A power distribution network load optimization method, device, equipment, medium and product

Abstract

The application discloses a power distribution network load optimization method, device, equipment, medium and product. It can be applied to the field of power distribution network management. The method comprises the following steps: for each iteration period, the historical individual optimization load of each particle and the historical global optimization load of the entire particle group are obtained; according to the historical individual optimization load and the historical global optimization load of the particle itself, the speed iteration update rule of the particle swarm optimization algorithm is combined, the power distribution network load optimization model and the corresponding constraint condition are comprehensively considered in the iteration process, the candidate load scheme under the current iteration period is generated, the fitness is calculated based on the candidate load scheme by using the power distribution network load optimization model and the real-time power distribution network operation data, the current individual optimization load of each particle is updated, and the global optimization load under the current iteration period is further selected from the current individual optimization load of all particles.

Description

Technical Field

[0001] This invention relates to the field of distribution network management, and in particular to a method, apparatus, equipment, medium and product for optimizing distribution network load. Background Technology

[0002] In the field of distribution network management, the scenario of distribution network load optimization and control is the core link to improve the utilization efficiency of distribution network facilities. It is directly related to the operating economy, asset lifespan and power supply reliability of the distribution network.

[0003] In existing distribution network load control methods, there is a lack of traditional static load allocation or single-objective optimization strategies. These methods lack iterative mining of distribution network operation data and dynamic optimization under multiple constraints. This can easily lead to poor adaptability between load control and the actual operating state of the power grid, and the optimization results may not be globally optimal. Consequently, the peak-valley difference in the distribution network is too large, and the load of facilities is unbalanced. Therefore, it is impossible to provide an efficient and reliable load optimization control method for the daily operation of the distribution network. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, medium, and product for optimizing the load of a power distribution network, thereby achieving load optimization and improving the utilization efficiency of power distribution network facilities.

[0005] According to one aspect of the present invention, a method for optimizing the load of a distribution network is provided, the method comprising: Obtain the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle; Based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and according to at least one constraint condition corresponding to the pre-set distribution network load optimization model, the current individual optimized load for the current iteration period is generated; the distribution network load optimization model is determined based on historical distribution network load data. Based on the current individual optimized load, and using the distribution network load optimization model and distribution network operation data, the current global optimized load under the current iteration cycle is determined. If the current iteration cycle meets the preset iteration end condition, then the current global optimized load is determined as the target load, and the distribution network load is optimized based on the target load.

[0006] According to another aspect of the present invention, a power distribution network load optimization device is provided, the device comprising: The load acquisition module is used to acquire the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle. The load generation module is used to generate the current individual optimized load under the current iteration cycle based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and at least one constraint condition corresponding to the pre-set distribution network load optimization model; the distribution network load optimization model is determined based on historical distribution network load data. The load determination module is used to determine the current global optimized load under the current iteration cycle based on the current individual optimized load, the distribution network load optimization model, and the distribution network operation data. The distribution network load optimization module is used to determine the current global optimized load as the target load if the current iteration cycle meets the preset iteration end condition, and to perform distribution network load optimization based on the target load.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the power distribution load optimization method of any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the power distribution network load optimization method of any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the power distribution network load optimization method of any embodiment of the present invention.

[0010] The technical solution of this invention obtains historical global optimized load, historical individual optimized load, and historical particle velocity vectors under historical iteration cycles. Based on these historical global optimized loads, historical individual optimized loads, and historical particle velocity vectors, and according to at least one constraint condition corresponding to a pre-set distribution network load optimization model, it generates the current individual optimized load for the current iteration cycle. The distribution network load optimization model is determined based on historical distribution network load data. Based on the current individual optimized load, the distribution network load optimization model, and distribution network operation data, the current global optimized load for the current iteration cycle is determined. If the current iteration cycle meets a preset iteration termination condition, the current global optimized load is determined as the target load, and distribution network load optimization is performed based on the target load. This enables precise iterative optimization of distribution network load based on historical iteration data, ensuring that the load optimization process conforms to the actual operating rules of the distribution network, guaranteeing the rationality and adaptability of the load optimization results, effectively improving the accuracy and scientific nature of distribution network load optimization, achieving efficient optimization of distribution network load, and thus improving the overall operating efficiency and facility utilization efficiency of the distribution network.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used 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 those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a power distribution network load optimization method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a power distribution network load optimization method according to Embodiment 2 of the present invention; Figure 3 This is a flowchart of a power distribution network load optimization method provided in Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of a power distribution network load optimization device according to Embodiment 4 of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device that implements a power distribution network load optimization method according to an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a distribution network load optimization method provided in Embodiment 1 of the present invention. This embodiment is applicable to distribution network load optimization scenarios in the field of distribution network management. The method can be executed by a distribution network load optimization device, which can be implemented in hardware and / or software and can be configured in electronic equipment. Figure 1 As shown, the method includes: S101. Obtain the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle.

