User power load real-time scheduling method and system, electronic device, and storage medium

Abstract

The application discloses a user power load real-time scheduling method and system, electronic equipment and a storage medium. When it is monitored that an overload condition occurs in a transformer of a transformer area, an optimization problem with the least number of users affected and the least influence on each user as optimization objectives is constructed, a user power load scheduling problem of the transformer area is converted into a mathematical model for multi-objective optimization solution, and the mathematical model is solved through a multi-objective particle swarm algorithm, so that a group of feasible solutions can be obtained. Users can select a required scheduling scheme from the group of feasible solutions according to actual conditions to perform scheduling, the fault tolerance is stronger, the number of users participating in scheduling can be reduced to the minimum in the scheduling process, the load adjustment of the users participating in scheduling is minimized, the influence of the scheduling task on the users under the transformer area is minimized, and the user satisfaction is best.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power Internet of Things, and in particular to a method and system for real-time scheduling of user power loads, electronic equipment, and a computer-readable storage medium. Background Art

[0002] With the accelerated construction of a new power system, enterprise-level real-time measurement centers aggregate data from all aspects of the power grid, providing data support for various businesses. For substation load monitoring, enterprise-level real-time measurement centers can aggregate real-time operating data from 10kV lines, substation transformers, and users, thereby monitoring the real-time load situation of the substation. However, statistics show that substation transformers experience thousands of severe overloads each year, leading to regional power outages. During the Spring Festival, many rural substation transformers are particularly prone to severe overloads due to the increase in people returning home. During the peak summer season, the significant increase in urban air conditioning loads can also cause severe overloads in urban substation transformers. While some methods currently exist for monitoring severe overloads in substations, these only extend from transformers to lines and then to substation transformers. Currently, there is no digital method to identify the specific users responsible for the increased load in a substation, making it impossible to implement targeted interventions, forcing power outages and affecting all users in the substation area.

[0003] When a substation transformer is severely overloaded, the previous dispatch method relies on manual experience to identify customers with excessive power consumption and then reduce the substation load by having them limit their power usage. However, this approach is inefficient, as it slows down processing once staff members are replaced. Furthermore, the lack of real-time data guidance makes user power adjustments unclear, and staff are unclear about how to dispatch to reduce the substation load to a safe level, often leading to over-dispatching. Clearly, the need to quickly, accurately, and scientifically guide user load adjustments based on data collected by an enterprise-level real-time measurement center is crucial to ensuring safe and economical operation of the substation. Specifically, how can we minimize the impact on as few customers as possible while minimizing the load adjustments required by these customers and restoring the load on the substation transformer to a healthy level? Summary of the Invention

[0004] The present invention provides a real-time scheduling method and system for user power load, electronic equipment, and a computer-readable storage medium to solve the technical problem that existing power load scheduling methods cannot achieve accurate scheduling.

[0005] According to one aspect of the present invention, a method for real-time scheduling of user power loads is provided, comprising the following:

[0006] Real-time collection of power load data of each user connected to the transformer in the substation area;

[0007] The power load of the transformer in the substation is monitored in real time. When the transformer is detected to be overloaded, an optimization problem is constructed with the minimum number of users affected and the minimum impact on each user as the optimization objectives, and a multi-objective particle swarm algorithm is used to solve the optimization problem.

[0008] The user's power load is dispatched in real time based on the solution results.

[0009] Furthermore, the optimization problem is:

[0010]

[0011] st

[0012]

[0013]

[0014] C3:x n ∈{0,1}

[0015] C4:y n ∈[L n ,H n ]

[0016] Where X={x1,x2,...,x N}, represents the binary set of power adjustment, N represents the number of users, x n If it is 1, it means that user n needs to adjust the power, x n If it is 0, it means that user n does not need to adjust the power, Y={y1,y2,...,y N}, represents the adjusted power set, y n is the power load value after adjustment for user n, K represents the upper limit of the number of users for power adjustment, γ represents the power safety threshold of the transformer in the substation, and L n and H n Respectively represent the user's minimum power value and maximum power value, λ n represents the weight coefficient of user n, P n represents the real-time power load value of user n, T n Indicates the package capacity reported by user n when connecting to the power grid.

