Methods, apparatus and electronic equipment for determining power grid system strategies

Abstract

This invention discloses a strategy determination method, apparatus, and electronic device for a power grid system. The method includes: acquiring power grid state data of a target power grid system at the current time, wherein the target power grid system includes target equipment; retrieving an objective function corresponding to the target power grid system and corresponding objective constraints, wherein the objective function aims to minimize total network loss, and the objective constraints include voltage qualification rate constraints; the objective function includes voltage functions and network loss data items corresponding to multiple feeders, and the corresponding voltage functions are functions aimed at minimizing the network loss of the corresponding feeder; and solving the objective function based on the power grid state data and under the objective constraints to obtain the execution strategy corresponding to the target power grid system. This invention solves the technical problem in related technologies where control based on a determined power grid system execution strategy easily leads to poor system adaptability and economy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power systems, in particular to a power grid system strategy determination method and device and electronic equipment. BACKGROUND

[0002] Traditional power networks, such as main grid AVC systems, usually rely on control strategies based on fixed rules such as nine-zone diagrams and thirteen-zone diagrams, which have long control periods and high levels of discrete adjustment instructions, making it difficult to adapt to second-level voltage fluctuations caused by high proportions of distributed power access.

[0003] In related technologies, although the multi-agent collaborative control method based on reinforcement learning (such as MADDPG) can achieve hierarchical collaboration between substations and distribution networks, it also has the problem of poor system adaptability and economy when controlling according to the determined power grid system execution strategy.

[0004] To solve the above problems, no effective solutions have been proposed so far. SUMMARY

[0005] The embodiments of the present application provide a power grid system strategy determination method and device and electronic equipment to at least solve the technical problem of poor system adaptability and economy when controlling according to the determined power grid system execution strategy in related technologies.

[0006] According to an aspect of an embodiment of the present application, a power grid system strategy determination method is provided, comprising: obtaining power grid state data corresponding to a target power grid system at a current time, wherein the target power grid system includes a target device, the target device includes a transformer tap changer and a capacitor bank, and the power grid state data includes transformer tap changer position data and capacitor bank switching state data; calling a target function corresponding to the target power grid system and a target constraint corresponding to the target function, wherein the target function aims to minimize total network loss, the target constraint includes a voltage eligibility rate constraint, and the target function includes voltage functions corresponding to multiple feeder lines and network loss data items, the corresponding voltage function is a function aiming to minimize the network loss of the corresponding feeder line to determine the corresponding operating voltage; solving the target function under the target constraint according to the power grid state data to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy includes a transformer tap changer position strategy and a capacitor bank switching strategy.

[0007] Optionally, before the step of obtaining the target function, the method further comprises: determining a target voltage term corresponding to each of the plurality of feeders, and a target device action penalty term, wherein the target device action penalty term comprises an action cost term corresponding to each of the target devices and a gear change impact term; and constructing the target function according to the target device action penalty term, and a voltage function corresponding to each of the plurality of feeders, a loss data term, and the target voltage term.

[0008] Optionally, before the step of obtaining the target function, the method further comprises: determining a target voltage term corresponding to each of the plurality of feeders, and a target device action penalty term, wherein the target device action penalty term comprises an action cost term corresponding to each of the target devices and a gear change impact term; and constructing the target function according to the target device action penalty term, and a voltage function corresponding to each of the plurality of feeders, a loss data term, and the target voltage term.

[0009] Optionally, before the step of obtaining the target function, the method further comprises: determining a target voltage term corresponding to each of the plurality of feeders, a reference voltage term, a loss data term, and an adjustment weight term; for each feeder, determining a square of a difference between the target voltage term and the reference voltage term corresponding to the feeder to obtain a corresponding voltage difference square term; determining a product of the corresponding voltage difference square term and the corresponding adjustment weight term to obtain a corresponding voltage adjustment term; and determining a sum of the corresponding voltage adjustment term and the loss data term to obtain a voltage function corresponding to each of the plurality of feeders.

[0010] Optionally, before the step of obtaining the target constraint corresponding to the target function, the method further comprises: determining an extreme voltage term, wherein the extreme voltage term is a term corresponding to a voltage that is an extreme value among operating voltages corresponding to the plurality of feeders; determining a voltage deviation amount term corresponding to each of the plurality of feeders at a predetermined time; determining an upper limit value term and a lower limit value term corresponding to each of the plurality of feeders according to the extreme voltage term and the voltage deviation amount term corresponding to each of the plurality of feeders; and determining the voltage eligibility rate constraint according to the upper limit value term and the lower limit value term corresponding to each of the plurality of feeders.

