Flexible load distribution and power supply optimization method and system

Abstract

The invention discloses a flexible load distribution and power supply optimization method and system, and relates to the technical field of electric power, and the method comprises the steps: collecting a load demand in an electricity utilization environment and the power supply capability of power supply equipment; carrying out first classification, and dividing the load into a multi-stage load set; based on the load demand and the power supply capability of the power supply equipment, solving a load distribution problem by using a dynamic programming algorithm; monitoring the operation state of a power utilization environment in real time, and adjusting a power supply strategy through a genetic algorithm; according to the invention, efficient matching of the load and the power supply resource is realized, the electric energy utilization rate and the power supply stability are remarkably improved, the energy waste and the unit power supply cost are reduced, the method is suitable for various complex power utilization environments, and the power supply mode is more intelligent and diversified.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a flexible load distribution and power supply optimization method and system. Background Art

[0002] With the continuous growth of electricity demand in modern power systems and the increasing complexity of the power consumption environment, traditional load distribution and power supply optimization methods have become difficult to cope with diverse load characteristics, dynamic power demand, uncertain power supply resources, and high requirements for system stability and cost optimization.

[0003] Existing technologies usually adopt fixed load distribution strategies or simple dynamic adjustment methods, which show obvious limitations when facing complex power consumption environments and diverse power supply resources. For example, they often cannot effectively balance the power supply needs of high-priority and low-priority loads, resulting in waste or insufficient resources; at the same time, the utilization efficiency of new energy is low, and it is difficult to respond to power supply fluctuations and load changes in a timely manner, resulting in decreased system stability and response speed. In addition, traditional power supply methods also lack flexibility in cost optimization and cannot give full play to the advantages of low-cost energy such as new energy, thereby increasing the overall power supply cost. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to achieve flexible allocation of loads and optimal configuration of power supply resources in a complex power consumption environment to improve power supply efficiency, system stability and economy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a flexible load distribution and power supply optimization method, including:

[0008] Collect the load demand in the power environment and the power supply capacity of the power supply equipment;

[0009] Performing a first classification, dividing the loads into multiple levels of load sets;

[0010] Based on the load demand and the power supply capacity of the power supply equipment, the load distribution problem is solved using the dynamic programming algorithm;

[0011] Monitor the operating status of the power consumption environment in real time and adjust the power supply strategy through genetic algorithms.

[0012] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0013] The load demand and power supply capacity of the power supply equipment in the power collection environment include:

[0014] The power demand of the load and the supply capacity of the power supply equipment are obtained in real time through sensors and monitoring systems.

[0015] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0016] The first classification of the loads into multiple load sets includes:

[0017] Divide the loads into multiple levels of load sets according to their priority, importance, and real-time requirements;

[0018] By calculating the comprehensive priority of the load, it is used to measure the importance and urgency of the load, wherein the comprehensive priority is calculated based on the importance level, urgency and real-time demand weight of the load;

[0019] The weight coefficients are determined to ensure that the sum of the importance level, urgency, and real-time demand of the load in the comprehensive priority of the load is 1.

[0020] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0021] The method of solving the load distribution problem by using a dynamic programming algorithm includes:

[0022] The load distribution is optimized through a dynamic programming algorithm, with the objective function of minimizing the power supply cost and satisfying the constraints of load power demand, power supply capacity limit of power supply equipment and non-negative power distribution.

[0023] Based on the required power and priority weighted value of the load, the optimal value of the first k loads when the power supply device capacity is j is calculated through recursive logic to optimize the allocation strategy of loads and power supply devices.

[0024] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0025] The recursive logic includes:

[0026] If the current power supply equipment capacity is insufficient to meet the needs of load k, the optimal value F(k-1,j) of the previous k-1 loads is directly used;

[0027] If the capacity is sufficient, compare the value of allocating load k with the value of not allocating load k and take the maximum value of the two.

[0028] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0029] The real-time monitoring of the operating status of the power environment and adjusting the power supply strategy through a genetic algorithm include:

[0030] Initialize the population, each individual represents a power supply scheme;

[0031] Select a population based on the fitness function; perform crossover and mutation operations on the population to generate a new power supply plan; repeat the iteration until the optimization goal is met or the preset number of iterations is reached.