[0017] Furthermore, the process of solving the optimization problem using the multi-objective particle swarm algorithm includes the following:

[0018] Initialize the particle swarm size to Np, randomly generate the initial position of each particle, and the particle position is expressed as {X, Y} = {x1, x2, ..., x N,y1,y2,...,y N};

[0019] Calculate the fitness value of each particle in the particle swarm, wherein the values ​​of the two functions are calculated as the fitness value of a particle according to the definition of the two objective functions in the optimization problem;

[0020] Initialize the particle's historical optimal position, global optimal position and initial archive;

[0021] Update the velocity and position of each particle, where the velocity update equation is v i =ω×v i +c1×r1×(pbset i -z i )+c2×r2×(gbest-z i ), the position update equation is z i =z i +v i , ω represents the inertia factor, c1 and c2 represent the acceleration factors, r1 and r2 represent random numbers between (0,1), z i Indicates the position of the i-th particle, pbset i represents the historical optimal position of the i-th particle, gbest represents the global optimal position, and v i represents the velocity of the i-th particle;

[0022] When the generated random number is greater than the perturbation probability, the new particle is randomly perturbed to generate a perturbed particle, otherwise the particle is not randomly perturbed;

[0023] Prune new particles and perturbed particles to make the particles meet the constraints;

[0024] Calculate the fitness value of each particle's next position and the disturbed position of the corresponding disturbed particle, and update the historical optimal position, global optimal position and archive according to the fitness value;

[0025] Iterates continuously until the maximum number of iterations is reached, and returns the particle position data in the archive.

[0026] Furthermore, in the process of randomly perturbing new particles to generate perturbed particles:

[0027] For particle i’s nth variable z i,n , first generate a random number, if the random number is less than the preset variable disturbance probability P m , then the variable z is calculated according to the following formula i,n Perform random perturbations to obtain new values

[0028]

[0029] in, represents the value of the nth variable of particle i after random perturbation, random(L n ,H n ) represents the interval [L n ,H n ] to generate a random number.

[0030] Furthermore, the perturbation probability is updated during the iteration based on the following formula:

[0031]

[0032] Among them, Pr represents the disturbance probability, P min and P max They represent the preset minimum and maximum perturbation probabilities, T represents the maximum number of iterations, and t represents the current number of iterations.

[0033] Furthermore, in the process of pruning new particles and disturbed particles so that the particles meet the constraints:

[0034] For solutions that do not satisfy constraint C3, the following formula is used to prune the first N variables:

[0035]

[0036] For solutions that do not satisfy constraint C4, the following formula is used to prune the last N variables:

[0037]

[0038] For a solution that does not satisfy constraint C1, randomly select an element with a value of 1 from the first N elements of the solution and flip it to 0. Repeat this operation until the solution satisfies constraint C1.

[0039] For the solution that does not satisfy the constraint C2, reduce the values ​​of the last N elements of the solution, that is:

[0040] z i,n =(1-α)z i,n ,n=N+1,N+2,...,2N

[0041] Among them, α represents the reduction factor, which is continuously reduced until the solution satisfies the constraint condition C2.

[0042] Furthermore, in the process of updating the historical optimal position, the global optimal position and archiving according to the fitness value:

[0043] If the current position of the particle dominates the next position and the disturbed position, the historical optimal position is the current position; if the next position of the particle dominates the current position and the disturbed position, the historical optimal position is the next position; if the disturbed position of the particle dominates the current position and the next position, the historical optimal position is the disturbed position; if the current position, next position and disturbed position of the particle do not dominate each other, one of the non-dominated positions is randomly selected as the historical optimal position;

[0044] According to the dominance relationship, the non-dominated solutions in the new and disturbed positions of all particles are added to the archive. A second round of screening is then performed based on the dominance relationship to eliminate the dominated solutions in the archive. Then, a non-dominated solution is randomly selected from the archive as the new global optimal position based on the congestion degree.