[0017] S102. Based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and based on at least one constraint condition corresponding to the pre-set distribution network load optimization model, generate the current individual optimized load under the current iteration cycle; the distribution network load optimization model is determined based on historical distribution network load data.

[0018] S103. Based on the current individual optimized load, and using the distribution network load optimization model and distribution network operation data, determine the current global optimized load for the current iteration cycle.

[0019] S104. If the current iteration cycle meets the preset iteration end condition, then the current global optimization load is determined as the target load, and the distribution network load is optimized based on the target load.

[0020] Among them, the historical iteration period can be the previous solution iteration period relative to the current solution iteration period during the execution of the particle swarm optimization algorithm. The historical global optimized load can be the group optimal load value obtained by the particle swarm optimization algorithm in the historical iteration period. The optimized load can be the comprehensive active power load value of each node in the distribution network after load optimization and control. It is the core parameter characterizing the active power load control effect of the distribution network node. The historical individual optimized load can be the optimal load value corresponding to a single particle in the particle swarm in the historical iteration period. The historical particle velocity vector can be the load velocity value of a single particle in the particle swarm optimization algorithm in the historical iteration period, representing the adjustment step size and direction of the load of a single particle. The particle swarm optimization algorithm can be a stochastic optimization algorithm based on swarm intelligence that is pre-defined by relevant technical personnel. It maps the solution of the distribution network load optimization problem to the position of particles in the solution space. With load as the core optimization variable, it searches for the global optimal solution of distribution network load optimization by iteratively updating the position and velocity of particles.

[0021] For example, the relevant data of the first k iterations of the particle swarm optimization algorithm can be extracted from the iteration record database. The historical global optimization load is the load corresponding to the optimal group objective value of all particles in the first k iterations, the historical individual optimization load is the optimal load of a single particle in the solution space search in the first k iterations, and the historical particle velocity vector is the change in the load velocity parameter corresponding to the single particle obtained by solving the velocity update formula in the first k iterations.

[0022] The constraints can be pre-set by relevant technical personnel regarding the safe operation and load regulation of the distribution network. The distribution network load optimization model can be a model selected based on historical distribution network load data. The current iteration period can be the ongoing iterative calculation period of the particle swarm optimization algorithm. The current individual optimized load can be the load solution obtained by a single particle in the particle swarm after updating in the current iteration period.

[0023] For example, the historical global optimized load, the historical individual optimized load, and the historical particle velocity vector are substituted into the particle swarm optimization (PSO) velocity update formula pre-set by relevant technical personnel according to actual needs to calculate the new particle load velocity value for the current iteration cycle. Then, combined with the position update formula pre-set by relevant technical personnel, the particle load position is updated, ultimately generating the current individual optimized load that satisfies all preset constraints. For instance, the PSO velocity update formula can be set as: historical particle velocity vector × inertia coefficient + historical individual optimized load deviation × first learning factor + historical global optimized load deviation × second learning factor. If the historical particle velocity vector is 2MW, the historical individual optimized load deviation is 3MW, the historical global optimized load deviation is 4MW, the inertia coefficient is 0.8, the first learning factor is 0.5, and the second learning factor is 0.6; the PSO velocity update is: the current load adjustment velocity equals the historical particle velocity vector multiplied by the inertia coefficient, plus the historical individual optimized load deviation multiplied by the first learning factor, plus the historical global optimized load deviation multiplied by the second learning factor, substituting the values ​​yields 5.5MW.

[0024] Among them, the distribution network operation data can be the real-time monitoring data of the distribution network, such as the real-time or historical load, current, voltage, resistance, electricity price, and cable asset-related parameters of each branch. The current global optimal load can be the group optimal load value obtained by solving the current individual optimal load of all particles in the current iteration cycle through the distribution network load optimization model.

[0025] For example, the current individual optimized load is substituted into the filtered distribution network load optimization model, the objective function values ​​corresponding to all particles in the current iteration cycle are traversed, the individual optimal values ​​of all particles are compared, and the load solution with the optimal objective function value is selected as the current global optimized load.