[0032] As a preferred solution for flexible load distribution and power supply optimization method, wherein:

[0033] The fitness function is expressed as:

[0034]

[0035] Among them, f(X) represents the fitness value of the power supply scheme X, which represents the negative value of the total power supply cost;

[0036] C ij represents the unit power supply cost; X ij Indicates the power obtained by load i from power supply device j in the power supply scheme.

[0037] In a second aspect, an embodiment of the present invention provides a flexible load distribution and power supply optimization system, including:

[0038] The load and power supply capacity acquisition module is used to collect the load demand in the power environment and the power supply capacity of the power supply equipment;

[0039] A load multi-level classification module, used for performing a first classification to classify the load into a multi-level load set;

[0040] The load dynamic planning and allocation module is used to solve the load allocation problem using a dynamic programming algorithm based on load demand and the power supply capacity of the power supply equipment;

[0041] The power supply strategy optimization module is used to monitor the operating status of the power consumption environment in real time and adjust the power supply strategy through genetic algorithms.

[0042] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0043] Memory and processor;

[0044] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the flexible load distribution and power supply optimization method as described in any embodiment of the present invention.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the flexible load distribution and power supply optimization method.

[0046] Beneficial effects of the present invention: The present invention can achieve efficient matching of loads and power supply resources in a complex power consumption environment through a flexible load distribution and power supply optimization method, combined with a dynamic programming algorithm and a distributed optimization model. By allocating resources to key loads and high-priority loads first, the power consumption of non-essential loads is reduced, so that the overall power supply efficiency is significantly improved. Application scenario tests show that the present method can increase the utilization rate of electric energy by about 15%-30%, while effectively reducing energy waste; the system responds to power supply fluctuations and load changes in complex environments through real-time monitoring and feedback mechanisms combined with dynamic adjustment strategies. Especially in the scenario of coordinated power supply of new energy and traditional power grids, the present method can give priority to the use of new energy resources, reduce dependence on traditional power grids, and ensure the continuous and stable operation of key equipment. Experimental results show that after using the present method, the power supply stability of the system is improved by about 20%-25%, and the response time to load fluctuations is shortened by about 10%-20%; the present invention effectively reduces the unit power supply cost, especially in the new energy scenario, giving full play to the advantages of low-cost energy such as photovoltaics and wind power, and reducing the power supply cost of traditional power grids. In addition, the present method is suitable for a variety of complex power consumption environments such as industrial parks, data centers, smart grids and remote areas, and has strong flexibility and scalability. The application results show that electricity expenditure during peak hours is reduced by about 15%-25%, and the power supply mode is more intelligent and diversified. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0048] Figure 1 It is an overall flow chart of the flexible load distribution and power supply optimization method described in the first embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] Example 1

[0053] Reference Figure 1 , which is the first embodiment of the present invention, provides a flexible load distribution and power supply optimization method, including:

[0054] S1: Collect the load demand in the power environment and the power supply capacity of the power supply equipment;

[0055] S2: Perform the first classification to divide the load into multiple levels of load sets;

[0056] S3: Based on the load demand and the power supply capacity of the power supply equipment, the load distribution problem is solved using a dynamic programming algorithm;

[0057] S4: Monitor the operating status of the power environment in real time and adjust the power supply strategy through genetic algorithms.

[0058] It should be noted that through the implementation of steps S1 to S4, the system can achieve real-time matching of load demand and power supply capacity, efficiently allocate power supply resources, and dynamically adjust the power supply strategy through real-time monitoring and optimization to ensure efficient, reliable and intelligent operation of the system.

[0059] Example 2

[0060] Reference Figure 1 , which is an embodiment of the present invention, provides a flexible load distribution and power supply optimization method based on the previous embodiment, including:

[0061] In the embodiment of the present application, collecting the load demand in the power environment and the power supply capacity of the power supply equipment in the above step S1 includes:

[0062] Obtain the power demand P of the load in real time through sensors and monitoring systems i (t) and the supply capacity S of the power supply equipment j (t).