[0045] In addition, the present invention also provides a user power load real-time dispatching system, comprising:

[0046] The data acquisition module is used to collect the power load data of each user connected to the transformer in the substation in real time;

[0047] The optimization solution module is used to monitor the power load of the transformer in the substation in real time. When the transformer in the substation is detected to be overloaded, an optimization problem is constructed with the optimization objectives of minimizing the number of users affected and the minimum impact on each user. The optimization problem is solved using a multi-objective particle swarm algorithm.

[0048] The real-time scheduling module is used to perform real-time scheduling of user power loads based on the solution results.

[0049] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0050] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for real-time scheduling of user power loads, wherein the computer program executes the steps of the above-mentioned method when running on a computer.

[0051] The present invention has the following effects:

[0052] The real-time dispatching method of user power load of the present invention, when monitoring the overload of the transformer in the substation, converts the user power load dispatching problem of the substation into a mathematical model for multi-objective optimization solution by constructing an optimization problem with the least number of users affected and the minimum impact on each user as the optimization objectives, and solves the mathematical model through the multi-objective particle swarm algorithm to obtain a group of feasible solutions. The user can select a scheduling scheme that meets the requirements from the group of feasible solutions according to the actual situation for scheduling, which has stronger fault tolerance and can minimize the number of users participating in the scheduling during the scheduling process. At the same time, the load adjustment of the users participating in the scheduling is minimized, the impact of the scheduling task on the users in the substation is minimized, and the user satisfaction is the best.

[0053] In addition, the user power load real-time dispatching system of the present invention also has the above advantages.

[0054] In addition to the above-described objects, features and advantages, the present invention has other objects, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are intended to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a flow chart of a method for real-time dispatching of user power loads according to a preferred embodiment of the present invention.

[0057] Figure 2 It is a schematic diagram of a curve showing a change in the weight coefficient when the user's registered capacity is set to 1 in a preferred embodiment of the present invention.

[0058] Figure 3 yes Figure 1 Schematic diagram of the sub-process of step S2 in FIG.

[0059] Figure 4 Schematic diagram of the module structure of a real-time dispatching system for user power loads according to another embodiment of the present invention. DETAILED DESCRIPTION

[0060] The embodiments of the present invention are described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways as defined and covered below.

[0061] like Figure 1 As shown, a preferred embodiment of the present invention provides a method for real-time scheduling of user power loads, comprising the following contents:

[0062] Step S1: Real-time collection of power load data of each user connected to the transformer in the substation area;

[0063] Step S2: Monitor the power load of the transformer in the substation in real time. When the transformer in the substation is detected to be overloaded, an optimization problem is constructed with the minimum number of users affected and the minimum impact on each user as the optimization objectives, and a multi-objective particle swarm algorithm is used to solve the optimization problem.

[0064] Step S3: Perform real-time scheduling of user power loads based on the solution results.

[0065] It can be understood that the real-time scheduling method for user power load of this embodiment, when it is monitored that the transformer in the substation is overloaded, converts the user power load scheduling problem in the substation into a mathematical model for multi-objective optimization solution by constructing an optimization problem with the least number of users affected and the minimum impact on each user as the optimization objectives, and solves the mathematical model through the multi-objective particle swarm algorithm to obtain a set of feasible solutions. The user can select a scheduling scheme that meets the requirements from a set of feasible solutions according to the actual situation, which has stronger fault tolerance and can minimize the number of users participating in the scheduling during the scheduling process. At the same time, the load adjustment of the users participating in the scheduling is minimized, the impact of the scheduling task on the users in the substation is minimized, and the user satisfaction is the best.

[0066] It can be understood that in step S1, the enterprise-level real-time measurement center is integrated with the distribution automation system, the electricity consumption information collection system, and the marketing system to generate a "line-transformer-household" file relationship for the users in the substation area, thereby being able to collect the power load data of each user connected to the substation transformer in real time.