[0026] The iteration termination condition can be a pre-defined condition set by relevant technical personnel to determine whether the iteration has ended. Examples include the objective function value of the distribution network load optimization model converging to a preset threshold, the number of iterations reaching a preset maximum, or the global optimum showing no significant change after multiple consecutive iterations. The target load can be the global optimum load value for distribution network load optimization finally obtained by the particle swarm optimization algorithm when the iteration termination condition is met.

[0027] For example, the difference between the objective function value of the model in the current iteration cycle and the objective function value of the previous iteration is calculated. If the difference is less than the preset convergence threshold, the iteration termination condition is met. The current global optimized load is then directly determined as the target load. Subsequently, load control strategies for each node of the distribution network at each time can be formulated based on the target load. The load of each node is adjusted according to the corresponding strategy to complete the load optimization and control of the distribution network.

[0028] The technical solution of this invention obtains historical global optimized load, historical individual optimized load, and historical particle velocity vectors under historical iteration cycles. Based on these historical global optimized loads, historical individual optimized loads, and historical particle velocity vectors, and according to at least one constraint condition corresponding to a pre-set distribution network load optimization model, it generates the current individual optimized load for the current iteration cycle. The distribution network load optimization model is determined based on historical distribution network load data. Based on the current individual optimized load, the distribution network load optimization model, and distribution network operation data, the current global optimized load for the current iteration cycle is determined. If the current iteration cycle meets a preset iteration termination condition, the current global optimized load is determined as the target load, and distribution network load optimization is performed based on the target load. This enables precise iterative optimization of distribution network load based on historical iteration data, ensuring that the load optimization process conforms to the actual operating rules of the distribution network, guaranteeing the rationality and adaptability of the load optimization results, effectively improving the accuracy and scientific nature of distribution network load optimization, achieving efficient optimization of distribution network load, and thus improving the overall operating efficiency and facility utilization efficiency of the distribution network.

[0029] Example 2 Figure 2 This is a flowchart of a distribution network load optimization method provided in Embodiment 2 of the present invention. This embodiment optimizes and improves upon the above-mentioned technical solutions. The step "Obtain historical distribution network load data, and based on the historical distribution network load data, perform model screening on deterministic models, robust optimization models, and distributed robust optimization models to obtain a distribution network load optimization model" is added to the step "Obtain historical global optimized load, historical individual optimized load, and historical particle velocity vector under historical iteration cycles". This improves the specific generation method of the distribution network load optimization model.

[0030] It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments. For example... Figure 2 As shown, the method includes the following specific steps: S201. Obtain historical distribution network load data, and based on the historical distribution network load data, perform model selection for deterministic model, robust optimization model and distributed robust optimization model to obtain distribution network load optimization model.

[0031] S202. Obtain the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle.

[0032] S203. Based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and based on at least one constraint condition corresponding to the pre-set distribution network load optimization model, generate the current individual optimized load for the current iteration cycle; the distribution network load optimization model is determined based on historical distribution network load data.

[0033] S204. Based on the current individual optimized load, and using the distribution network load optimization model and distribution network operation data, determine the current global optimized load for the current iteration cycle.

[0034] S205. If the current iteration cycle meets the preset iteration end condition, then the current global optimization load is determined as the target load, and the distribution network load is optimized based on the target load.

[0035] Among them, historical distribution network load data can be the load fluctuation amplitude of the distribution network in a preset historical period, which can be collected in advance by relevant technical personnel.

[0036] For example, the ratio of the actual fluctuation amplitude of the distribution network load to the nominal load value preset by relevant technical personnel is calculated. If the ratio is less than the threshold A preset by relevant technical personnel based on actual needs, that is, the load has no obvious random fluctuation and the operating state is stable, then a deterministic model is selected as the distribution network load optimization model; if the ratio is greater than the preset threshold A and less than or equal to the preset threshold B, then it is considered that the distribution network load only has deterministic fluctuations within a fixed range, and a robust optimization model is selected as the distribution network load optimization model; if the ratio is greater than the preset threshold B, then a distributed robust optimization model is selected as the distribution network load optimization model.

[0037] Furthermore, in order to improve the utilization efficiency of distribution network equipment under scenarios where the distribution network operation is stable and load parameters do not fluctuate randomly, in an optional embodiment, the deterministic model is constructed as follows: Step a1: Based on the optimized load, original load, and distribution network electricity price of different nodes at different times of different seasons in the distribution network operation data, construct the load value adjustment function.