[0011] Optionally, the step of determining the voltage deviation amount term corresponding to each of the plurality of feeders at the predetermined time comprises: determining a maximum absolute deviation ratio term according to the extreme voltage term and a reference voltage term; determining a feeder capacity term corresponding to each of the plurality of feeders and a load change amount term at the predetermined time; and determining the voltage deviation amount term corresponding to each of the plurality of feeders at the predetermined time according to the maximum absolute deviation ratio term, and the feeder capacity term corresponding to each of the plurality of feeders and the load change amount term at the predetermined time.

[0012] Optionally, before the target function is invoked, the method further comprises: determining, for each feeder, a target voltage term corresponding to each feeder, active power injection terms corresponding to the plurality of nodes on each feeder, reactive power injection terms, and resistance terms of line sections adjacent to the nodes; and determining, according to the target voltage term corresponding to each feeder, the active power injection terms corresponding to the plurality of nodes on each feeder, the reactive power injection terms, and the resistance terms of line sections adjacent to the nodes, the loss data term corresponding to each feeder.

[0013] According to an aspect of an embodiment of the present application, there is provided a strategy determination apparatus for a power grid system, comprising: an acquisition module configured to acquire power grid state data corresponding to a target power grid system at a current time, wherein the target power grid system comprises a target device, the target device comprising a transformer tap changer and a capacitor bank, and the power grid state data comprises transformer tap changer position data and capacitor bank switching state data; an invocation module configured to invoke a target function corresponding to the target power grid system and a target constraint corresponding to the target function, wherein the target function aims to minimize total loss, the target constraint comprises a voltage eligibility rate constraint, and the target function comprises voltage functions corresponding to a plurality of feeders and loss data terms, the corresponding voltage function being a function aiming to minimize loss of the corresponding feeder and used to determine a corresponding operating voltage; and a determination module configured to solve the target function under the target constraint according to the power grid state data to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy comprises a position strategy of the transformer tap changer and a switching strategy of the capacitor bank.

[0014] According to an aspect of an embodiment of the present application, there is provided an electronic device, comprising: a processor; and a memory configured to store instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the strategy determination method for a power grid system according to any one of the preceding embodiments.

[0015] According to an aspect of an embodiment of the present application, there is provided a computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement the strategy determination method for a power grid system according to any one of the preceding embodiments.

[0016] In the embodiment of the present application, the power grid state data corresponding to the target power grid system at the current time is acquired, wherein the target power grid system comprises a target device, the target device comprises a transformer tap, a capacitor bank, the power grid state data comprises transformer tap position data and capacitor bank switching state data; a target function corresponding to the target power grid system and a target constraint corresponding to the target function are called, wherein the target function aims to minimize the total network loss, the target constraint comprises a voltage eligibility rate constraint, and the target function comprises a voltage function corresponding to each of the plurality of feeders and a network loss data item, the corresponding voltage function is a function aiming to minimize the network loss of the corresponding feeder and used to determine the corresponding operating voltage; the target function is solved under the target constraint according to the power grid state data, to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy comprises a transformer tap position strategy and a capacitor bank switching strategy. It can be known that in the present application, the execution strategy is determined by using the target function, and the operating voltage and the network loss corresponding to the plurality of feeders are considered respectively due to the voltage function corresponding to each of the plurality of feeders and the network loss data item, the influence of the economic and adaptive differences of different feeders on the total network loss is considered, therefore, the execution strategy determined can be considered comprehensively, and the execution strategy determined has adaptability and economy, thereby solving the technical problem that the system adaptability and economy are poor when the power grid system execution strategy determined is controlled in the related art. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0018] Figure 1 It is a flowchart of a strategy determination method of a power grid system according to an embodiment of the present application;

[0019] Figure 2 It is a flowchart of a strategy execution method determination provided by an optional embodiment of the present application;