[0063] In the embodiment of the present application, the first classification is performed in the above step S2, and the loads are divided into multiple levels of load sets including:

[0064] According to the priority, importance and real-time requirements of the load, the load is divided into a multi-level load set L = {L1, L2, ..., Ln};

[0065] Specifically, the load priority is calculated using the following formula:

[0066] W i =α i ·R i +β i ·U i +γ i ·D i

[0067] Among them, W i Represents the comprehensive priority of load i, which is used to measure the importance and urgency of the load; R i Indicates the importance level of load i, indicating the impact of the load on the overall operation of the system, with a value range of [0,1]; U i Indicates the urgency of load i, indicating the load's dependence on real-time power supply, and its value range is [0,1]; D i represents the real-time demand weight of load i, which is calculated based on the current power demand of the load and has a value range of [0,1]; α i represents the importance weight, and represents R i The proportion in the priority, satisfying α i +

[0068] β i +γ i =1;β i represents the urgency weight, and represents U i The proportion in the priority; γ i represents the real-time demand weight, and represents D i The proportion in priority.

[0069] In another possible implementation, performing the first classification may further include the following implementation steps:

[0070] The collected load data is preprocessed to remove outliers and noise data to ensure the accuracy and reliability of the data.

[0071] Analyze the characteristics of each load, including its historical power usage data, power usage pattern, load type, etc., to better understand the load's power demand and behavior pattern.

[0072] According to the load characteristic analysis results, construct the characteristic matrix of each load. The matrix elements include the importance level R of the load i、Urgent i and real-time demand weight D i wait.

[0073] Considering the system operation objectives and load characteristics, determine the weight coefficient α i , β i and γ i The specific value of is used to ensure the rationality and effectiveness of load priority calculation.

[0074] During system operation, the load power demand changes are monitored in real time, and the load real-time demand weight D is dynamically updated. i , and adjust load priority.

[0075] According to the calculated load comprehensive priority W i , divide the loads into multi-level load sets of high priority, medium priority and low priority, ensuring that critical loads and high priority loads get power supply resources first.

[0076] The division results of multi-level load sets and load priority information are displayed visually, making it easier for system operators to monitor and adjust power supply strategies in real time.

[0077] Regularly re-evaluate and adjust load priorities, and dynamically optimize load priority ranking based on changes in load power demand and system operating status.

[0078] In the embodiment of the present application, solving the load distribution problem by using the dynamic programming algorithm in the above step S3 includes:

[0079] The optimization of power supply resource allocation is achieved through the following objective function:

[0080]

[0081] Constraints:

[0082] Meet load power requirements:

[0083]

[0084] Meet the power supply capacity restrictions of the power supply equipment:

[0085]

[0086] The allocated power is non-negative:

[0087]

[0088] Among them, C ij It represents the unit cost of load i obtaining electric energy from power supply equipment j (unit: yuan / kWh);

[0089] X ij Indicates the power allocated from load i to power supply device j (unit: kilowatt);

[0090] P i (t) represents the real-time power demand of load i (unit: kilowatt);

[0091] S j (t) represents the real-time power supply capacity of power supply device j (unit: kilowatt);

[0092] n represents the number of loads in the system;

[0093] m represents the number of power supply devices in the system.

[0094] Dynamic programming algorithm is used to optimize load distribution, and its recursive formula is:

[0095] F(k,j)=max{F(k-1,j),F(k-1,j-Pk)+Vk}

[0096] F(k,j) represents the optimal value of the first k loads when the capacity of the power supply equipment is j;

[0097] Pk represents the required power of load k (unit: kilowatt);

[0098] Vk represents the priority weighted value of load k;

[0099] j represents the current available capacity of the power supply equipment (unit: kilowatt).

[0100] Recursive logic:

[0101] If the current power supply equipment capacity is insufficient to meet the needs of load k, the optimal value F(k-1,j) of the previous k-1 loads is directly used;

[0102] If the capacity is sufficient, compare the value of allocating load k with the value of not allocating load k and take the maximum value of the two.