[0038] Step a2: Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, construct the line loss cost function.

[0039] Step a3: Based on the cable replacement cost, construction cost, discount rate and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0040] Step a4: Construct a deterministic model based on the load value adjustment function, line loss cost function, and cable depreciation cost function.

[0041] The original load can be the initial active load value of each node in the distribution network before load optimization and control. The distribution network price can be the real-time price obtained in advance by relevant technical personnel. The load value adjustment function can be a function pre-set by relevant technical personnel to quantify the economic value generated by load optimization and adjustment of distribution network nodes.

[0042] For example, the load value adjustment function is expressed as follows: in, Represents the load value adjustment function. It is the set of all nodes. It is the first 1 node It is a collection of all seasons. It is the first Each season, It is the set of all sampling time points throughout the day. It is the first Each sampling time point It is the first In the The first of the seasons Optimize load in real time ， It is the first Node at the The first of the seasons The original load at any given moment, This represents the distribution network electricity price at time t.

[0043] In this context, a branch can be a power line connecting two nodes in a distribution network. The square of the branch current can be the square of the current transmitted by the branch in a unit of time. The branch resistance can be the inherent resistance of the branch itself. The line loss cost function can be a function pre-defined by relevant technical personnel to quantify the economic cost of power loss in a distribution network branch.

[0044] For example, the line loss cost function can be expressed as follows: in, For line loss cost function, It is the first The branch road is in The first of the seasons The square of the current at time _____. For the first The branch resistance of the strip, It is the set of all branches. It is the first A side road.

[0045] Among these, cable replacement cost refers to the cost of replacing underground cables in the distribution network with new ones after they have reached the end of their service life. Construction cost refers to the initial cost incurred when laying underground cables in the distribution network. The discount rate is the interest rate used to discount future cable replacement and construction costs to their present value. Cable lifespan refers to the effective service life of underground cables in the distribution network. The cable depreciation cost function is a pre-defined, quantifiable cost function for the entire lifespan of underground cables in the distribution network, set by relevant technical personnel.

[0046] For example, the cable depreciation cost function can be expressed as follows: in, This represents the cable depreciation cost function, where r represents the discount rate. No. The cost of replacing a branch road, It is the first The construction cost of the branch road, It is the first The lifespan of a branch cable.

[0047] The lifespan of a cable depends on its temperature, and the transient temperature rise of the cable can be divided into two parts. The first part is the transient temperature rise of the conductor based on the cable surface. Represented as: in, It's power loss. and It is the equivalent thermal resistance. and It is a time constant. The first part is the time step. The second part is the transient temperature rise of the soil around the cable based on ambient temperature. , is represented as: in, It is the total loss of each single-pole cable. It is the soil thermal resistivity. It is the thermal diffusivity of the soil. It is an exponential integral function. The axial burial depth of the hottest cable, It is the outer diameter of the cable. It is a cable to cable Distance from the center It is a cable to cable The distance from the center of the mirror image.

[0048] The thermal diffusivity of soil varies with soil moisture content, expressed as: in, It is the dry density of the soil. It refers to soil moisture content.

[0049] Total temperature rise of the cable The sum of the two temperature rises plus the ambient temperature is expressed as: in, It is a factor that quantifies the transient thermal effect of surface temperature on conductor temperature. It refers to the ambient temperature.

[0050] Based on the transient temperature rise model, the aging process of the cable under thermal stress was quantified and expressed as follows: in, It is thermal stress. This is a reference temperature. It is the ratio of activation energy to Boltzmann constant.

[0051] The daily lifetime loss of the cable is the cumulative loss over each time step, expressed as: in, It is the first Daily life loss of cables in branch circuits. It is the sum of all time steps in a day. No. The cable of the branch line is in the first The loss for each time step is expressed as: in, It is the first The cable of the branch line is in the first A constant temperature at a time step Lifespan at that time It is the first Each time step The infinitesimal interval for each time step.

[0052] Based on the daily life loss of the cable, the annual life loss is the cumulative daily life loss for all days of each season, expressed as: in, It is the first Annual lifespan loss of cables in a branch circuit. It is the first The number of days in each season.

[0053] According to Miller's cumulative damage theory, a cable fails when its daily lifespan loss accumulates to 1. Therefore, the cable's lifespan can be expressed as: in, It is the first The lifespan of the cables in each branch circuit, expressed in years.

[0054] Among them, the deterministic model can be a load optimization model built based on historical operating data of the distribution network and fixed parameters.

