with a real-number encoded genetic algorithm to solve the configuration optimization model.

[0010] Furthermore, the power distribution network system model includes:

[0011] Battery energy storage model, electric vehicle charging station model, and distributed power source model.

[0012] Furthermore, the configuration optimization model for distributed resources is as follows:

[0013]

[0014] In the formula, It is a collection of time periods; It is the collection of components in the system that generate power loss; It is the equivalent resistance of the component; It is the current flowing through component l during the time period 𝑡.

[0015] Furthermore, the constraints for optimizing the model include:

[0016] Power balance, bus voltage limit, line current, output range of distributed power sources, penetration rate limit of distributed power sources, capacity of electric vehicle charging stations, charging and discharging power of battery energy storage systems, and state of charge of battery energy storage systems.

[0017] Furthermore, the specific steps for obtaining the optimal configuration scheme of distributed resources by combining the power flow calculation model with the real-number encoded genetic algorithm to solve the configuration optimization model are as follows:

[0018] Construct the nodal admittance matrix of the entire power distribution system The matrix is ​​obtained by integrating the original admittance matrix of all circuit elements. Y This is formed, and then the voltage of each node is solved iteratively through a power flow calculation model;

[0019] In the voltage input configuration optimization model of each node, the global optimal solution is then obtained through a real-number encoded genetic algorithm as the optimal configuration scheme.

[0020] Furthermore, nodes j The voltage is:

[0021]

[0022] In the formula, It is the current passing through the power converter; It is a node j The voltage.

[0023] Furthermore, the specific steps for obtaining the global optimal solution as the optimal configuration scheme using the real-number encoded genetic algorithm are as follows:

[0024] (1) Initialization parameters: The initial population size is 1. ;

[0025] (2) Decode the individual node numbers in the population into integers, and then convert the nodes... j The target function is input with voltage, and the target function value is calculated.

[0026] (3) Set fitness:

[0027] Fitness is:

[0028]

[0029] In the formula, It is the i-th individual; It is the value of the objective function; It is the base value of the penalty; It is the deviation value of the d-th constraint;

[0030] (4) Iterative solution based on the selection, crossover, mutation and truncation process of genetic algorithm;

[0031] (5) Algorithm termination and optimal solution output: If the preset termination condition is met, the algorithm ends; otherwise, return to step (2) and finally output the global optimal solution.

[0032] Furthermore, the mutated solution during mutation is:

[0033]

[0034]

[0035] In the formula, These are the lower and upper bounds of the decision variable, respectively; It is a random number that is uniformly distributed between [0,1].

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] This invention constructs a distribution network system model that includes battery energy storage, electric vehicle charging stations, and distributed power sources. It accurately quantifies the intermittent characteristics of wind and solar energy, providing a data foundation for subsequent coordinated configuration and solving the problem that a single resource model cannot adapt to the operating characteristics of multiple types of distributed resources. Through power balance constraints to ensure grid supply and demand stability, bus voltage and line current constraints to ensure equipment safety, DG penetration rate constraints to avoid the impact of excessive grid connection of new energy sources, and EVCS capacity / BESS charge / discharge state constraints to control resource operating boundaries, a comprehensive constraint system is formed. This avoids the system risks caused by unconstrained optimization while ensuring that the optimization direction is highly aligned with the grid's energy-saving and safe operation requirements, taking into account system stability, renewable energy consumption, and grid benefits.

[0038] This invention also proposes that power flow calculation, by constructing a node admittance matrix, can accurately simulate the power flow of components such as lines and transformers in a power distribution system, providing a realistic system operation scenario for the genetic algorithm. In the improved genetic algorithm, tournament selection ensures the retention of high-quality individuals, Laplace crossover improves the diversity of offspring, power mutation enhances the global search capability of the algorithm, and truncation adapts to the integer requirements of node numbers. Compared with traditional algorithms, this invention significantly improves the solution efficiency and the accuracy of the optimal solution, and solves the problems of slow convergence and easy getting trapped in local optima in complex configuration models. Attached Figure Description

[0039] Figure 1 This is a flowchart of a power distribution network source-load-storage resource allocation method based on artificial intelligence, according to an embodiment of the present invention.