[0103] In the embodiment of the present application, in the above step S4, the operation status of the power environment is monitored in real time, and the power supply strategy is adjusted by the genetic algorithm, including:

[0104] Initialize the population, each individual represents a power supply scheme;

[0105] Select a population based on the fitness function; perform crossover and mutation operations on the population to generate a new power supply plan; repeat the iteration until the optimization goal is met or the preset number of iterations is reached.

[0106] The fitness function is expressed as:

[0107]

[0108] Among them, f(X) represents the fitness value of the power supply scheme X, which represents the negative value of the total power supply cost (used to transform the minimization problem into a maximization problem);

[0109] C ij represents the unit power supply cost (yuan / kWh); X ij Indicates the power (in kilowatts) obtained by load i from power supply device j in the power supply scheme.

[0110] In another possible implementation, the new energy power supply can be combined with the traditional power grid power supply, and the new energy power supply can be allocated preferentially through the following formula:

[0111]

[0112] Pnew(t) represents the new energy allocation power (unit: kilowatt);

[0113] Srenewable(t) represents the real-time power supply capacity of renewable energy (unit: kilowatt);

[0114] η represents the allocation efficiency factor, which indicates the priority of renewable energy in power supply, and its value range is [0,1];

[0115] Represents the real-time total power demand of all loads in the system.

[0116] In another possible implementation, a deep reinforcement learning model can also be used to optimize load distribution. The model state st includes the power demand of each load and the power supply capacity of the power supply device. The action at represents the adjustment strategy. The reward function is:

[0117]

[0118] st represents the current state of the system, including the load power demand P i (t) and power supply capacity S j (t);

[0119] at represents the adjustment action of the power supply strategy; Rt represents the reward value, which indicates the matching degree between the system power supply demand and power supply capacity. The closer the value is to zero, the better the match is.

[0120] Indicates the total power demand of all current loads;

[0121] Indicates the total power supply capacity of all current power supply devices.

[0122] Example 3

[0123] The above is a schematic scheme of the flexible load distribution and power supply optimization method of this embodiment. It should be noted that the technical scheme of the flexible load distribution and power supply optimization system and the technical scheme of the above-mentioned flexible load distribution and power supply optimization method belong to the same concept, and the details of the technical scheme of the flexible load distribution and power supply optimization system in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the above-mentioned flexible load distribution and power supply optimization method.

[0124] This embodiment also provides a system based on flexible load distribution and power supply optimization method, including:

[0125] The load and power supply capacity acquisition module is used to collect the load demand in the power environment and the power supply capacity of the power supply equipment;

[0126] A load multi-level classification module, used for performing a first classification to classify the load into a multi-level load set;

[0127] The load dynamic planning and allocation module is used to solve the load allocation problem using a dynamic programming algorithm based on load demand and the power supply capacity of the power supply equipment;

[0128] The power supply strategy optimization module is used to monitor the operating status of the power consumption environment in real time and adjust the power supply strategy through genetic algorithms.

[0129] This embodiment further provides a computing device, which is applicable to the case of the flexible load distribution and power supply optimization method, including:

[0130] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the flexible load distribution and power supply optimization method proposed in the above embodiment.

[0131] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the flexible load distribution and power supply optimization method proposed in the above embodiment is implemented.

[0132] The storage medium proposed in this embodiment and the flexible load distribution and power supply optimization method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0133] Example 4

[0134] Industrial Park Load Distribution Optimization

[0135] In an industrial park, various types of production equipment, office equipment and auxiliary equipment have different demands for power supply, which are classified according to importance and urgency:

[0136] Critical loads: such as production lines and industrial robots, belong to the L1 level and have the highest priority;

[0137] High priority loads: such as computer equipment in the office area, which belongs to the L2 level;

[0138] Low-priority loads: such as landscape lighting and non-essential equipment in the park, belong to the L3 level.

[0139] Calculate the comprehensive priority W of each load using the priority formula in the claim i :

[0140] W i =α i ·R i +β i ·U i +γ i ·D i

[0141] Based on real-time data, the system collects the power demand P of each device. i (t) and the urgency of its current working status U i .

