A power distribution network weak period optimization scheduling method and device based on an adjustable capacity domain, a terminal device, and a storage medium

Abstract

The application discloses a power distribution network weak period optimization scheduling method and device based on an adjustable capacity domain, a terminal device and a storage medium, and belongs to the technical field of power dispatching. The method generates capacity demand domains of each new energy generation cluster in a plurality of randomly generated scenes in a prediction period according to generation prediction data of the new energy generation cluster, and then constructs a system adjustable capacity domain according to the optimization scheduling ability of energy storage systems and traditional units in each prediction period, calculates the adjustment capacity margin of the power distribution network in each prediction period under different scenes, constructs a key boundary matrix, quantifies the self-adjustment ability of the power distribution network under different periods, and finally generates an optimization scheduling scheme for improving the adjustment capacity margin of each weak period and implements scheduling. The method accurately identifies weak periods of the power distribution network with insufficient adjustment capacity, overcomes the difficulty of accurately identifying weak periods under uncertain scenes in the prior art, and effectively improves the stability of the power distribution network.

Description

Technical Field

[0001] This invention relates to the field of power dispatching technology, and in particular to a method, apparatus, terminal equipment, and storage medium for optimized dispatching of distribution networks during weak periods based on adjustable capacity domain. Background Technology

[0002] As the penetration rate of renewable energy sources such as wind and solar power in the power system continues to increase, the randomness, volatility, and intermittency of their output due to natural conditions are becoming increasingly prominent, posing a core challenge to the safe and stable operation of the power system and the optimization of dispatch efficiency. Against this backdrop, ensuring the safety and stability of the power grid hinges on accurately analyzing and assessing the power system's capacity to accommodate renewable energy fluctuations. The core prerequisite for this lies in scientifically identifying vulnerable periods in the power grid—critical periods under dynamic operating conditions when the system's self-regulation capabilities are insufficient and it is susceptible to power fluctuations.

[0003] In the field of identifying weak periods in the power grid, existing technical approaches mainly focus on two directions: one is based on power system state analysis methods, relying on numerical calculation methods such as power flow calculation, transient stability simulation, and voltage stability assessment to identify potential safety hazards from the perspective of system operation; the other is to use complex network theory to abstract the power grid into a topological graph composed of nodes and edges, and identify structural weaknesses by analyzing the characteristics of the network structure.

[0004] However, these traditional technologies have significant shortcomings. The main problem is that the identification of vulnerable periods is mostly focused on analyzing single scenarios and fails to cover dynamic scenarios with fluctuations in renewable energy. Under conditions of random changes in wind and solar power output, the power grid may be in a critical instability state at certain times, even without faults, due to insufficient regulation capacity. Existing methods are unable to accurately identify vulnerable periods under uncertain scenarios and cannot implement effective dispatching in a timely manner, resulting in insufficient stability of the distribution network. Summary of the Invention

[0005] This invention provides a method, apparatus, terminal equipment, and storage medium for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain. The method can solve the problem in the prior art that it is difficult to accurately identify weak periods under uncertain scenarios, and that it is impossible to implement effective scheduling in a timely manner, resulting in insufficient stability of the distribution network.

[0006] An embodiment of the present invention provides a method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain, comprising: The system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters are obtained; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional units. Based on the power generation forecast data, capacity demand domains are generated for each of the new energy power generation clusters in several randomly generated scenarios within the forecast period. Based on the state of charge and the output data, the system adjustable capacity domain is calculated to characterize the ability of energy storage systems and traditional units to participate in optimized scheduling in several consecutive time periods within the forecast period. Based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, the adjustment capacity margin of the distribution network in each continuous time period is calculated, and a critical boundary matrix is ​​constructed based on the adjustment capacity margin. Based on the critical boundary matrix, weak periods of insufficient distribution network regulation capacity are identified, and a corresponding weak period data is constructed based on load forecast data and power generation forecast data for each weak period. The system operation data and several weak period data are input into a preset scheduling optimization model so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. The new energy power generation cluster, the energy storage system, and the traditional generating units are scheduled according to the optimized scheduling scheme.

[0007] Furthermore, the power generation forecast data includes: the predicted total power generation of the new energy power generation cluster within the forecast period and its confidence level; The step of generating capacity demand domains for each of the new energy power generation clusters within several randomly generated scenarios during the forecast period, based on the power generation forecast data, includes: Obtain the planned power generation of each of the aforementioned new energy power generation clusters for each forecast period within the forecast cycle; Using the Monte Carlo method, based on the predicted total power generation and confidence level of each of the new energy power generation clusters, scenarios with different confidence levels are randomly generated, as well as the power generation of each predicted time period in each scenario. Based on the power generation and planned power generation of each of the new energy power generation clusters in each forecast period, calculate the power generation deviation rate of each of the new energy power generation clusters in each forecast period. Based on the continuous time period formed by several consecutive prediction periods within the prediction period, calculate the total predicted output deviation of each new energy power generation cluster in each continuous time period under each scenario, and construct the power deviation matrix of each new energy power generation cluster under each scenario based on the total predicted output deviation. Based on the power deviation matrix, the upward and downward capacity demand of the new energy power generation cluster in each continuous period are determined, and a capacity demand domain is constructed based on the upward and downward capacity demand.