[0040] Figure 2 This is a flowchart of an artificial intelligence-based optimized allocation method according to an embodiment of the present invention;

[0041] Figure 3 An improved IEEE 34-node power distribution system according to an embodiment of the present invention;

[0042] Figure 4 These are the daily load curves for residential, commercial, and industrial use in embodiments of the present invention.

[0043] Figure 5 The solar irradiance and temperature curves are from an embodiment of the present invention;

[0044] Figure 6 The total power loss curves are shown for different locations of the battery energy storage system in this embodiment of the invention.

[0045] Figure 7 This is the daily active power loss curve of the power distribution system according to an embodiment of the present invention. Detailed Implementation

[0046] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0047] This invention provides an artificial intelligence-based method for allocating power generation, load, and storage resources in a distribution network. First, a distributed resource framework for the distribution network, including battery storage, electric vehicle charging stations, and distributed power sources, is proposed, and a mathematical model of the distributed resources is established to quantify their operational characteristics. Then, with minimizing power loss in the distribution network as the optimization objective, and considering the operational constraints of the distribution network and distributed resources, a configuration optimization model for the distributed resources is established. Next, an AI-based distributed resource configuration model is constructed, and combined with the OpenDSS power flow calculation model, a genetic algorithm is used to iteratively solve the distributed resource configuration model. Finally, using basic distribution network data and the types, quantities, and capacities of the distributed resources to be configured as input, the genetic algorithm is applied to solve the distributed resource configuration model, yielding the optimal configuration scheme for the distributed resources. This invention provides an innovative solution for integrating multiple types of distributed resources, and, combined with artificial intelligence algorithms, achieves the scientific allocation of power generation, load, and storage resources, providing scientific and efficient technical support for the planning of new distribution networks.

[0048] To address the shortcomings of existing technologies, this invention provides an artificial intelligence-based method for allocating power generation, load, and energy storage resources in a distribution network. This method determines the optimal installation nodes for battery energy storage systems, electric vehicle charging stations, and distributed power sources within the power grid, providing methodological support for distribution network planning and resource allocation.

[0049] To achieve the above objectives, the present invention provides the following technical solution:

[0050] An artificial intelligence-based method for allocating power generation, load, and storage resources in a distribution network comprises the following steps:

[0051] S1 proposes a distributed resource framework for power distribution networks that includes battery energy storage, electric vehicle charging stations, and distributed power sources. It establishes a mathematical model of distributed resources and quantifies the operational characteristics of distributed resources.

[0052] S2 takes minimizing power loss in the distribution network as its optimization objective, and considers the operational constraints of the distribution network and distributed resources to establish a configuration optimization model for distributed resources.

[0053] S3 constructs a distributed resource allocation model for distribution networks based on artificial intelligence, and combines it with the OpenDSS power flow calculation model to iteratively solve the distributed resource allocation model for distribution networks using a genetic algorithm.

[0054] S4 takes the basic data of the distribution network and the type, quantity and capacity of the distributed resources to be configured as input, and applies a genetic algorithm to solve the configuration model of the distributed resources of the distribution network to obtain the optimal configuration scheme of the distributed resources.

[0055] In step 1, a distributed resource framework for the power distribution network, including battery energy storage, electric vehicle charging stations and distributed power sources, is proposed, and a mathematical model of distributed resources is established.

[0056] Specifically, the distributed resource framework and its mathematical model for the distribution network of battery energy storage, electric vehicle charging stations, and distributed power sources constructed in step 1 are as follows:

[0057] For Battery Energy Storage Systems (BESS), two predetermined thresholds are set to activate the peak-shaving control strategy: the charging initiation threshold and the charging initiation threshold. and discharge start threshold Therefore, when the substation power is lower than the charging start threshold, the battery storage begins to charge; when the power exceeds the discharging start threshold, the battery storage discharges.

[0058]

[0059] In the formula, For the first s The power of a battery's energy storage during charging or discharging at any given time. , These are the charging start threshold and the discharging start threshold, respectively. for t Power of the substation at all times.

[0060] The exchange power between battery energy storage and its grid connection node is calculated using the following formula:

[0061] Charging status:

[0062]

[0063] Discharge state:

[0064]

[0065] Idle state:

[0066]

[0067] In the formula, The active and reactive power flowing into the inverter; The power is the output power after conversion by the inverter; This is idle power; The power flowing to the charging / discharging stage; Provide power to the power grid; inject power into the power grid; The power flowing into / out of the ideal energy storage; These are the inverter efficiency, charging efficiency, and discharging efficiency.