[0142] With the dynamic programming algorithm as the core, the power distribution of each load is optimized, and the final result is as follows: the critical loads are given priority to obtain 90% of the power supply resources;

[0143] High-priority loads get some of the remaining resources without affecting critical loads;

[0144] Low priority loads automatically reduce power demand at night or when power is insufficient.

[0145] By implementing this method, the industrial park avoided downtime of key equipment during peak electricity consumption periods and reduced unnecessary waste of electricity.

[0146] Example 5

[0147] Data Center Power Optimization

[0148] In a certain data center, servers are divided into primary servers, backup servers, and auxiliary servers: Primary servers: such as trading system servers, have the highest priority (L1) and require constant power supply;

[0149] Backup server: The second highest priority (L2), which can partially reduce the load when the power supply is insufficient;

[0150] Auxiliary server: such as development and testing server, with the lowest priority (L3) and can be flexibly adjusted.

[0151] The data center uses the optimization objective function:

[0152]

[0153] Key data collected by the system include:

[0154] The power demand of the main server is P1(t) = 200kW;

[0155] The power demand of the backup server is P2(t) = 100 kW;

[0156] Power demand of auxiliary server P3(t) = 50kW; power supply capacity of new energy S renewable (t) = 250 kW;

[0157] Grid power supply capacity S grid (t) = 300kW Through calculation, the formula for priority allocation of new energy is:

[0158]

[0159] Among them, the new energy allocation efficiency η = 0.9. The system preferentially allocates 180kW of new energy power to the main server, and the remaining load is supplemented by the power supply of the grid.

[0160] Optimization results:

[0161] The main server load is fully met, the backup server obtains 80% of the power demand, and the auxiliary server power is reduced to 30%; the utilization rate of new energy reaches 90%, and the power supply cost is reduced by 15%.

[0162] Example 6

[0163] Smart Grid Distributed Optimization

[0164] In a smart grid with multiple power stations and load nodes, the system achieves load distribution through a distributed optimization method.

[0165] Assume the following power supply and load configuration:

[0166] Power station G1: power supply capacity S1(t) = 500kW;

[0167] Power station G2: power supply capacity S2(t) = 300kW;

[0168] Load nodes L1, L2, L3: total demands P1(t), P2(t), P3(t) are 200kW, 300kW and 250kW respectively.

[0169] Using distributed optimization formula:

[0170]

[0171] The adjustment step size λ=0.1.

[0172] After the initial allocation, each power station continuously iterates and adjusts the allocated power X ij , achieving balanced distribution of the entire network load.

[0173] The final result is: G1 allocates 300kW to supply nodes L1 and L2; G2 allocates 200kW to supply node L3. Through distributed optimization, the power grid achieves maximum resource utilization and avoids overload or no-load of a single power station.

[0174] Example 7

[0175] Coordinated optimization of new energy and traditional power grids

[0176] A remote mountainous area uses photovoltaic power generation as the main source of electricity, and supplements it with power from the power grid. The system adopts a new energy priority allocation strategy:

[0177]

[0178] Including: Photovoltaic power generation capacity S r enewable(t)=400kW;

[0179] Total load demand∑ i =1 n P i (t) = 600kW; new energy allocation efficiency η = 0.95.

[0180] After optimization, photovoltaic power generation gives priority to meeting critical loads L1 and high-priority loads L2, and the remaining loads are supplemented by grid power supply.

[0181] The results are as follows: Photovoltaic power generation provides 380kW; the grid provides 220kW.

[0182] This solution significantly improves the utilization rate of new energy, reduces power supply costs, and ensures the power supply stability of the system.

[0183] Example 8

[0184] Application of Deep Reinforcement Learning in Small Campuses

[0185] In a small park, the system uses deep reinforcement learning to optimize load distribution. The input of the model is the current load demand P. i (t) and power supply capacity S j (t), the output is the adjustment strategy a t .