[0067] It is understood that in step S2, the enterprise-level real-time measurement center can collect the power load of the transformers in the substation area. If the power load of a transformer exceeds the preset threshold, it means that the transformer is overloaded, and the power consumption of users in the substation area needs to be adjusted. Conversely, if the power load does not exceed the threshold, it means that the transformer can operate normally and no adjustment is required. For each overloaded transformer, the following optimization problem is established:

[0068]

[0069] st

[0070]

[0071]

[0072] C3:x n ∈{0,1}

[0073] C4:y n ∈[L n ,H n ]

[0074] Where X={x1,x2,...,x N}, represents the binary set of power adjustment, N represents the number of users, x n If it is 1, it means that user n needs to adjust the power, x n If it is 0, it means that user n does not need to adjust the power, Y={y1,y2,...,y N}, represents the adjusted power set, y n is the power load value after adjustment for user n, K represents the upper limit of the number of users for power adjustment, γ represents the power safety threshold of the transformer in the substation, and L n and H n Respectively represent the user's minimum power value and maximum power value, λ n represents the weight coefficient of user n, P n represents the real-time power load value of user n, T n Indicates the package capacity reported by user n when connecting to the power grid.

[0075] Specifically, let P = {P1, P2, ..., P N} represents the power consumption of N users connected to the transformer, T n is the user capacity reported by user n when connecting to the grid, and γ represents the power safety threshold of the substation transformer. Therefore, the optimization goal of the present invention is to reduce the overall load below the threshold while affecting the minimum number of users and the minimum impact on each scheduled user. This optimization goal is essentially a multi-objective optimization problem. Specifically, when the transformer load exceeds the threshold, it is necessary to select a subset of users to reduce their power consumption. First, the selection of users for adjustment must affect as few users as possible, and second, the power adjustment for the selected subset must be as minimal as possible, meaning that the minimum number of appliances must be turned off to achieve the desired load reduction effect.

[0076] Define X={x1,x2,...,x N} represents the binary set of power adjustment, N represents the number of users, x n If it is 1, it means that user n needs to adjust the power, x n If it is 0, it means that user n does not need to adjust the power. Let Y = {y1,y2,...,y N} represents the adjusted power set, y n is the adjusted power load value of user n. Next, the optimization objective function 1 is established: And objective function 2: Among them, the weight coefficient When the actual power P of user n n Exceeding the reported capacity T nThe more , the greater the load adjustment of user n. For example, let T n =1, then λ n The curve is as Figure 2 As shown in Figure 2. Regarding objective function 2, the present invention uses weighted coefficients to adjust the power of scheduled users because overload in a substation is often caused by users who are overloading their electricity. If users are not differentiated, the probability of any user's electricity load being adjusted is the same, which is obviously unreasonable and, in serious cases, can even harm the rights and interests of normal electricity users. Therefore, weighting overloaded users can make the optimization strategy more reasonable, rather than treating all users equally, and the resulting solution will be more feasible.

[0077] In addition, the following constraints must be met during scheduling:

[0078]

[0079]

[0080] C3:x n ∈{0,1}

[0081] C4:y n ∈[L n ,H n ]

[0082] Among them, constraint C1 refers to adjusting the power load of at most K users, constraint C2 refers to the power load of the transformer after adjustment being lower than the safety threshold, and constraint C3 refers to x n The value is 0 or 1, constraining L in C4 n and H n Represents y n The minimum power value and the maximum power value of L n The purpose is to avoid the situation where all the user's electrical appliances are turned off in the solution.

[0083] Therefore, the optimization problem constructed in the present invention is:

[0084]

[0085] It is understandable that Figure 3 As shown, the process of solving the optimization problem using the multi-objective particle swarm algorithm includes the following:

[0086] Step S21: Initialize the particle swarm size to Np, randomly generate the initial position of each particle, and the particle position is expressed as {X, Y} = {x1, x2, ..., x N ,y1,y2,...,y N};

[0087] Step S22: Calculate the fitness value of each particle in the particle swarm, wherein the values ​​of the two functions are calculated according to the definitions of the two objective functions in the optimization problem as the fitness value of a particle;

[0088] Step S23: Initialize the particle's historical optimal position, global optimal position, and initial archive;