[0008] Furthermore, the step of calculating the system adjustable capacity domain, based on the state of charge and the output data, to characterize the ability of the energy storage system and conventional generating units to participate in optimized scheduling over several consecutive time periods within the prediction period, includes: Obtain the first performance parameters of the energy storage system and the second performance parameters of the conventional unit; Based on the first performance parameters, construct the first set of constraint functions for the energy storage system; Based on the first set of constraint functions and the state of charge, the first upward adjustment capacity and the first downward adjustment capacity of the energy storage system under several consecutive time periods are generated, and based on the first upward adjustment capacity and the first downward adjustment capacity, the first adjustable capacity domain of the energy storage system is constructed. Based on the second performance parameter, construct the second set of constraint functions for the traditional unit; Based on the second set of constraint functions and the output data, the second upward adjustment capacity and the second downward adjustment capacity of the traditional unit under several consecutive time periods are generated, and based on the second upward adjustment capacity and the second downward adjustment capacity, the second adjustable capacity domain of the traditional unit is constructed. Based on the first adjustable capacity domain and the second adjustable capacity domain, a system adjustable capacity domain is constructed.

[0009] Furthermore, the step of calculating the adjustment capacity margin of the distribution network in each consecutive time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and constructing a critical boundary matrix based on the adjustment capacity margin, includes: Based on the load forecast data, determine the upward capacity margin threshold and the downward capacity margin threshold of the distribution network in each consecutive time period; The sum of the first and second increases in capacity under each consecutive period is taken as the total increase capacity. The sum of the increase capacity demand for each scenario under each consecutive period is taken as the total increase demand. The absolute value of the difference between the total increase capacity and the total increase demand under the corresponding consecutive period is taken as the increase capacity margin. The sum of the first and second reduction capacities in each consecutive time period is taken as the total reduction capacity. The sum of the reduction capacity demand for each scenario in each consecutive time period is taken as the total reduction demand. The absolute value of the difference between the total reduction capacity and the total reduction demand in the corresponding consecutive time period is taken as the reduction capacity margin. Set the upward capacity margin that is greater than the upward capacity margin threshold to 0, and set the downward capacity margin that is greater than the downward capacity margin threshold to 0. A critical boundary matrix is ​​constructed based on the upward and downward capacity margins for each consecutive time period.

[0010] Furthermore, determining the upward and downward capacity margin thresholds for the distribution network in each consecutive time period based on the load forecast data includes: Based on the forecast periods included in each consecutive time period, a first upward adjustment influence coefficient and a first downward adjustment influence coefficient are determined; wherein, the first upward adjustment influence coefficient and the first downward adjustment influence coefficient are positively correlated with the historical load data of each forecast period; The second upward adjustment impact coefficient and the second downward adjustment impact coefficient are determined based on the duration of each consecutive period; wherein the second upward adjustment impact coefficient and the second downward adjustment impact coefficient are positively correlated with the duration of each consecutive period. Based on the generated scenario, obtain the preset third upward adjustment influence coefficient and third downward adjustment influence coefficient; Calculate the weighted sum of the first upward adjustment impact coefficient, the second upward adjustment impact coefficient, and the third upward adjustment impact coefficient, and use it as the upward adjustment dynamic threshold for each consecutive time period; calculate the weighted sum of the first downward adjustment impact coefficient, the second downward adjustment impact coefficient, and the third downward adjustment impact coefficient, and use it as the downward adjustment dynamic threshold for each consecutive time period. Based on the load forecast data, the upward adjustment dynamic threshold, and the downward adjustment dynamic threshold, the upward adjustment capacity margin threshold and the downward adjustment capacity margin threshold for each consecutive time period are generated.

[0011] Furthermore, identifying weak periods of insufficient distribution network regulation capacity based on the critical boundary matrix includes: The continuous time periods in the critical boundary matrix where the upward or downward capacity boundary is not 0 are identified as weak periods.

[0012] Furthermore, the system operation data and several weak period data are input into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period, including: Construct an optimization constraint set; wherein the optimization constraint set includes: cost constraints, power imbalance constraints, first output constraints of traditional units, second output constraints of energy storage systems, new energy consumption constraints, and optimization constraints during weak periods; Based on the set of optimization constraints, construct the loss function; The data on the weak periods and the system operation data are input into a preset scheduling optimization model, so that the agent in the scheduling optimization model can generate an optimized scheduling scheme based on the loss function, with the goal of minimizing the weak periods and maximizing the adjustment capacity margin of each weak period.

[0013] An embodiment of the present invention also provides a distribution network weak period optimization scheduling device based on adjustable capacity domain, comprising: The data acquisition module is used to acquire the system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional unit. The capacity calculation module is used to generate capacity demand domains for each of the new energy power generation clusters in several randomly generated scenarios within the prediction period based on the power generation prediction data, and to calculate the system adjustable capacity domains to characterize the energy storage system and traditional units' ability to participate in optimized scheduling in several consecutive time periods within the prediction period based on the state of charge and the output data. The boundary calculation module is used to calculate the adjustment capacity margin of the distribution network in each continuous time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and to construct a key boundary matrix based on the adjustment capacity margin. The time period identification module is used to identify weak periods where the distribution network's regulation capacity is insufficient based on the key boundary matrix, and to construct a corresponding weak period data based on load forecast data and power generation forecast data for each weak period; The scheme generation module is used to input the system operation data and several weak period data into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. The optimized scheduling module is used to schedule the new energy power generation cluster, the energy storage system, and the traditional generating units according to the optimized scheduling scheme.

[0014] This application also provides a terminal device, including: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a distribution network weak period optimization scheduling method based on adjustable capacity domain as described in the above embodiments of the invention.