[0020] Figure 3 It is a structural block diagram of a strategy determination device of a power grid system according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0022] It is to be understood that the terminology "first", "second", and the like used in the specification and the claims of the application as well as the foregoing drawings may be used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of such terms as "first", "second", and the like, if they are used in the specification and / or claims of this disclosure, are also not necessarily used consistently in reference to terms for the same gauage throughout portions of the specification and claims unless otherwise indicated. Furthermore, the terms "comprise", "comprising", "include", "including", and the like, when used in the specification and / or claims of this disclosure, specifically do not serve as the exclusionary limits of for example, processes, methods, articles, or apparatuses comprising more than one step or unit, or as limitations to compositions of matter comprising more than one chemical or biological unit. Unless otherwise indicated, the use of relational terms, if any, such as "associated with", "comprises", "comprising", "including", "includes", "with" or "without", are used herein to establish a reciprocal or predictive relationship between or among two or more objects or variables.

[0023] Embodiment 1

[0024] According to an embodiment of the present application, an embodiment of a method for determining a strategy of a power grid system is provided. It is to be understood that the steps shown in the flowcharts of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0025] Figure 1 is a flowchart of a method for determining a strategy of a power grid system according to an embodiment of the present application, as shown in Figure 1 the method comprises the following steps:

[0026] Step S102, obtaining power grid state data corresponding to the target power grid system at the current time, wherein the target power grid system comprises a target device, the target device comprises a transformer tap, a capacitor bank, the power grid state data comprises transformer tap position data, and capacitor bank switching state data;

[0027] In the step S102 provided in the present application, the power grid state data corresponding to the target power grid system at the current time is obtained.

[0028] Among them, the target power grid system refers to a specific power network, and the system includes electrical equipment and lines in the power supply area, such as transformer substations, feeder lines, capacitor banks, and transformer taps. Alternatively, the target power grid system involved in the present application can be an AVC automatic voltage control power network.

[0029] Among them, the power grid state data refers to the actual operating parameters of the power network at a certain time, such as voltage, current, power factor, transformer tap position, and capacitor bank switching state.

[0030] Among them, the target device is involved, that is, the device in the target power grid system that needs to execute subsequent strategy regulation.

[0031] Among them, the transformer tap is involved, and the transformer tap position is a key parameter that affects the output voltage. By changing the tap position, the transformer ratio can be adjusted to control the grid voltage.

[0032] Among them, the capacitor bank is involved, and the capacitor bank is used to provide reactive power compensation in the power system. By switching the capacitor bank, the reactive power in the system can be adjusted to affect the grid voltage.

[0033] Among them, the transformer tap position data is involved, which indicates the current position of the transformer tap.

[0034] Among them, the capacitor bank switching state data is involved, which is data indicating whether each capacitor bank is in operation and the position of the input or output. It can be used to optimize the distribution of reactive power.

[0035] In step S102, the state data of the target power grid system is first collected in real time. By obtaining the position of the transformer tap and the switching state of the capacitor bank, the running condition of the power grid can be understood in real time, such as including voltage level and reactive power distribution. In order to provide accurate power grid running state information for the formulation of subsequent AVC strategy, ensure the real-time and accuracy of the control strategy.

[0036] Step S104, call the target function corresponding to the target power grid system, and the target constraint corresponding to the target function, wherein the target function minimizes the total network loss, the target constraint includes the voltage qualification rate constraint, the target function includes the voltage function corresponding to each feeder and the network loss data item, the corresponding voltage function is a function with the minimum network loss of the corresponding feeder as the target, for determining the corresponding operating voltage;

[0037] In the step S104 provided in the present application, the corresponding target function and the corresponding constraint condition are called.

[0038] Among them, the target function is involved, and the target function minimizes the total network loss, that is, reduces the energy loss in the process of power transmission through optimization strategy.

[0039] Among them, the target constraint is involved, which is used to constrain the target function. The target constraint in this step includes the voltage qualification rate constraint, that is, to ensure that the grid voltage is within the specified safe range, and to avoid power quality problems caused by voltage out-of-limit.

[0040] The voltage eligibility rate is an important indicator for measuring the voltage quality of the power system, and it defines the percentage of the voltages of the nodes in the power grid within the specified range. Optionally, other constraints can also be included in the system. However, one of the target constraints of the system is to ensure the voltage eligibility rate, that is, to ensure that the voltages of all nodes in the power grid are maintained within the allowed fluctuation range, avoiding damage to equipment or affecting power quality due to excessively high or low voltage.