[0089] Step S24: Update the velocity and position of each particle, where the velocity update equation is v i =ω×v i +c1×r1×(pbset i -z i )+c2×r2×(gbest-z i ), the position update equation is z i =z i +v i , ω represents the inertia factor, c1 and c2 represent the acceleration factors, r1 and r2 represent random numbers between (0,1), z i Indicates the position of the i-th particle, pbset i represents the historical optimal position of the i-th particle, gbest represents the global optimal position, and v i represents the velocity of the i-th particle;

[0090] Step S25: When the generated random number is greater than the perturbation probability, the new particle is randomly perturbed to generate a perturbed particle; otherwise, the particle is not randomly perturbed;

[0091] Step S26: pruning the new particles and the disturbed particles so that the particles meet the constraints;

[0092] Step S27: Calculate the fitness value of each particle's next position and the disturbed position of the corresponding disturbed particle, and update the historical optimal position, global optimal position and archive according to the fitness value;

[0093] Step S28: Continuously iterate until the maximum number of iterations is reached, and return the particle position data in the archive.

[0094] Specifically, the particles are initialized first, the particle swarm size is Np, and the initial position of each particle is randomly generated. In the multi-objective particle swarm algorithm, the position of the particle represents a solution. In the present invention, the position of the particle can be expressed as z={X,Y}={x1,x2,...,x N ,y1,y2,...,y N}, that is, a vector of dimension 1×2N, let z i represents the position of the i-th particle.

[0095] Then, the fitness value of each particle in the particle swarm is calculated. Specifically, the values ​​of the two functions f1 and f2 in the optimization problem P1 are calculated, which are used as the fitness value of a particle.

[0096] Next, initialize the particle's historical optimal position pbest i For the initial particle position, an empty initial archive A is established, the non-dominated solutions in the particle are added to the initial archive A, and a solution is randomly selected from the initial archive A as the global optimal position gbest based on the congestion degree.

[0097] Then update the speed and position of each particle, where the speed update equation is v i =ω×v i +c1×r1×(pbset i -z i )+c2×r2×(gbest-z i ), the position update equation is z i =z i +v i ω represents the inertia factor, which is a non-negative real number, c1 and c2 represent the acceleration factors, both real numbers, r1 and r2 represent random numbers between (0,1), z i Indicates the position of the i-th particle, pbset i represents the historical optimal position of the i-th particle, gbest represents the global optimal position, and v i represents the velocity of the i-th particle.

[0098] Then, random perturbation is performed to generate a new solution. Specifically, each particle is randomly perturbed based on the perturbation probability Pr to increase the diversity of the population. When the generated random number is greater than the perturbation probability Pr, the new particle is randomly perturbed to generate a perturbed particle. Otherwise, the particle is not randomly perturbed. For each variable of the perturbed particle, based on the variable perturbation probability Pr, the new particle is randomly perturbed to generate a perturbed particle. m Perform the perturbation. Specifically, for the nth variable z of particle i, i,n , first generate a random number, if the random number is less than the preset variable disturbance probability P m , then the variable z is calculated according to the following formula i,n Perform random perturbations to obtain new values

[0099]

[0100] in, represents the value of the nth variable of particle i after random perturbation, random(L n ,H n ) represents the interval [L n ,Hn ] is a random number generated in [1]. Obviously, a new particle, namely the perturbed particle, can be obtained by performing the above perturbation process on each variable of particle i.

[0101] In addition, optionally, the perturbation probability is updated during the iteration based on the following formula:

[0102]

[0103] Among them, Pr represents the disturbance probability, P min and P max Represent the preset minimum and maximum perturbation probabilities, T represents the maximum number of iterations, and t represents the current number of iterations. It can be understood that in the early stages of the algorithm iteration, the perturbation probability is large, which can increase uncertainty. The initial particle quality is poor, and perturbation increases the probability of producing better particles, thereby accelerating the convergence of the algorithm. In the middle stages of the algorithm iteration, the particle quality is generally good, and the probability of perturbation producing better particles decreases. At this time, the perturbation probability value is halved to reduce the algorithm complexity. In the late stages of the algorithm iteration, the particle swarm is close to convergence, and the perturbation probability value is further reduced, making the algorithm iteration faster.