[0068] The Electric Vehicle Charging Station (EVCS) model is constructed using a constant power load, where the active and reactive power consumed remain constant, as expressed by the following formula.

[0069]

[0070] In the formula, It's voltage. These are the active power and reactive power of the electric vehicle station, respectively. These are the reference voltages Rated active power and rated reactive power; under constant power load .

[0071] In this invention, the distributed generation (DG) model of the distribution network system mainly considers photovoltaic power generation, which consists of two parts: a photovoltaic array and an inverter. The output power of the photovoltaic array is shown below.

[0072]

[0073] In the formula, t represents the DC power output and illuminance of the photovoltaic array at time t; Let t be the ambient temperature at time t; This is a temperature correction factor; The photovoltaic panel under standard illumination (1000W / m) 2 ), and the maximum DC power at standard temperature (usually 25°C).

[0074] In step 2, with minimizing the power loss of the distribution network as the optimization objective, and considering the operational constraints of the distribution network and distributed resources, a configuration optimization model for distributed resources is established.

[0075] Specifically, the objective function of the optimization model is to minimize the power loss of the distribution network, as shown below.

[0076]

[0077] In the formula, It is a collection of time periods; It is the collection of components in the system that generate power loss; It is the equivalent resistance of the component; It is the current flowing through component l during the time period 𝑡.

[0078] The constraints are power balance, bus voltage limit, line current, output range and penetration limit of distributed power sources, electric vehicle charging station capacity, battery energy storage system charge and discharge rate and state of charge, as shown below.

[0079] 1. Power balance:

[0080]

[0081]

[0082] In the formula, These are the active power and reactive power of the substation, respectively. These are the sums of the active and reactive power of the h distributed power sources at time t, respectively. These are the sum of the active and reactive power of the energy stored in the s batteries at time t; These are the sums of the active and reactive power of the j load nodes, respectively. These are the sum of the active and reactive power consumed by the k electric vehicle charging stations at time t, respectively. It is the line resistance; It is the line current at time t; It is the first l The reactive power loss of the line at time t; It is a collection of routes.

[0083] 2. Bus voltage limitation:

[0084]

[0085] In the formula, It is the voltage at point n on the bus at time t; That is the maximum voltage; That is the minimum voltage.

[0086] 3. Line current

[0087]

[0088] In the formula, It is the current flowing along line l at time t; It is the maximum output current.

[0089] 4. Output range of distributed power sources:

[0090]

[0091]

[0092] In the formula, These are the active and reactive power at time t and h, respectively; These represent the maximum and minimum active power, respectively. These represent the maximum and minimum reactive power, respectively.

[0093] 5. Limitations on distributed power penetration:

[0094]

[0095] In the formula, It is the sum of the active power output of all distributed power sources at time t; This represents the maximum penetration rate of distributed power sources. It is the rated capacity of the substation.

[0096] 6. Electric vehicle charging station capacity:

[0097]

[0098] In the formula, It is the total active power of the k-th electric vehicle charging station at time t; This refers to the number of Class C charging stations; It is the active power of the c-th type charging pile at time t.

[0099] 7. Battery energy storage system charging and discharging power:

[0100]

[0101]

[0102] In the formula, These represent the charging and discharging power of the s batteries at time t, respectively. These are the rated charging and discharging power of the battery energy storage, respectively.

[0103] 8. State of charge of battery energy storage system:

[0104]

[0105] In the formula, Let be the energy storage capacity of the s-th battery at time t; These are the maximum and minimum energy storage capacities of the s-th battery, respectively.

[0106] Furthermore, in step 3, a distributed resource allocation model for the distribution network based on artificial intelligence and combined with OpenDSS power flow calculation is constructed, and the distributed resource allocation model for the distribution network is iteratively solved using a genetic algorithm (GA).

[0107] Power flow calculation models are a fixed-point iterative method for solving nonlinear equation systems. First, the nodal admittance matrices of the entire power distribution system are constructed. The matrix is ​​obtained by integrating the original admittance matrix of all circuit elements (lines, transformers, regulators, etc.). YThis is formed; then iterative solutions are performed.