[0015] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for optimizing scheduling of distribution networks during weak periods based on adjustable capacity domains as described in the above embodiments.

[0016] The following benefits can be obtained by implementing the present invention: This invention provides a method, apparatus, terminal equipment, and storage medium for optimized scheduling of distribution networks during weak periods based on adjustable capacity domains. The method generates capacity demand domains for each new energy power generation cluster within several randomly generated scenarios during the prediction period, based on power generation forecast data. It considers the operational status of the new energy power generation clusters under various scenarios, and then constructs an adjustable capacity domain based on the optimization scheduling capabilities of energy storage systems and traditional generating units in each prediction period. It also calculates the adjustment capacity margin of the distribution network in each prediction period under different scenarios to construct a key boundary matrix, quantifying the self-regulation capability of the distribution network in different periods. This accurately identifies weak periods where the distribution network's adjustment capacity is insufficient, overcoming the difficulty of existing methods in accurately identifying weak periods under uncertain scenarios. Finally, based on the current system operation data of the distribution network and the weak period data for each weak period, an optimized scheduling scheme for improving the adjustment capacity margin of each weak period is generated and implemented, effectively improving the stability of the distribution network. Attached Figure Description

[0017] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for optimizing the scheduling of distribution networks during weak periods based on adjustable capacity domain, according to a certain embodiment of this application. Figure 2 This is a schematic diagram of the structure of a distribution network weak period optimization dispatching device based on adjustable capacity domain provided in a certain embodiment of this application; Figure 3 This is a schematic diagram of the structure of a terminal device provided in a certain embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0021] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0024] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0025] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0026] See Figure 1 To address the problems in the prior art, an embodiment of the present invention provides a method for optimizing the scheduling of distribution networks during weak periods based on adjustable capacity domain, comprising: S1. Obtain the system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional unit. In a preferred embodiment of the present invention, the prediction period is set to the next 24 hours. The new energy power generation cluster includes wind farms, photovoltaic power farms, hydropower farms, etc. The power generation prediction data consists of the predicted output value and corresponding confidence level of each new energy power generation cluster within the next 24 hours. This power generation prediction data is generated by an existing output prediction model based on historical output data and weather forecasts. In this embodiment, the conventional generating unit is set as a gas turbine. The energy storage system is an energy storage device configured in the distribution network.

[0027] S2. Based on the power generation forecast data, generate the capacity demand domain of each of the new energy power generation clusters in several randomly generated scenarios within the forecast period, and calculate the system adjustable capacity domain to characterize the energy storage system and traditional units' ability to participate in optimized scheduling in several consecutive time periods within the forecast period based on the state of charge and the output data. In a preferred embodiment of the present invention, considering two typical flexible resources—energy storage and generating units—the adjustable capacity domain of the system is formed by aggregating the flexible adjustable range of these resources using a Minkowski Sum-based spatial geometry adjustable capacity domain generation method. This constructs a flexibility constraint that covers the fluctuation range of the renewable energy cluster as much as possible, ensuring that the optimization results meet the feasibility requirements of all scenarios and serving as the technical basis for identifying weak periods based on the capacity domain. Specifically, based on probabilistic predictions of power generation forecast data, the quantile prediction results are organized into a quantile prediction matrix. Using the probability distribution information between quantiles, a capacity demand domain matrix is ​​constructed; and based on the generating unit parameters, a system capacity adjustable domain matrix is ​​constructed.

[0028] Preferably, the power generation forecast data includes: the predicted total power generation of the new energy power generation cluster within the forecast period and its confidence level; The step of generating capacity demand domains for each of the new energy power generation clusters within several randomly generated scenarios during the forecast period, based on the power generation forecast data, includes: The following steps are taken: First, obtain the planned power generation of each of the aforementioned new energy power generation clusters for each prediction period within the prediction period. Second, using the Monte Carlo method, randomly generate scenarios with different confidence levels and the power generation for each prediction period under each scenario, based on the predicted total power generation and confidence level of each of the aforementioned new energy power generation clusters. Third, calculate the power generation deviation rate of each of the aforementioned new energy power generation clusters for each prediction period based on the power generation for each prediction period and the planned power generation. Fourth, calculate the total predicted output deviation of each of the aforementioned new energy power generation clusters for each continuous period under each scenario, based on the continuous period formed by several consecutive prediction periods within the prediction period. Finally, construct a power deviation matrix for each of the aforementioned new energy power generation clusters under each scenario based on the total predicted output deviation. Fifth, determine the upward and downward capacity demand of each of the aforementioned new energy power generation clusters for each continuous period based on the power deviation matrix. Finally, construct a capacity demand domain based on the upward and downward capacity demand.

[0029] In a preferred embodiment of the present invention, in order to comprehensively describe the fluctuation characteristics of new energy power generation, the fluctuation domain is modeled from two dimensions: "upward fluctuation" and "downward fluctuation".

[0030] Based on the prediction results of total power generation from new energy sources at different confidence levels, and utilizing the probability distribution information between quantiles, a large number of random scenarios at different confidence levels are generated using the Monte Carlo method, as follows: ; In the formula, express Moment New Energy Power Generation The contribution of each scenario Indicates the total number of scenes.