[0104] Due to the existence of constraints, the present invention also adds a pruning strategy, that is, pruning the positions of particles that do not meet the constraints. Specifically, in the process of pruning new particles and disturbed particles to make the particles meet the constraints:

[0105] For solutions that do not satisfy constraint C3, the following formula is used to prune the first N variables:

[0106]

[0107] That is, the value is first mapped to the interval [0,1]. If the mapped value is not less than 0.5, the value is clipped to 1, otherwise it is clipped to 0.

[0108] For solutions that do not satisfy constraint C4, the following formula is used to prune the last N variables:

[0109]

[0110] That is, the out-of-bounds value is directly trimmed to the value that meets the constraint.

[0111] For a solution that does not satisfy constraint C1, randomly select an element with a value of 1 from the first N elements of the solution and flip it to 0. Repeat this operation until the solution satisfies constraint C1. In addition, if the first N elements of the solution are all 0, randomly initialize the first N elements of the solution. This interpretation satisfies constraint C1.

[0112] For the solution that does not satisfy the constraint C2, reduce the values ​​of the last N elements of the solution, that is:

[0113] z i,n =(1-α)z i,n ,n=N+1,N+2,...,2N

[0114] Here, α is the reduction factor, a small constant that is continuously reduced until the solution satisfies constraint C2. Similarly, if the last N elements of the solution are all 0, a solution that satisfies constraint C2 is randomly generated.

[0115] It can be understood that the above pruning process ensures that the new position of the particle is a feasible solution that satisfies the constraints.

[0116] Then, the fitness value of each particle's next position is calculated. In addition, if a particle has a corresponding perturbed particle, the perturbed position of the perturbed particle must also be calculated. Then, the historical optimal position, the global optimal position, and the archive A are updated based on the fitness value. Specifically, the strategy for updating the historical optimal position is:

[0117] If the current position of the particle dominates the next position and the disturbed position, the historical optimal position is the current position; if the next position of the particle dominates the current position and the disturbed position, the historical optimal position is the next position; if the disturbed position of the particle dominates the current position and the next position, the historical optimal position is the disturbed position; if the current position, next position and disturbed position of the particle do not dominate each other, one of the non-dominated positions is randomly selected as the historical optimal position.

[0118] The strategy for updating the global optimal position and archiving A is:

[0119] Based on the dominance relationship, all non-dominated solutions from the new and perturbed positions of all particles are added to archive A. Because some solutions already exist in archive A, newly added non-dominated solutions may dominate previous solutions. Therefore, a second round of screening based on the dominance relationship is performed to remove the dominated solutions from archive A. Specifically, when the size of archive A exceeds a threshold, solutions are removed based on an adaptive grid. The higher the congestion level of a solution, the higher the probability of being removed. Finally, a non-dominated solution is randomly selected from the archive based on the congestion level as the new global optimal position.

[0120] Finally, after continuous iterations and reaching the maximum number of iterations, the position data of the particles in archive A is returned.

[0121] It can be understood that compared with the standard multi-objective particle swarm optimization algorithm, the multi-objective particle swarm optimization algorithm of the present invention combines the random perturbation mechanism and the pruning mechanism, so that the search ability of the particle swarm is significantly enhanced, and the generated solution satisfies the constraint conditions.

[0122] It can be understood that in step S3, the archive A output by step S2 is a set of feasible solutions for the optimization problem P1. The staff can select one of the feasible solutions to perform the scheduling task according to actual needs, thereby reducing the power load of the substation transformer to below the safety threshold.

[0123] In addition, if Figure 4 As shown, another embodiment of the present invention further provides a user power load real-time scheduling system, preferably using the above-mentioned scheduling method, the system comprising:

[0124] The data acquisition module is used to collect the power load data of each user connected to the transformer in the substation in real time;

[0125] The optimization solution module is used to monitor the power load of the transformer in the substation in real time. When the transformer in the substation is detected to be overloaded, an optimization problem is constructed with the optimization objectives of minimizing the number of users affected and the minimum impact on each user. The optimization problem is solved using a multi-objective particle swarm algorithm.