[0055] For example, the deterministic model is specifically represented as follows: The above technical solution constructs a multi-objective optimization model based on fixed operating parameters, incorporating load regulation benefits, line loss costs, and cable depreciation costs into a unified objective function for solution. This allows for the rapid generation of a globally optimized load allocation scheme under stable operating conditions, precise quantification of the economic benefits and asset depreciation costs of load optimization, and assurance of the economy and reliability of distribution network load regulation.

[0056] Furthermore, to address scenarios where distribution network load fluctuates and ensure the robustness of the load optimization scheme, thereby improving the operational stability of the distribution network under load fluctuation scenarios, in one optional embodiment, the robust optimization model is constructed as follows: Step b1: Based on the optimized load, uncertain original load, distribution network electricity price, and load uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, construct a load adjustment value function that considers load uncertainty.

[0057] Step b2: Based on the branch current square, branch resistance, and distribution network electricity price at different times and in different seasons of the distribution network operation data, construct the line loss cost function.

[0058] Step b3: Based on the cable replacement cost, construction cost, discount rate and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0059] Step b4: Construct a robust optimization model based on the load adjustment value function, line loss cost function, and cable depreciation cost function that take into account load uncertainty.

[0060] The load adjustment value function considering load uncertainty can be a function used to quantify the economic value of distribution network load regulation under load fluctuation scenarios, based on the difference between the optimized load and the uncertain original load. The uncertain original load can be the active power load variable that fluctuates around the original load within a defined range at different nodes of the distribution network in different seasons and at different times. The load uncertainty parameter can be a boundary parameter used to limit the maximum fluctuation range of the uncertain original load from the mean original load.

[0061] For example, the value function for load adjustment considering load uncertainty is expressed as follows: in, This represents an uncertain initial load. An uncertain initial load needs to meet certain conditions; specifically, it is a set of uncertainties. Represented as: in, It is the mean load. It is a parameter of load uncertainty.

[0062] For example, the line loss cost function can be expressed as follows: For example, the cable depreciation cost function can be expressed as follows: Among them, the robust optimization model can be an optimization model that introduces a set of load uncertainties to construct constraints with the goal of maximizing the total revenue under the worst load fluctuation scenario.

[0063] For example, the robust optimization model is specifically represented as follows: The above technical solution incorporates the load fluctuation boundary into the constraint conditions, solves the optimized load allocation scheme under the worst load scenario, effectively avoids the operational risks caused by load fluctuation, ensures that the load optimization scheme is feasible within the load fluctuation range, and takes into account the economic efficiency and robustness of the distribution network operation.

[0064] Furthermore, to address the uncertainty in load probability distribution caused by the distributed nature of distribution networks, and to balance the conservatism and economy of load optimization in order to improve the long-term operational reliability of distribution networks under complex and uncertain scenarios, in one optional embodiment, the distributed robust optimization model is constructed as follows: Step c1: Based on the optimized load, uncertain original load probability distribution, distribution network electricity price, and load distribution uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, construct a load adjustment value function that considers the uncertain load distribution.

[0065] Step c2: Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, construct the line loss cost function.

[0066] Step c3: Based on the cable replacement cost, construction cost, discount rate and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0067] Step c4: Construct a distributed robust optimization model based on the load adjustment value function, line loss cost function, and cable depreciation cost function that take into account uncertain load distribution.

[0068] The uncertain initial load probability distribution can be a probability distribution characteristic that the initial load of the distribution network follows, fluctuating around an empirical distribution. The load adjustment value function considering the uncertain load distribution can be a function constructed based on the difference between the optimized load and the uncertain initial load probability distribution, combined with the time-of-use pricing of the distribution network. The load distribution uncertainty parameter can be a sphere radius parameter used to limit the maximum Wasserstein distance of the uncertain initial load probability distribution from its distribution.

[0069] For example, the load adjustment value function considering uncertain load distribution is expressed as: in, This represents the probability distribution of the uncertain initial load. The values ​​of this probability distribution need to meet certain conditions, specifically, fuzzy sets. Represented as: in, yes The probability distribution, It is the probability distribution of the uncertain original load. and experience distribution Wasserstein distance distance ， Wasserstein distance), This represents the parameter of distribution uncertainty.

[0070] For example, the line loss cost function can be expressed as follows: For example, the cable depreciation cost function can be expressed as follows: Among them, the distributed robust optimization model can be a model that adapts to uncertain operating scenarios where the probability distribution of the distribution network load has drifted, based on the construction of fuzzy sets using Wasserstein distance and maximizing the expected total revenue under the worst probability distribution scenario.