[0108]

[0109] In the formula, It is the current passing through the power converter; It is a node j The voltage.

[0110] The flowchart of the AI-based optimization allocation method is as follows: Figure 2 As shown. Figure 2 The demonstrated process is a real-number encoded genetic algorithm, where the input data is the basic data of the distribution network (grid), including the node topology of the distribution network (such as the node connection relationship of the node system), line parameters (equivalent parameters of components such as resistance and reactance), bus voltage constraint range, line current limit, substation rated capacity, and load data.

[0111] Data related to the BESS battery energy storage system are shown in Table 1.

[0112] The data for EVCS electric vehicle charging stations are shown in Table 3.

[0113] The relevant data for DG distributed power generation are shown in Table 2.

[0114] The steps of the real-number encoded genetic algorithm are as follows:

[0115] (1) Initialization parameters: The initial population size is 1. The population dimension is The specific population consists of configuration schemes for battery storage nodes, electric vehicle charging station nodes, and distributed power generation nodes. , and These represent the number of battery storage nodes, electric vehicle charging station nodes, and distributed power generation nodes, respectively.

[0116] (2) Decode the individual node number in the population into an integer, call the power flow calculation of the distribution network containing resource allocation, simulate the system operation, and calculate the objective function value.

[0117] (3) Set the penalty function

[0118] Genetic algorithms are suitable for solving unconstrained optimization problems. By performing fitness evaluation and constraint handling, the constraints of power distribution network planning are "integrated" into the objective function as a penalty function, thus transforming a constrained optimization problem into a formally unconstrained one.

[0119] Specifically, fitness is calculated using the following formula:

[0120]

[0121] In the formula, It is the i-th individual; It is the value of the objective function; It is the base value of the penalty; It is the deviation value of the d-th constraint. Determine whether the stopping criterion has been met (the maximum number of iterations has been reached). If yes, output the optimal configuration positions of the battery storage node, electric vehicle charging station node and distributed power node; otherwise, execute (4).

[0122] (4) Iterative solution based on the selection, crossover, mutation and truncation process of genetic algorithm.

[0123] 1. Selection: First, the best individual is selected from the population. These selected individuals form a group that will proceed to the next genetic operator. A tournament selection method is used, where several rounds of competition are held between n solutions to select the best solution. In this invention's model, m individuals (m=3) are randomly selected from the population each time, and their fitness is compared (i.e., the smaller the objective function value, the higher the fitness). The individual with the best fitness is selected and placed into the "mating pool" to serve as the parent generation for the next generation. This process is repeated until the number of selected individuals is the same as the population size.

[0124] 2. Crossover: Recombination is performed on the parent individuals in the "mating pool" using Laplace crossover. Two parent individuals are randomly selected. , For each variable (i.e., each position in the vector), generate a random number that follows a Laplace distribution. .

[0125]

[0126] Generate two new offspring individuals ,

[0127]

[0128] In the formula, It is a random number uniformly distributed between [0,1]. It is a position parameter; It is a scaling parameter, and .

[0129] 3. Mutation: For the new population generated after crossover, perform power-law mutation. First, generate a random number 𝑠 that follows the power distribution. , It is a random number. , where is the mutation index. If the decision variable is an integer, then = .𝑛𝑡 Otherwise, if the decision variable is a real number, then 𝑝=𝑝 𝑟𝑒𝑎l . 𝑛𝑡 Represents the predefined integer-type decision variable mutation index; 𝑝 𝑟𝑒𝑎l This represents the pre-defined mutation index of real-valued decision variables.

[0130] Mutant solution:

[0131]

[0132]

[0133] In the formula, These are the lower and upper bounds of the decision variable, respectively; It is a random number that is uniformly distributed between [0,1]. Let l be the l-th decision variable.

[0134] 4. Truncation: Offspring with integer restrictions can be computed as real numbers. After crossover and mutation, the values ​​in an individual remain real numbers, but the node number must be an integer. If If it is an integer, then Otherwise for a real number Round down with a 50% probability. Or round up to 50% .

[0135] (5) Algorithm termination and optimal solution output: If the preset termination condition is met, the algorithm ends; otherwise, return to step (2) and finally output the global optimal solution.