[0186] The reward function is:

[0187]

[0188] Through continuous training, the model learns to prioritize the critical load L1 and dynamically adjust the required power of low-priority loads when the power supply capacity is insufficient.

[0189] The experimental results show that the power supply stability of key equipment in the park has been improved by 20% and the total power utilization rate has been increased by 15%.

[0190] The above-mentioned embodiments 4-8 illustrate the application of the present invention in different scenarios, and verify the high efficiency, real-time performance and reliability of its dynamic harmonic suppression. The present invention is applicable to various complex environments such as industrial power grids, household power grids and smart grids, and has broad application prospects.

[0191] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A flexible load distribution and power supply optimization method, characterized in that: include: Collect the load demand in the power environment and the power supply capacity of the power supply equipment; Performing a first classification, dividing the loads into multiple levels of load sets; Based on the load demand and the power supply capacity of the power supply equipment, the load distribution problem is solved using the dynamic programming algorithm; Monitor the operating status of the power consumption environment in real time and adjust the power supply strategy through genetic algorithms.

2. The flexible load distribution and power supply optimization method according to claim 1, characterized in that: The load demand and power supply capacity of the power supply equipment in the power collection environment include: The power demand of the load and the supply capacity of the power supply equipment are obtained in real time through sensors and monitoring systems.

3. The flexible load distribution and power supply optimization method according to claim 2, characterized in that: The first classification of the loads into multiple load sets includes: Divide the loads into multiple levels of load sets according to their priority, importance, and real-time requirements; By calculating the comprehensive priority of the load, it is used to measure the importance and urgency of the load, wherein the comprehensive priority is calculated based on the importance level, urgency and real-time demand weight of the load; The weight coefficients are determined to ensure that the sum of the importance level, urgency, and real-time demand of the load in the comprehensive priority of the load is 1.

4. The flexible load distribution and power supply optimization method according to claim 3, characterized in that: The method of solving the load distribution problem by using a dynamic programming algorithm includes: The load distribution is optimized through a dynamic programming algorithm, with the objective function of minimizing the power supply cost and satisfying the constraints of load power demand, power supply capacity limit of power supply equipment and non-negative power distribution. Based on the required power and priority weighted value of the load, the optimal value of the first k loads when the power supply device capacity is j is calculated through recursive logic to optimize the allocation strategy of loads and power supply devices.

5. The flexible load distribution and power supply optimization method according to claim 4, characterized in that: The recursive logic includes: If the current power supply equipment capacity is insufficient to meet the needs of load k, the optimal value F(k-1,j) of the previous k-1 loads is directly used; If the capacity is sufficient, compare the value of allocating load k with the value of not allocating load k and take the maximum value of the two.

6. The flexible load distribution and power supply optimization method according to claim 5, characterized in that: The real-time monitoring of the operating status of the power environment and adjusting the power supply strategy through a genetic algorithm include: Initialize the population, each individual represents a power supply scheme; Select a population based on the fitness function; perform crossover and mutation operations on the population to generate a new power supply plan; repeat the iteration until the optimization goal is met or the preset number of iterations is reached.

7. The flexible load distribution and power supply optimization method according to claim 6, characterized in that: The fitness function is expressed as: Among them, f(X) represents the fitness value of the power supply scheme X, which represents the negative value of the total power supply cost; C ij represents the unit power supply cost; X ij Indicates the power obtained by load i from power supply device j in the power supply scheme.

8. A system using the flexible load distribution and power supply optimization method according to any one of claims 1 to 7, characterized in that: include: The load and power supply capacity acquisition module is used to collect the load demand in the power environment and the power supply capacity of the power supply equipment; A load multi-level classification module, used for performing a first classification to classify the load into a multi-level load set; The load dynamic planning and allocation module is used to solve the load allocation problem using a dynamic programming algorithm based on load demand and the power supply capacity of the power supply equipment; The power supply strategy optimization module is used to monitor the operating status of the power consumption environment in real time and adjust the power supply strategy through genetic algorithms.

9. A computing device comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the flexible load distribution and power supply optimization method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the flexible load distribution and power supply optimization method according to any one of claims 1 to 7.

Images