[0071] For example, the distributed robust optimization model is specifically represented as follows: in, This represents the expected value.

[0072] The above technical solution incorporates the uncertainty of load probability distribution into the optimization framework and defines the distribution fluctuation range based on fuzzy sets. This can effectively avoid the problem of overly conservative traditional robust optimization. In the scenario of load distribution drift in the distribution network, it takes into account both operational economy and asset security, improves the adaptability of the distribution network to complex and uncertain operating environments, and achieves synergistic optimization of short-term load regulation benefits and long-term cable asset depreciation costs.

[0073] Furthermore, to ensure the safety, feasibility, and compliance with power grid operation constraints of distribution network load optimization and control, thereby improving the stability of distribution network operation, in one optional embodiment, the constraints include: The total daily load of each node in different seasons is within the preset range of the original total load.

[0074] The optimized load of each node at different times is within the adjustable ratio range of the original load.

[0075] The power factor of each node is not lower than the preset threshold.

[0076] The voltage at each node and the current in each branch are all within the preset safety range.

[0077] Specifically, the constraints can be: in, It is the minimum boundary coefficient. It is the maximum boundary coefficient. It is the first Adjustable ratio of flexible load at any time. It is the jth In the The first of the seasons The optimized net reactive load at any given time; It is the power factor threshold. yes for Downstream load, It is the jk branch in the 1st rank. The first of the seasons The load of time, yes for upstream load, Is the ij-th branch in the 1st... The first of the seasons The load of time, It is the jk branch in the 1st rank. The first of the seasons Net reactive load at any given time Is the ij-th branch in the 1st... The first of the seasons Net reactive load at any given time No. The reactance of the branch circuit, It is the first Node at the The first of the seasons The square of the voltage at time 10:00. It is the first Node at the The first of the seasons The square of the voltage at time 10:00. It is the minimum value of the square of the voltage. It is the maximum value of the square of the voltage. It is the maximum value of the square of the current.

[0078] The above constraints construct a multi-level constraint system from four dimensions: total load regulation, single-point load regulation range, power quality, and power grid equipment safety. This comprehensively limits the feasible solution space for distribution network load optimization, avoids large fluctuations in electricity demand caused by excessive load regulation, and achieves a synergistic unity between the economic efficiency of load optimization and the safety and feasibility of distribution network operation.

[0079] This embodiment constructs a concise model selection rule based on the actual fluctuation characteristics of historical distribution network load data, achieving accurate adaptation of the optimization model to the actual operation scenario of the distribution network. This avoids the problem of infeasible optimization schemes and increased operational risks caused by the neglect of uncertainties in the load fluctuation scenario by deterministic models. It also prevents distribution network operation losses caused by excessive conservatism in the low-fluctuation stable scenario by robust optimization and distributed robust optimization models, effectively improving the scenario adaptability of the load optimization model and the engineering feasibility of the optimization scheme.

[0080] Example 3 Figure 3 This is a flowchart illustrating a method for optimizing distribution network loads by differentiating types through modeling, as provided in Embodiment 3 of the present invention. Based on the above embodiments, this embodiment further provides preferred implementation methods for constructing deterministic, robust, and distributed robust optimization models respectively.

[0081] S301. If the distribution network load optimization model is a deterministic model, then execute S302-S305. If it is a robust optimization model, then execute S306-S309. If it is a distributed robust optimization model, then execute S310-S313.

[0082] S302. Based on the optimized load, original load, and distribution network electricity price of different nodes at different times of different seasons in the distribution network operation data, construct a load value adjustment function.

[0083] S303. Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, construct the line loss cost function.

[0084] S304. Based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0085] S305. Construct a deterministic model based on the load value adjustment function, line loss cost function, and cable depreciation cost function.

[0086] S306. Based on the optimized load, uncertain original load, distribution network electricity price, and load uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, construct a load adjustment value function that considers load uncertainty.

[0087] S307. Based on the branch current square, branch resistance and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, construct the line loss cost function.

[0088] S308. Based on the cable replacement cost, construction cost, discount rate and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0089] S309. Construct a robust optimization model based on the load adjustment value function, line loss cost function, and cable depreciation cost function that take into account load uncertainty.

[0090] S310. Based on the optimized load, uncertain original load probability distribution, distribution network electricity price, and load distribution uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, construct a load adjustment value function that considers uncertain load distribution.