[0136] In step S4, the distribution network basic data and the type, quantity and capacity of the distributed resources to be configured are used as inputs. The genetic algorithm is applied to solve the configuration model of the distributed resources of the distribution network and obtain the optimal configuration scheme of the distributed resources.

[0137] Compared to existing technologies, this solution offers the following advantages: it provides an artificial intelligence-based method for allocating power generation, load, and energy storage resources in a distribution network. It proposes a distributed resource framework for the distribution network that includes battery energy storage, electric vehicle charging stations, and distributed power sources. An AI-based solution method is constructed, and combined with power flow calculations, a genetic algorithm is used to iteratively solve the distributed resource allocation model, providing a scientific and effective method for allocating power generation, load, and energy storage resources in the distribution network. By applying this method, a reasonable optimization approach for allocating power generation, load, and energy storage resources in the distribution network can be provided. The effectiveness of the model is verified through implementation examples, clarifying the characteristics and advantages of this solution.

[0138] Figure 1 The illustrated embodiment includes the following steps:

[0139] Step S1 proposes a distributed resource framework for the power distribution network that includes battery energy storage, electric vehicle charging stations, and distributed power sources, establishes a mathematical model of the distributed resources, and quantifies the operational characteristics of the distributed resources.

[0140] The actual experiment will be conducted below:

[0141] (1) Selection of test system

[0142] An improved IEEE 34-bus system was chosen as the test case. This system includes unbalanced loads, parallel capacitors, voltage regulators, and transformers, such as... Figure 3 As shown. Figure 3 In this diagram, 800 is the substation exit node; 802 is the load and resource access node; 806 is the line junction node; 808 is the line junction node; 810 is the load node; 812 is the line junction node; 814 is the load node; 816 is the load node; 818 is the load node; 820 is the load node; 822 is the load node; 824 is the load node; 826 is the load node; 828 is the load node; 828 is the load and resource access node; 830 is the load node; 832 is the line junction node; 834 is the load and resource access node; 836 is the line junction node; 838 is the line junction node; 840 is the line junction node; 842 is the line junction node; 844 is the resource access node; 846 is the load node; 848 is the load node; 850 is the line junction node; 852 is the load node; 854 is the load node. 856 is a load node; 858 is a load node; 860 is a load node; 862 is a load node; 864 is a load node; 888 is a resource access node; 890 is a resource access node.

[0143] (2) Configuration object and parameter definition

[0144] The location allocation of one battery energy storage unit, three electric vehicle charging stations, and two distributed generator sets is defined, with specific parameter designs shown in Tables 1-3. The load is divided into three categories: residential, commercial, and industrial. The daily load curves for these three categories are shown below. Figure 4 As shown; the output of distributed photovoltaic power is determined by the solar radiation and temperature curves ( Figure 5 The decision was made by simulating the intermittency of renewable energy; suitable candidate nodes that can be connected to battery storage, electric vehicle charging stations and distributed power sources were selected, and each node was configured with at most one type of resource.

[0145] Table 1 Battery energy storage parameters

[0146]

[0147] Table 2 Distributed Power Generation Parameters

[0148]

[0149] Table 3 Parameters of Electric Vehicle Charging Stations

[0150]

[0151] (3) Optimize algorithm parameter settings

[0152] Furthermore, the parameters of the AI-based optimization algorithm were set as follows: number of individuals 300, number of iterations 50, crossover probability 0.80, mutation probability 0.005. , , , , .

[0153] (4) Optimize the output results

[0154] Figure 6 This represents the total power loss at different energy storage access locations. In the optimized final node location scheme for this example, the final optimized location node for the battery energy storage system is 888, the final optimized location nodes for the three electric vehicle charging stations are 802, 828, and 834, and the final optimized location nodes for the two photovoltaic distributed power sources are 890 and 844. Node 888 of the battery energy storage system is close to node 890, where the distributed power source is already installed, and is located in a high-current branch area. This allows for full utilization of the distributed power source's daytime power generation for charging, while simultaneously supplying power to surrounding high-demand loads during peak load periods. The battery energy storage system's operation strategy employs peak shaving and valley filling scheduling, with charging occurring during the distribution network's off-peak load period (8:00-16:00) and discharging during the peak load period (18:00-23:00), aligning with the daily load fluctuation patterns of the distribution network.