[0031] To quantify the difference between renewable energy power generation output and planned output under different scenarios, a renewable energy power generation deviation rate is defined, and the calculation formula is as follows: In the formula, M represents the number of new energy power generation clusters. Let T be the number of scenarios in the m-th new energy power generation cluster scenario set, and T be the total number of optimization time periods. For the m-th new energy power generation cluster The power deviation rate of a scenario in time period t. For the m-th new energy power generation cluster The planned power generation capacity for the t-th time period in the given scenario For the m-th new energy power generation cluster The power generation during time period t in each scenario.

[0032] Considering all possible consecutive time periods within a day, the total predicted power output deviation is calculated, forming the power deviation matrix for this scenario, as follows: In the formula, For the m-th new energy power generation cluster Power deviation matrix for each scenario For the m-th new energy power generation cluster The total deviation of the predicted output from time period i to time period j in each scenario is expressed as: In the formula, Let m be the planned power output of the m-th new energy power generation cluster during time period t. To optimize the time period length, considering the maximum value of the total power deviation, a capacity demand domain for the new energy power generation cluster is constructed, expressed as: ; ; ; In the formula, Let m be the capacity demand matrix for the m-th renewable energy power generation cluster. Let be the reduced capacity demand matrix for the m-th new energy power generation cluster. Together, they constitute the capacity demand domain of the new energy power generation cluster. and These represent the upward and downward capacity demands of the m-th renewable energy power generation cluster from time period i to time period j. .

[0033] Preferably, the step of calculating the system adjustable capacity domain, which characterizes the ability of the energy storage system and conventional generating units to participate in optimized scheduling over several consecutive time periods within the prediction period, based on the state of charge and the output data, includes: The process involves: acquiring first performance parameters of the energy storage system and second performance parameters of the conventional generating unit; constructing a first set of constraint functions for the energy storage system based on the first performance parameters; generating a first upward adjustment capacity and a first downward adjustment capacity for the energy storage system over several consecutive time periods based on the first set of constraint functions and the state of charge, and constructing a first adjustable capacity domain for the energy storage system based on the first upward adjustment capacity and the first downward adjustment capacity; constructing a second set of constraint functions for the conventional generating unit based on the second performance parameters; generating a second upward adjustment capacity and a second downward adjustment capacity for the conventional generating unit over several consecutive time periods based on the second set of constraint functions and the output data, and constructing a second adjustable capacity domain for the conventional generating unit based on the second upward adjustment capacity and the second downward adjustment capacity; and constructing a system adjustable capacity domain based on the first adjustable capacity domain and the second adjustable capacity domain.

[0034] In a preferred embodiment of the present invention, a first set of constraint functions is constructed based on the first performance parameters of the energy storage system as follows: In the formula, For energy storage self-loss rate, For energy storage charging and discharging efficiency, , and These represent the maximum and minimum remaining energy storage capacity, and the remaining energy storage capacity at time t, respectively. For maximum charge and discharge power of energy storage, Let t represent the charging and discharging power of energy storage during time period t, where discharging is positive and charging is negative.

[0035] Based on energy storage constraints, the adjustable capacity domain is constructed as follows: ; ; ; In the formula, and These are the up-adjustment and down-adjustment capacity capability matrices for energy storage, which together constitute the first adjustable capacity domain of energy storage. and These represent the first upward adjustment capacity and the first downward adjustment capacity that energy storage can provide from time period i to time period j, respectively. .

[0036] Furthermore, to ensure that the unit constraints are met at any point within the adjustable range of the gas turbine, based on the second performance parameters of traditional units, the following second constraint function set is constructed, namely, the adjustable power at each time period should satisfy: ; ; ; The first equation represents the unit's output constraint, and the second equation represents the unit's ramp rate constraint.

[0037] In the formula, The output power of the gas turbine during time period t. and These represent the adjustable power output of the gas turbine during time period t, which can be increased and decreased respectively. and These represent the upper and lower limits of the gas turbine output, respectively. For gas turbine ramp rate, and These represent the adjustable power and adjustable power of unit n during time period t, respectively. If and only if their values ​​are positive, it indicates that unit n has an upward or downward adjustment margin during time period t.

[0038] Based on the adjustable power range of the gas turbine at different times, the adjustable capacity range of the gas turbine is constructed: ; ; ; In the formula, and These are the up-adjustment and down-adjustment capacity capability matrices for the gas turbine, which together constitute the adjustable capacity range of the gas turbine. and , These represent the second upward and second downward capacity that the gas turbine can provide from time period i to time period j.

[0039] The first and second upward capacity adjustments are integrated based on the corresponding continuous time periods, and the first and second downward capacity adjustments are integrated to form the system's adjustable capacity domain.

[0040] S3. Based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, calculate the adjustment capacity margin of the distribution network in each continuous time period, and construct a critical boundary matrix based on the adjustment capacity margin. Preferably, the step of calculating the adjustment capacity margin of the distribution network in each consecutive time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and constructing a critical boundary matrix based on the adjustment capacity margin, includes: Based on the load forecast data, determine the upward capacity margin threshold and downward capacity margin threshold for the distribution network in each consecutive time period; take the sum of the first upward capacity and the second upward capacity in each consecutive time period as the total upward capacity, take the sum of the upward capacity demand for each scenario in each consecutive time period as the total upward demand, and calculate the absolute value of the difference between the total upward capacity and the total upward demand in the corresponding consecutive time period as the upward capacity margin; take the sum of the first downward capacity and the second downward capacity in each consecutive time period as the total downward capacity, take the sum of the downward capacity demand for each scenario in each consecutive time period as the total downward demand, and calculate the absolute value of the difference between the total downward capacity and the total downward demand in the corresponding consecutive time period as the downward capacity margin; set the upward capacity margin greater than the upward capacity margin threshold to 0, and set the downward capacity margin greater than the downward capacity margin threshold to 0; construct a critical boundary matrix based on the upward capacity margin and the downward capacity margin in each consecutive time period.