[0091] S311. Based on the branch current square, branch resistance and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, construct the line loss cost function.

[0092] S312. Based on the cable replacement cost, construction cost, discount rate and cable life of each branch in the distribution network operation data, construct the cable depreciation cost function.

[0093] S313. Construct a distributed robust optimization model based on the load adjustment value function, line loss cost function, and cable depreciation cost function that take into account uncertain load distribution.

[0094] Example 4 Figure 4 This is a schematic diagram of a distribution network load optimization device provided in Embodiment 4 of the present invention. The distribution network load optimization device provided in this embodiment of the present invention is applicable to distribution network load optimization scenarios in the field of distribution network management. This distribution network load optimization device can be implemented in hardware and / or software, and can be applied to a distribution network load optimization method. Specifically, it can be configured in a controller, such as... Figure 4 As shown, the device includes: a load acquisition module 401, a load generation module 402, a load determination module 403, and a distribution network load optimization module 404. Wherein: The load acquisition module 401 is used to acquire the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle. The load generation module 402 is used to generate the current individual optimized load under the current iteration cycle based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and based on at least one constraint condition corresponding to the pre-set distribution network load optimization model; the distribution network load optimization model is determined based on historical distribution network load data. The load determination module 403 is used to determine the current global optimized load under the current iteration cycle based on the current individual optimized load, the distribution network load optimization model, and the distribution network operation data. The distribution network load optimization module 404 is used to determine the current global optimized load as the target load if the current iteration cycle meets the preset iteration end condition, and to perform distribution network load optimization based on the target load.

[0095] The technical solution of this invention obtains historical global optimized load, historical individual optimized load, and historical particle velocity vectors under historical iteration cycles. Based on these historical global optimized loads, historical individual optimized loads, and historical particle velocity vectors, and according to at least one constraint condition corresponding to a pre-set distribution network load optimization model, it generates the current individual optimized load for the current iteration cycle. The distribution network load optimization model is determined based on historical distribution network load data. Based on the current individual optimized load, the distribution network load optimization model, and distribution network operation data, the current global optimized load for the current iteration cycle is determined. If the current iteration cycle meets a preset iteration termination condition, the current global optimized load is determined as the target load, and distribution network load optimization is performed based on the target load. This enables precise iterative optimization of distribution network load based on historical iteration data, ensuring that the load optimization process conforms to the actual operating rules of the distribution network, guaranteeing the rationality and adaptability of the load optimization results, effectively improving the accuracy and scientific nature of distribution network load optimization, achieving efficient optimization of distribution network load, and thus improving the overall operating efficiency and facility utilization efficiency of the distribution network.

[0096] Optionally, the device further includes: The load optimization model construction module is used to acquire historical distribution network load data and, based on the historical distribution network load data, to screen deterministic models, robust optimization models, and distributed robust optimization models to obtain the distribution network load optimization model.

[0097] Optional, the load optimization model building module includes: The load value function construction unit is used to construct a load value adjustment function based on the optimized load, original load, and distribution network electricity price of different nodes at different times of different seasons in the distribution network operation data.

[0098] The cost function construction unit is used to construct the line loss cost function based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data.

[0099] The depreciation cost construction unit is used to construct the cable depreciation cost function based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the distribution network operation data.

[0100] The deterministic model building unit is used to build a deterministic model based on the load value adjustment function, the line loss cost function, and the cable depreciation cost function.

[0101] Optionally, the load optimization model building module also includes: The load uncertainty value function construction unit is used to construct a load adjustment value function that considers load uncertainty based on the optimized load, uncertain original load, distribution network electricity price, and load uncertainty parameters of different nodes in different seasons and at different times in the distribution network operation data.

[0102] The cost function construction unit is used to construct the line loss cost function based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data.

[0103] The depreciation cost construction unit is used to construct the cable depreciation cost function based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the distribution network operation data.

[0104] The robust optimization model construction unit is used to construct a robust optimization model based on the load adjustment value function considering load uncertainty, the line loss cost function, and the cable depreciation cost function.

[0105] Optionally, the load optimization model building module also includes: The value function construction unit is used to construct a load adjustment value function that considers uncertain load distribution based on the optimized load, uncertain original load probability distribution, distribution network electricity price, and load distribution uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data.

[0106] The cost function construction unit is used to construct the line loss cost function based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data.

[0107] The depreciation cost construction unit is used to construct the cable depreciation cost function based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the distribution network operation data.