[0041] The multiple feeders are involved. In the power system, multiple lines from a substation to different areas are called feeders. The operating state and characteristics of each feeder can be different. By considering the characteristics of multiple feeders, the application can comprehensively optimize the operating state of all feeders, avoid the optimization of a single feeder leading to reduced efficiency of other feeders or excessive use of equipment, and ultimately minimize the system loss, improving the overall economic operation level of the power system.

[0042] The voltage functions corresponding to the multiple feeders are involved. Considering the voltage control targets and economic differences of different feeders, specific voltage functions are designed for each feeder to guide the dynamic optimization of voltage. The feeder loss is directly related to its voltage, such as the head voltage. By constructing a voltage function with the goal of minimizing the loss, the economic operating voltage of each feeder can be accurately calculated, that is, under the premise of meeting power supply and voltage quality, the feeder loss reaches the theoretical minimum, thereby saving energy loss in the power transmission process, reducing operating costs, and improving the economy of the power system.

[0043] The loss data items corresponding to the multiple feeders are involved. The loss data of each feeder is collected and analyzed to minimize the overall loss. Compared with traditional power system loss calculation, which often takes the entire system or substation as a unit, the determination of the loss data items of each feeder in the embodiment of the application realizes more detailed loss management. The loss data items of each feeder are directly related to the operating efficiency of the feeder. By analyzing and optimizing the loss of each feeder, the system can dynamically adjust the reactive power compensation and voltage regulation strategy to reduce energy loss in the power transmission process and achieve economic operation.

[0044] The operating voltage is involved. The operating voltage refers to the voltage level of each point in the power grid and is a key indicator for stable operation of the power system. Reasonable operating voltage can reduce the operating stress of equipment and avoid damage or performance degradation due to excessively high or low voltage. Ideally, the operating voltage should be within an optimal range to ensure power quality, reduce system loss, and improve economic operation level.

[0045] In this step, by calling the pre-set target function and constraint condition, the target function takes minimizing total network loss as the core objective, prompting the system to prioritize minimizing energy loss during power transmission in operation. Through the carefully designed optimization algorithm, the system can dynamically adjust the operating voltage of each feeder to approach or reach the economic operating point of minimum network loss, thereby significantly reducing the operating cost of the power company and improving the economic efficiency of the power grid. The voltage qualification requirement in the target constraint ensures that the operating voltage of the power system always remains within a safe and standard range, and the voltage function corresponding to multiple feeders determines the optimal operating voltage for each feeder. The combination of the target function of minimizing total network loss and the voltage function of each feeder enables the system to achieve global and local collaborative optimization. This means that while meeting the objective of minimizing total network loss, the system can also take into account the voltage characteristics and economic operation requirements of each feeder, thereby improving the overall performance of the entire power grid system, including economy, power quality, and operational stability.

[0046] In step S106, the target function is solved under the target constraint according to the grid state data to obtain an execution strategy corresponding to the target grid system, wherein the execution strategy includes a transformer tap position strategy and a capacitor bank switching strategy.

[0047] In step S106 provided in the present application, the target function is solved under the target constraint according to the grid state data to obtain the transformer tap position strategy and the capacitor bank switching strategy.

[0048] The execution strategy refers to the specific operation instructions calculated by the system according to the optimization target and constraint condition, including the transformer tap position adjustment strategy and the capacitor bank switching strategy.

[0049] The transformer tap position strategy directly affects the voltage level on the secondary side of the transformer. By optimizing the tap position, the AVC system can ensure that the grid voltage remains within the allowed range, avoiding excessively low or high voltage, thereby improving power quality and ensuring the normal operation of user equipment.

[0050] The capacitor bank switching strategy directly affects the reactive power compensation level of the power system. A reasonable switching strategy can ensure that appropriate reactive power is provided under different load conditions, maintaining the power factor at an optimal level and reducing additional losses caused by reactive power flow. The capacitor bank can assist the system in voltage regulation by absorbing or releasing reactive power. An optimized switching strategy can more accurately control the voltage level, especially in situations requiring fine voltage adjustment.