[0041] In a preferred embodiment of the present invention, a critical boundary of the system capacity adjustable domain is defined. The critical boundary can provide the system dispatcher with important information about the physical weak periods of the power system, thereby enabling the effective identification of the weak periods of the power grid.

[0042] Based on the information of the system's adjustable capacity domain and capacity demand domain, a critical boundary matrix is ​​constructed: ; and , These represent the upward and downward capacity margin boundaries for the system from time period i to time period j, respectively. as well as These are the thresholds for increasing and decreasing capacity margin from time period i to time period j in scenario s, respectively.

[0043] Preferably, determining the upward and downward capacity margin thresholds for the distribution network in each consecutive time period based on the load forecast data includes: Based on the forecast periods included in each consecutive time period, a first upward adjustment influence coefficient and a first downward adjustment influence coefficient are determined; wherein, the first upward adjustment influence coefficient and the first downward adjustment influence coefficient are positively correlated with the historical load data of each forecast period; based on the duration of each consecutive time period, a second upward adjustment influence coefficient and a second downward adjustment influence coefficient are determined; wherein, the second upward adjustment influence coefficient and the second downward adjustment influence coefficient are positively correlated with the duration of each consecutive time period; based on the generated scenario, a preset third upward adjustment influence coefficient and a third downward adjustment influence coefficient are obtained; the weighted sum of the first upward adjustment influence coefficient, the second upward adjustment influence coefficient, and the third upward adjustment influence coefficient is calculated as the upward adjustment dynamic threshold for each consecutive time period; the weighted sum of the first downward adjustment influence coefficient, the second downward adjustment influence coefficient, and the third downward adjustment influence coefficient is calculated as the downward adjustment dynamic threshold for each consecutive time period; based on the load forecast data, the upward adjustment dynamic threshold, and the downward adjustment dynamic threshold, an upward adjustment capacity margin threshold and a downward adjustment capacity margin threshold for each consecutive time period are generated.

[0044] In a preferred embodiment of the present invention, the setting of the upward and downward capacity margin thresholds is based on the needs of safe and stable system operation and includes two parts: the operating reserve based on the load (i.e., load forecast data) as the benchmark value, and the dynamically adjustable capacity margin based on the uncertainty of new energy sources and output and load fluctuations. Considering that both are time-related, they are used to construct the identification of weak periods and the correlation between scenarios.

[0045] It is understandable that the vulnerability of the power grid varies at different times, such as the evening when load peaks or the midday when renewable energy sources are surging, and therefore the threshold should also vary. Secondly, the severity of a capacity shortage lasting one hour differs from that of a shortage lasting five hours, and the judgment criteria should also differ. Finally, under the current predicted scenario s, if the fluctuation range of renewable energy sources is already large, then the requirements for system margin are more stringent, i.e., the threshold is higher, to cope with greater uncertainty. Therefore, this embodiment designs the following threshold adjustment function to adaptively adjust the power grid regulation capacity margin threshold at different times based on scenario information, as follows: In the formula, , These are the load forecast data for time periods i to j, respectively. , The first upward adjustment impact coefficient and the first downward adjustment impact coefficient are for the weak period of time on the upward and downward adjustment of the capacity threshold. , These are the weighting coefficients of the function; The duration of the weak period is the second upward adjustment influence coefficient and the second downward adjustment influence coefficient on the capacity threshold. These are the weighting coefficients of the function; , The reaction is reflected in scenario s, during the period from i to j, when the range of upward fluctuations and downward fluctuations of new energy are weak, and the third upward adjustment influence coefficient and the third downward adjustment influence coefficient of the capacity threshold are identified. , These are the weight coefficients corresponding to the function, and the function values ​​have all been normalized.

[0046] S4. Based on the critical boundary matrix, identify the weak periods where the distribution network regulation capacity is insufficient, and construct a corresponding weak period data based on the load forecast data and power generation forecast data in each weak period. Preferably, identifying weak periods of insufficient distribution network regulation capacity based on the critical boundary matrix includes: determining continuous periods in the critical boundary matrix where the upward or downward capacity boundary is not 0 as weak periods.

[0047] In a preferred embodiment of the present invention, each element in the critical boundary matrix is ​​compared with the calculated upward capacity margin threshold and downward capacity margin threshold. If the upward capacity margin threshold is less than the upward capacity margin threshold, the continuous period is marked as an "upward weak period". If the downward capacity margin threshold is less than the downward capacity margin threshold, the period (i, j) is marked as a "downward weak period".

[0048] According to the formula in step S3, the upward capacity margin that is greater than the upward capacity margin threshold has been set to 0, and the downward capacity margin that is greater than the downward capacity margin threshold has been set to 0. Therefore, it is only necessary to identify the continuous time periods in the critical boundary matrix where the elements are not 0 as the weak time periods.

[0049] S5. Input the system operation data and several weak period data into a preset scheduling optimization model so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. Preferably, the step of inputting the system operation data and several weak period data into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period, includes: Construct an optimization constraint set; wherein the optimization constraint set includes: cost constraints, power imbalance constraints, first output constraints of traditional units, second output constraints of energy storage systems, new energy consumption constraints, and weak period optimization constraints; construct a loss function based on the optimization constraint set; input the weak period data and the system operation data into a preset scheduling optimization model, so that the agent in the scheduling optimization model generates an optimized scheduling scheme based on the loss function, with the goal of minimizing the weak period and maximizing the adjustment capacity margin of each weak period.