[0126] The real-time scheduling module is used to perform real-time scheduling of user power loads based on the solution results.

[0127] It can be understood that the user power load real-time dispatching system of this embodiment, when monitoring the overload of the substation transformer, converts the user power load dispatching problem of the substation into a mathematical model for multi-objective optimization solution by constructing an optimization problem with the least number of users affected and the minimum impact on each user as the optimization objectives, and solves the mathematical model through the multi-objective particle swarm algorithm to obtain a set of feasible solutions. The user can select a scheduling scheme that meets the requirements from a set of feasible solutions according to the actual situation, which has stronger fault tolerance and can minimize the number of users participating in the scheduling during the scheduling process. At the same time, the load adjustment of the users participating in the scheduling is minimized, the impact of the scheduling task on the users in the substation is minimized, and the user satisfaction is the best.

[0128] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the above method by calling the computer program stored in the memory.

[0129] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for real-time scheduling of user power loads, wherein the computer program executes the steps of the above-described method when running on a computer.

[0130] Common computer-readable storage media include: floppy disks, flexible disks, hard disks, magnetic tape, any other magnetic media, CD-ROMs, any other optical media, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash-erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. Instructions can further be transmitted or received via a transmission medium. The term transmission medium includes any tangible or intangible medium that can be used to store, encode, or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate communication of such instructions. Transmission media include coaxial cables, copper wire, and fiber optics, including the wires of a bus used to transmit a computer data signal.

[0131] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0132] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0133] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0137] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for real-time dispatching of user power load, characterized in that: Includes the following: Real-time collection of power load data of each user connected to the transformer in the substation area; The power load of the transformer in the substation is monitored in real time. When the transformer is detected to be overloaded, an optimization problem is constructed with the minimum number of users affected and the minimum impact on each user as the optimization objectives, and a multi-objective particle swarm algorithm is used to solve the optimization problem. Real-time dispatch of user power load based on the solution results; The optimization problem is: C3:x n ∈{0,1} C4:y n ∈[L n ,H n ] Where X={x1,x2,...,x N }, represents the binary set of power adjustment, N represents the number of users, x n If it is 1, it means that user n needs to adjust the power, x n If it is 0, it means that user n does not need to adjust the power, Y={y1,y2,...,y N }, represents the adjusted power set, y n is the power load value after adjustment for user n, K represents the upper limit of the number of users for power adjustment, γ represents the power safety threshold of the transformer in the substation, and L n and H n Respectively represent the user's minimum power value and maximum power value, λ n represents the weight coefficient of user n, P n represents the real-time power load value of user n, T n Indicates the package capacity reported by user n when connecting to the power grid.

2. The method for real-time dispatching of user power loads according to claim 1, wherein: The process of solving the optimization problem using the multi-objective particle swarm algorithm includes the following: Initialize the particle swarm size to Np, randomly generate the initial position of each particle, and the particle position is expressed as {X, Y} = {x1, x2, ..., x N ,y1,y2,...,y N }; Calculate the fitness value of each particle in the particle swarm, wherein the values ​​of the two functions are calculated as the fitness value of a particle according to the definition of the two objective functions in the optimization problem; Initialize the particle's historical optimal position, global optimal position and initial archive; Update the velocity and position of each particle, where the velocity update equation is v i =ω×v i +c1×r1×(pbset i -z i )+c2×r2×(gbest-z i ), the position update equation is z i =z i +v i , ω represents the inertia factor, c1 and c2 represent the acceleration factors, r1 and r2 represent random numbers between (0,1), z i Indicates the position of the i-th particle, pbset i represents the historical optimal position of the i-th particle, gbest represents the global optimal position, and v i represents the velocity of the i-th particle; When the generated random number is greater than the perturbation probability, the new particle is randomly perturbed to generate a perturbed particle, otherwise the particle is not randomly perturbed; Prune new particles and perturbed particles to make the particles meet the constraints; Calculate the fitness value of each particle's next position and the disturbed position of the corresponding disturbed particle, and update the historical optimal position, global optimal position and archive according to the fitness value; Iterates continuously until the maximum number of iterations is reached, and returns the particle position data in the archive.