[0108] The distributed robust optimization model construction unit is used to construct a distributed robust optimization model based on the load adjustment value function considering uncertain load distribution, the line loss cost function, and the cable depreciation cost function.

[0109] The power distribution network load optimization device provided in this embodiment of the invention can execute a power distribution network load optimization method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0110] Example 5 Figure 5A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0111] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded from storage unit 58 into the RAM 53. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0112] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as a power distribution network load optimization method.

[0114] In some embodiments, a distribution network load optimization method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the distribution network load optimization method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured as a distribution network load optimization method by any other suitable means (e.g., by means of firmware).

[0115] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0116] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0117] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0119] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0120] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0121] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for optimizing the load of a distribution network, characterized in that, include: Obtain the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle; Based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and according to at least one constraint condition corresponding to the pre-set distribution network load optimization model, the current individual optimized load for the current iteration period is generated; the distribution network load optimization model is determined based on historical distribution network load data. Based on the current individual optimized load, and using the distribution network load optimization model and distribution network operation data, the current global optimized load under the current iteration cycle is determined. If the current iteration cycle meets the preset iteration end condition, then the current global optimized load is determined as the target load, and the distribution network load is optimized based on the target load.

2. The method according to claim 1, characterized in that, The distribution network load optimization model includes a deterministic model, a robust optimization model, and a distributed robust optimization model; correspondingly, before obtaining the historical global optimized load, historical individual optimized load, and historical particle velocity vector under the historical iteration period, the model further includes: Historical distribution network load data is obtained, and based on the historical distribution network load data, the deterministic model, the robust optimization model, and the distributed robust optimization model are screened to obtain the distribution network load optimization model.

3. The method according to claim 2, characterized in that, The deterministic model is constructed as follows: Based on the optimized load, original load, and distribution network electricity price at different nodes in different seasons and at different times in the distribution network operation data, a load value adjustment function is constructed; and... Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, a line loss cost function is constructed. Based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the power distribution network operation data, a cable depreciation cost function is constructed. A deterministic model is constructed based on the load value adjustment function, the line loss cost function, and the cable depreciation cost function.

4. The method according to claim 2, characterized in that, The robust optimization model is constructed as follows: Based on the optimized load, uncertain original load, distribution network electricity price, and load uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, a load adjustment value function considering load uncertainty is constructed. as well as, Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, a line loss cost function is constructed. Based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the power distribution network operation data, a cable depreciation cost function is constructed. A robust optimization model is constructed based on the load adjustment value function considering load uncertainty, the line loss cost function, and the cable depreciation cost function.

5. The method according to claim 2, characterized in that, The distributed robust optimization model is constructed as follows: Based on the optimized load, uncertain original load probability distribution, distribution network electricity price, and load distribution uncertainty parameters of different nodes at different times of different seasons in the distribution network operation data, a load adjustment value function considering uncertain load distribution is constructed. as well as, Based on the branch current square, branch resistance, and distribution network electricity price of each branch in different seasons and at different times in the distribution network operation data, a line loss cost function is constructed. Based on the cable replacement cost, construction cost, discount rate, and cable life of each branch in the power distribution network operation data, a cable depreciation cost function is constructed. A distributed robust optimization model is constructed based on the load adjustment value function considering uncertain load distribution, the line loss cost function, and the cable depreciation cost function.

6. The method according to claim 1, characterized in that, The constraints may include: The total daily load of each node in different seasons is within the preset range of the original total load; The optimized load of each node at different times is within the adjustable ratio range of the original load; The power factor of each node is not lower than the preset threshold; The voltage at each node and the current in each branch are all within the preset safety range.

7. A power distribution network load optimization device, characterized in that, include: The load acquisition module is used to acquire the historical global optimization load, historical individual optimization load, and historical particle velocity vector under the historical iteration cycle; The load generation module is used to generate the current individual optimized load under the current iteration cycle based on the historical global optimized load, historical individual optimized load, and historical particle velocity vector, and at least one constraint condition corresponding to the pre-set distribution network load optimization model; the distribution network load optimization model is determined based on historical distribution network load data. The load determination module is used to determine the current global optimized load under the current iteration cycle based on the current individual optimized load, the distribution network load optimization model, and the distribution network operation data. The distribution network load optimization module is used to determine the current global optimized load as the target load if the current iteration cycle meets the preset iteration end condition, and to perform distribution network load optimization based on the target load.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the power distribution network load optimization method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the power distribution network load optimization method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the power distribution network load optimization method according to any one of claims 1-6.

Images