[0155] The optimized scheme has a minimum total active power loss of 1752 kWh. Figure 7 It is the daily active power loss curve of the distribution network.

[0156] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0157] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0158] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

[0159] Example 2:

[0160] The present invention also provides an apparatus corresponding to Embodiment 1. At the hardware level, this black-start partitioning device for a distribution network based on multiple types of distributed power sources includes a processor, an internal bus, a network interface, memory, and non-volatile memory, and may also include other hardware required for other operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The data acquisition method described above. Of course, in addition to software implementation, this invention does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0161] Improvements in a technology can be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology can now be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement in methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0162] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0163] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0164] Example 3:

[0165] This invention also proposes a computer-readable storage medium storing a program thereon, which, when executed, implements the method described in Embodiment 1. The computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves. The above-described functions, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for allocating power generation, load, and storage resources in a distribution network based on artificial intelligence, characterized in that, The method includes the following steps: Construct a power distribution network system model that includes battery energy storage, electric vehicle charging stations, and distributed power sources; Based on the model, a distributed resource allocation optimization model is constructed with the goal of minimizing power loss in the distribution network; The optimal configuration scheme for distributed resources is obtained by combining a power flow calculation model with a real-number encoded genetic algorithm to solve the configuration optimization model. The specific steps for solving the configuration optimization model using a power flow calculation model combined with a real-number encoded genetic algorithm to obtain the optimal configuration scheme for distributed resources are as follows: Construct the nodal admittance matrix of the entire power distribution system The matrix is ​​obtained by integrating the original admittance matrix of all circuit elements. Y This is formed, and then the voltage of each node is solved iteratively through a power flow calculation model; In the voltage input configuration optimization model of each node, the global optimal solution is then obtained by real number encoded genetic algorithm as the optimal configuration scheme; node j The voltage is: In the formula, It is the current passing through the power converter; It is a node j The voltage.

2. The method for allocating power distribution network source-load-storage resources based on artificial intelligence according to claim 1, characterized in that, The power distribution network system model includes: Battery energy storage model, electric vehicle charging station model, and distributed power source model.

3. The method for allocating power distribution network source-load-storage resources based on artificial intelligence according to claim 1, characterized in that, The configuration optimization model for distributed resources is as follows: In the formula, It is a collection of time periods; It is the collection of components in the system that generate power loss; It is the equivalent resistance of the component; It is the current flowing through component l during the time period 𝑡.

4. The method for allocating power distribution network source-load-storage resources based on artificial intelligence according to claim 1, characterized in that, The constraints of the optimization model include: Power balance, bus voltage limit, line current, output range of distributed power sources, penetration rate limit of distributed power sources, capacity of electric vehicle charging stations, charging and discharging power of battery energy storage systems, and state of charge of battery energy storage systems.

5. The method for allocating power distribution network source-load-storage resources based on artificial intelligence according to claim 1, characterized in that, The specific steps for finding the global optimal solution as the optimal configuration scheme using a real-number encoded genetic algorithm are as follows: (1) Initialization parameters: The initial population size is 1. ; (2) Decode the individual node numbers in the population into integers, and then convert the nodes... j The target function is input with voltage, and the target function value is calculated. (3) Set fitness: Fitness is: In the formula, It is the i-th individual; It is the value of the objective function; It is the base value of the penalty; It is the deviation value of the d-th constraint; (4) Iterative solution based on the selection, crossover, mutation and truncation process of genetic algorithm; (5) Algorithm termination and optimal solution output: If the preset termination condition is met, the algorithm ends; otherwise, return to step (2) and finally output the global optimal solution.

6. The method for allocating power distribution network source-load-storage resources based on artificial intelligence according to claim 5, characterized in that, The mutated solution during mutation is: In the formula, These are the lower and upper bounds of the decision variable, respectively; It is a random number uniformly distributed between [0,1]. Let be the l-th decision variable, and s represent the variable that follows the power distribution.

7. An artificial intelligence-based power distribution network source-load-storage resource allocation device, comprising a memory, a processor, and a program stored in the memory, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-6.

8. A storage medium having a program stored thereon, characterized in that, When the program is executed, it implements the method as described in any one of claims 1-6.

Images