[0050] In a preferred embodiment of the present invention, the system operating cost, total power imbalance constraint, traditional unit output adjustment constraint, energy storage output adjustment constraint, and system weak period optimization constraint are used as physical information loss functions. A control decision intelligent agent based on a kind of autoencoder is selected. The model input is the current operating data of the power system and the weak period data, and the output is the output adjustment scheme of the weak period. The proposed optimized output scheme can be solved at a faster speed and with a higher control success rate while strictly meeting the constraints.

[0051] The scheduling model is constructed as a physical information loss function, using physical laws to constrain and control model decisions, increasing model complexity without adding parameters, thus balancing efficiency and accuracy. The loss function mainly consists of six parts: system operating cost, total power imbalance constraint, traditional unit output adjustment constraint, energy storage output adjustment constraint, system renewable energy absorption rate constraint, and system weak period optimization constraint.

[0052] 1) System operating costs: To minimize the cost of the system's output scheme, the loss function is constructed as follows: ; ; ; In the formula, Indicates the parameters of the upper-layer network; , These are the cost loss functions for traditional generating units and energy storage, respectively. Let be the output cost function of the i-th conventional generator unit; Let j be the energy storage unit's output cost function; , The cost of the i-th conventional unit and the j-th energy storage unit after optimized control; a, b, and c are the cost coefficients of the gas turbine; For energy storage costs; , These are the weighting coefficients for the traditional unit cost loss function and the energy storage loss function.

[0053] 2) Total power imbalance constraint: To ensure that the power output scheme meets the power balance requirements, the loss function is constructed as follows: ; In the formula, This is the loss function for power imbalance.

[0054] 3) Constraints on output adjustment of traditional units: To ensure that the adjusted power output scheme does not violate the ramping constraint compared to the original scheme, the loss function is constructed as follows: ; In the formula, This represents the constraint loss function for adjusting the output of traditional generating units. The amount of adjustment compared to the original plan is related to the unit's ramp rate.

[0055] 4) Constraints on energy storage output adjustment: To ensure that the adjusted power output scheme does not violate energy storage constraints compared to the original scheme, the loss function is constructed as follows: ; In the formula, This represents the loss function for adjusting energy storage output constraints. The amount of adjustment compared to the original plan is related to the charging and discharging efficiency of the energy storage.

[0056] 5) System renewable energy consumption rate constraint: Fluctuations in renewable energy output are the main factor causing periods of weakness. To ensure that the optimized strategy still has a sufficient absorption rate for renewable energy output, the loss function is constructed as follows: ; In the formula, The loss function is constrained by the system's renewable energy absorption rate. This is the requirement for the system's renewable energy consumption rate.

[0057] 6) Optimization constraints during system weak periods: The optimization constraints for weak periods mainly consider the reduction of weak periods and the increase of adjustable capacity margin during weak periods in the optimized output scheme. Therefore, the loss function is constructed as follows: ; In the formula, , These represent the loss function for optimizing weak periods and the loss function for optimizing adjustable capacity margins during weak periods, respectively; C represents the number of weak periods identified based on the critical boundary matrix. This refers to the set of identified vulnerable periods.

[0058] The overall loss function is expressed as a weighted sum of the above loss functions, as detailed below: ; In the formula, , , , , , These represent the weighting coefficients of the corresponding physical constraints in the loss function.

[0059] Furthermore, a decision-making agent for optimizing the control output scheme during weak periods of the system is constructed based on an autoencoder-like model. The autoencoder (AE) comprises an encoder network and a decoder network. Its main function is to train the system with the output value as close as possible to the input value, and it can be used for feature transformation to improve the performance of the neural network model. The optimization model for the control output scheme during weak periods of the system first uses an autoencoder for feature transformation, and then outputs the decision by a deep fully connected neural network. Its model input includes the output of traditional generating units, energy storage output, predicted output of new energy sources, and predicted load. Its output is the optimization strategy, which includes the output of traditional generating units, energy storage output, and new energy sources. The encoder represents the hidden layer from the input layer. Assuming the input is... The encoding process is as follows: ; In the formula, It is the output after encoding; For the encoder activation function, this method uses ReLU; It is the encoder's weight matrix; This is the encoder's offset vector. The decoder represents the portion from the hidden layer to the output layer; assuming the output is... The decoding process is as follows: ; In the formula, This is the output after decoding; Let be the activation function of the decoder, and be a linear function. It is the weight matrix of the decoder; It is the offset vector of the decoder.

[0060] The autoencoder uses minimizing the input-output error as its loss function and employs the backpropagation algorithm to iteratively train and update the weights and bias matrices. The loss function is shown below: In the formula, x is the input state; z is the latent feature.

[0061] The autoencoder performs feature transformation on the operating state, inputs the transformed features into a deep fully connected neural network, and then guides the training of the deep fully connected neural network model based on the physical information loss function to obtain the optimized result of the control output scheme for the weak period of the system that conforms to the physical laws.

[0062] S6. The new energy power generation cluster, the energy storage system and the traditional units are scheduled according to the optimized scheduling scheme.

[0063] In a preferred embodiment of the present invention, scheduling instructions for new energy power generation clusters, energy storage systems and traditional units are generated according to an optimized scheduling scheme, so that the new energy power generation clusters, energy storage systems and traditional units operate according to the corresponding scheduling instructions.