3. The method for real-time dispatching of user power loads according to claim 2, wherein: In the process of randomly perturbing new particles to generate perturbed particles: For particle i’s nth variable z i,n , first generate a random number, if the random number is less than the preset variable disturbance probability P m , then the variable z is calculated according to the following formula i,n Perform random perturbations to obtain new values in, represents the value of the nth variable of particle i after random perturbation, random(L n ,H n ) represents the interval [L n ,H n ] to generate a random number.

4. The method for real-time dispatching of user power loads according to claim 2, wherein: During the iteration process, the perturbation probability is updated based on the following formula: Among them, Pr represents the disturbance probability, P min and P max They represent the preset minimum and maximum perturbation probabilities, T represents the maximum number of iterations, and t represents the current number of iterations.

5. The method for real-time dispatching of user power loads according to claim 2, wherein: In the process of pruning new particles and perturbed particles so that the particles satisfy the constraints: For solutions that do not satisfy constraint C3, the following formula is used to prune the first N variables: For solutions that do not satisfy constraint C4, the following formula is used to prune the last N variables: For a solution that does not satisfy constraint C1, randomly select an element with a value of 1 from the first N elements of the solution and flip it to 0. Repeat this operation until the solution satisfies constraint C1. For the solution that does not satisfy the constraint C2, reduce the values ​​of the last N elements of the solution, that is: With i,n =(1-α)z i,n ,n=N+1,N+2,...,2N Among them, α represents the reduction factor, which is continuously reduced until the solution satisfies the constraint condition C2.

6. The method for real-time dispatching of user power loads according to claim 2, wherein: In the process of updating the historical optimal position, the global optimal position and archiving according to the fitness value: If the current position of the particle dominates the next position and the disturbed position, the historical optimal position is the current position; if the next position of the particle dominates the current position and the disturbed position, the historical optimal position is the next position; if the disturbed position of the particle dominates the current position and the next position, the historical optimal position is the disturbed position; if the current position, next position and disturbed position of the particle do not dominate each other, one of the non-dominated positions is randomly selected as the historical optimal position; According to the dominance relationship, the non-dominated solutions in the new and perturbed positions of all particles are added to the archive. A second round of screening is then performed based on the dominance relationship to eliminate the dominated solutions in the archive. Then, a non-dominated solution is randomly selected from the archive as the new global optimal position based on the congestion degree.

7. A real-time dispatching system for user power load, characterized in that: include: The data acquisition module is used to collect the power load data of each user connected to the transformer in the substation in real time; The optimization solution module is used to monitor the power load of the transformer in the substation in real time. When the transformer in the substation is detected to be overloaded, an optimization problem is constructed with the optimization objectives of minimizing the number of users affected and the minimum impact on each user. The optimization problem is solved using a multi-objective particle swarm algorithm. Real-time scheduling module, used to perform real-time scheduling of user power loads based on the solution results; The optimization problem is: C3:x n ∈{0,1} C4:y n ∈[L n ,H n ] Where X={x1,x2,...,x N }, represents the binary set of power adjustment, N represents the number of users, x n If it is 1, it means that user n needs to adjust the power, x n If it is 0, it means that user n does not need to adjust the power, Y={y1,y2,...,y N }, represents the adjusted power set, y n is the power load value after adjustment for user n, K represents the upper limit of the number of users for power adjustment, γ represents the power safety threshold of the transformer in the substation, and L n and H n Respectively represent the user's minimum power value and maximum power value, λ n represents the weight coefficient of user n, P n represents the real-time power load value of user n, T n Indicates the package capacity reported by user n when connecting to the power grid.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the steps of the method according to any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium for storing a computer program for real-time scheduling of user power loads, characterized in that: When the computer program is run on a computer, the steps of the method according to any one of claims 1 to 6 are executed.

Images