[0064] See Figure 2 This invention provides an embodiment of a distribution network weak-period optimization scheduling device based on adjustable capacity domain, comprising: The data acquisition module is used to acquire the system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional unit. The capacity calculation module is used to generate capacity demand domains for each of the new energy power generation clusters in several randomly generated scenarios within the prediction period based on the power generation prediction data, and to calculate the system adjustable capacity domains to characterize the energy storage system and traditional units' ability to participate in optimized scheduling in several consecutive time periods within the prediction period based on the state of charge and the output data. The boundary calculation module is used to calculate the adjustment capacity margin of the distribution network in each continuous time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and to construct a key boundary matrix based on the adjustment capacity margin. The time period identification module is used to identify weak periods where the distribution network's regulation capacity is insufficient based on the key boundary matrix, and to construct a corresponding weak period data based on load forecast data and power generation forecast data for each weak period; The scheme generation module is used to input the system operation data and several weak period data into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. The optimized scheduling module is used to schedule the new energy power generation cluster, the energy storage system, and the traditional generating units according to the optimized scheduling scheme.

[0065] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can realize the method of optimizing the scheduling of distribution network during weak periods based on adjustable capacity domain provided by any of the above-described method embodiments of the present invention.

[0066] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0067] See Figure 3 One embodiment of this application also provides a terminal device, including: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the above-described method for optimizing the scheduling of distribution networks during weak periods based on adjustable capacity domains.

[0068] The processor controls the overall operation of the terminal device to complete all or part of the steps of the aforementioned method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domains. The memory stores various types of data to support the operation of the terminal device. This data may include, for example, instructions for any application or method operating on the terminal device, as well as application-related data. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0069] In an exemplary embodiment, the terminal device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute a distribution network weak period optimization scheduling method based on adjustable capacity domain as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0070] In another exemplary embodiment, a computer-readable storage medium including a computer program is also provided. When executed by a processor, the computer program implements the steps of the distribution network weak-period optimization scheduling method based on adjustable capacity domain as described in any of the foregoing embodiments. For example, the computer-readable storage medium may be the aforementioned memory including the computer program, which may be executed by a processor of a terminal device to complete the distribution network weak-period optimization scheduling method based on adjustable capacity domain as described in any of the foregoing embodiments, and achieve the same technical effects as the aforementioned method.

[0071] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain, characterized in that, include: The system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters are obtained; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional units. Based on the power generation forecast data, capacity demand domains are generated for each of the new energy power generation clusters in several randomly generated scenarios within the forecast period. Based on the state of charge and the output data, the system adjustable capacity domain is calculated to characterize the ability of energy storage systems and traditional units to participate in optimized scheduling in several consecutive time periods within the forecast period. Based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, the adjustment capacity margin of the distribution network in each continuous time period is calculated, and a critical boundary matrix is ​​constructed based on the adjustment capacity margin. Based on the critical boundary matrix, weak periods of insufficient distribution network regulation capacity are identified, and a corresponding weak period data is constructed based on load forecast data and power generation forecast data for each weak period. The system operation data and several weak period data are input into a preset scheduling optimization model so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. The new energy power generation cluster, the energy storage system, and the traditional generating units are scheduled according to the optimized scheduling scheme.

2. The method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 1, characterized in that, The power generation forecast data includes: the predicted total power generation of the new energy power generation cluster within the forecast period and its confidence level; The step of generating capacity demand domains for each of the new energy power generation clusters within several randomly generated scenarios during the forecast period, based on the power generation forecast data, includes: Obtain the planned power generation of each of the aforementioned new energy power generation clusters for each forecast period within the forecast cycle; Using the Monte Carlo method, based on the predicted total power generation and confidence level of each of the new energy power generation clusters, scenarios with different confidence levels are randomly generated, as well as the power generation of each predicted time period in each scenario. Based on the power generation and planned power generation of each of the new energy power generation clusters in each forecast period, calculate the power generation deviation rate of each of the new energy power generation clusters in each forecast period. Based on the continuous time period formed by several consecutive prediction periods within the prediction period, calculate the total predicted output deviation of each new energy power generation cluster in each continuous time period under each scenario, and construct the power deviation matrix of each new energy power generation cluster under each scenario based on the total predicted output deviation. Based on the power deviation matrix, the upward and downward capacity demand of the new energy power generation cluster in each continuous period are determined, and a capacity demand domain is constructed based on the upward and downward capacity demand.

3. The method for optimizing the scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 2, characterized in that, The calculation of the system adjustable capacity domain, based on the state of charge and the output data, to characterize the ability of the energy storage system and conventional generating units to participate in optimized scheduling over several consecutive time periods within the forecast period, includes: Obtain the first performance parameters of the energy storage system and the second performance parameters of the conventional unit; Based on the first performance parameters, construct the first set of constraint functions for the energy storage system; Based on the first set of constraint functions and the state of charge, the first upward adjustment capacity and the first downward adjustment capacity of the energy storage system under several consecutive time periods are generated, and based on the first upward adjustment capacity and the first downward adjustment capacity, the first adjustable capacity domain of the energy storage system is constructed. Based on the second performance parameter, construct the second set of constraint functions for the traditional unit; Based on the second set of constraint functions and the output data, the second upward adjustment capacity and the second downward adjustment capacity of the traditional unit under several consecutive time periods are generated, and based on the second upward adjustment capacity and the second downward adjustment capacity, the second adjustable capacity domain of the traditional unit is constructed. Based on the first adjustable capacity domain and the second adjustable capacity domain, a system adjustable capacity domain is constructed.

4. The method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 3, characterized in that, The step of calculating the adjustment capacity margin of the distribution network in each consecutive time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and constructing a critical boundary matrix based on the adjustment capacity margin, includes: Based on the load forecast data, determine the upward capacity margin threshold and the downward capacity margin threshold of the distribution network in each consecutive time period; The sum of the first and second increases in capacity under each consecutive period is taken as the total increase capacity. The sum of the increase capacity demand for each scenario under each consecutive period is taken as the total increase demand. The absolute value of the difference between the total increase capacity and the total increase demand under the corresponding consecutive period is taken as the increase capacity margin. The sum of the first and second reduction capacities in each consecutive time period is taken as the total reduction capacity. The sum of the reduction capacity demand for each scenario in each consecutive time period is taken as the total reduction demand. The absolute value of the difference between the total reduction capacity and the total reduction demand in the corresponding consecutive time period is taken as the reduction capacity margin. Set the upward capacity margin that is greater than the upward capacity margin threshold to 0, and set the downward capacity margin that is greater than the downward capacity margin threshold to 0. A critical boundary matrix is ​​constructed based on the upward and downward capacity margins for each consecutive time period.

5. The method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 4, characterized in that, The step of determining the upward and downward capacity margin thresholds for the distribution network in each consecutive time period based on the load forecast data includes: Based on the forecast periods included in each consecutive time period, a first upward adjustment influence coefficient and a first downward adjustment influence coefficient are determined; wherein, the first upward adjustment influence coefficient and the first downward adjustment influence coefficient are positively correlated with the historical load data of each forecast period; The second upward adjustment impact coefficient and the second downward adjustment impact coefficient are determined based on the duration of each consecutive period; wherein the second upward adjustment impact coefficient and the second downward adjustment impact coefficient are positively correlated with the duration of each consecutive period. Based on the generated scenario, obtain the preset third upward adjustment impact coefficient and third downward adjustment impact coefficient; Calculate the weighted sum of the first upward adjustment impact coefficient, the second upward adjustment impact coefficient, and the third upward adjustment impact coefficient, and use it as the upward adjustment dynamic threshold for each consecutive time period; calculate the weighted sum of the first downward adjustment impact coefficient, the second downward adjustment impact coefficient, and the third downward adjustment impact coefficient, and use it as the downward adjustment dynamic threshold for each consecutive time period. Based on the load forecast data, the upward adjustment dynamic threshold, and the downward adjustment dynamic threshold, the upward adjustment capacity margin threshold and the downward adjustment capacity margin threshold for each consecutive time period are generated.

6. The method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 5, characterized in that, The process of identifying weak periods of insufficient distribution network regulation capacity based on the critical boundary matrix includes: The continuous time periods in the critical boundary matrix where the upward or downward capacity boundary is not 0 are identified as weak periods.

7. The method for optimized scheduling of distribution networks during weak periods based on adjustable capacity domain as described in claim 6, characterized in that, The process involves inputting the system operation data and several vulnerable time period data into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each vulnerable time period to improve the adjustment capacity margin of each vulnerable time period, including: Construct an optimization constraint set; wherein the optimization constraint set includes: cost constraints, power imbalance constraints, first output constraints of traditional units, second output constraints of energy storage systems, new energy consumption constraints, and optimization constraints during weak periods; Based on the set of optimization constraints, construct the loss function; The data on the weak periods and the system operation data are input into a preset scheduling optimization model, so that the agent in the scheduling optimization model can generate an optimized scheduling scheme based on the loss function, with the goal of minimizing the weak periods and maximizing the adjustment capacity margin of each weak period.

8. A distribution network weak period optimization dispatching device based on adjustable capacity domain, characterized in that, include: The data acquisition module is used to acquire the system operation data of the distribution network in the current time period, the load forecast data in the next forecast period, and the power generation forecast data of several new energy power generation clusters; wherein, the system operation data includes: the state of charge of the energy storage system and the output data of the traditional unit. The capacity calculation module is used to generate capacity demand domains for each of the new energy power generation clusters in several randomly generated scenarios within the prediction period based on the power generation prediction data, and to calculate the system adjustable capacity domains to characterize the energy storage system and traditional units' ability to participate in optimized scheduling in several consecutive time periods within the prediction period based on the state of charge and the output data. The boundary calculation module is used to calculate the adjustment capacity margin of the distribution network in each continuous time period based on the load forecast data, the capacity demand domain, and the system adjustable capacity domain, and to construct a key boundary matrix based on the adjustment capacity margin. The time period identification module is used to identify weak periods where the distribution network's regulation capacity is insufficient based on the key boundary matrix, and to construct a corresponding weak period data based on load forecast data and power generation forecast data for each weak period; The scheme generation module is used to input the system operation data and several weak period data into a preset scheduling optimization model, so that the scheduling optimization model outputs an optimized scheduling scheme for each weak period data to improve the adjustment capacity margin of each weak period. The optimized scheduling module is used to schedule the new energy power generation cluster, the energy storage system, and the traditional generating units according to the optimized scheduling scheme.

9. A terminal device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the distribution network weak period optimization scheduling method based on adjustable capacity domain as described in any one of claims 1-7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements a distribution network weak period optimization scheduling method based on adjustable capacity domain as described in any one of claims 1-7.

Images