[0051] In this step, the execution strategy of the system is obtained by solving the optimization problem. The execution strategy not only guides the position adjustment of the transformer taps, but also determines the switching of the capacitor banks, thereby achieving effective control of the grid voltage and network loss. Dynamic optimization and real-time control of the strategy are realized, improving the economy and stability of grid operation.

[0052] Through steps S102-S106, the grid state data corresponding to the target grid system at the current time is obtained, wherein the target grid system includes a target device, the target device includes a transformer tap and a capacitor bank, and the grid state data includes transformer tap position data and capacitor bank switching state data. The target function corresponding to the target grid system is retrieved, as well as the target constraints corresponding to the target function, wherein the target function aims to minimize the total network loss, the target constraints include voltage eligibility rate constraints, and the target function includes voltage functions corresponding to multiple feeders and network loss data items. The corresponding voltage function is a function aiming to minimize the network loss of the corresponding feeder, used to determine the corresponding operating voltage. According to the grid state data, the target function is solved under the target constraints to obtain the execution strategy corresponding to the target grid system, wherein the execution strategy includes the position strategy of the transformer tap and the switching strategy of the capacitor bank. In this application, the target function is used to determine the execution strategy. Since the voltage function and the network loss data item corresponding to multiple feeders are considered, the operating voltage and network loss of multiple feeders are considered, and the influence of the economic and adaptive differences of different feeders on the total network loss is considered. Therefore, it can be considered comprehensively, so that the determined execution strategy has adaptability and economy, thereby solving the technical problem that the system adaptability and economy are poor when the determined grid system execution strategy is controlled in related technologies.

[0053] As an optional embodiment, according to the grid state data, the target function is solved under the target constraints to obtain the execution strategy corresponding to the target grid system, including: obtaining a predetermined future time period and load prediction data corresponding to multiple feeders; according to the grid state data and the load prediction data, the target function is solved under the target constraints to obtain the execution strategy corresponding to the target grid system.

[0054] In this embodiment, the execution strategy is predicted considering the load prediction parameter.

[0055] It involves a predetermined future time period, which refers to the time period for which the system needs to make predictions and plans for the future grid operation (e.g. 15-30 minutes). The data within this predetermined period is the basis for the system's forward-looking decision-making.

[0056] The load prediction data is related to the prediction of the future load demand of the power grid, including the predicted demand for active power and reactive power. These data help the system to predict the future state of the power grid and plan the device action in advance.

[0057] In this step, the system can obtain load prediction information for each feeder within the next 15-30 minutes from an external load prediction system. These information includes the predicted active and reactive power demand, as well as possible load fluctuation trends. By obtaining load prediction data, the system can pre-plan the action of the device, reduce the operation delay caused by sudden load changes. Predicting load data helps to reduce the frequent action of the device caused by load fluctuation, prolong the service life of the device, and reduce the maintenance cost. Then, the system comprehensively considers the real-time state data of the current power grid and the future load prediction data, while following the target constraints, solves the target function through optimization algorithm, and obtains the execution strategy. The formulation of the execution strategy takes into account the current state of the device and the expected load demand, optimizes the scheduling of the device, avoids unnecessary device action, improves the response capability of the system, and prolongs the service life of the device.

[0058] Compared with the related art which lacks the ability to predict the dynamic trend of the load, resulting in a control strategy that lags behind the actual working condition changes, the device action planning can be made before the load changes, and the operating parameters such as transformer tap position or capacitor bank switching state can be adjusted in advance to cope with the upcoming changes. This forward-looking control significantly reduces the lag of control, enabling the system to respond more timely and effectively to load fluctuations, maintain voltage within the qualified range, and improve the stability and safety of the system. The use of load prediction information enables the AVC system to make more accurate and timely device action decisions, avoiding frequent device adjustments. Based on the prediction of load changes, the system can reach the expected operating state through one or a few adjustments, rather than continuous fine-tuning, thereby reducing the mechanical and electrical stress of the device, prolonging the service life of the device, and reducing the operation and maintenance cost of the power system.

[0059] As an optional embodiment, before calling the target function, it further includes: determining the target voltage item corresponding to each of the plurality of feeders, and the target device action penalty item, wherein the target device action penalty item includes the action cost item corresponding to each of the target devices and the gear change impact item; constructing the target function according to the target device action penalty item, and the voltage function, the network loss data item and the target voltage item corresponding to each of the plurality of feeders.

[0060] In this embodiment, the process of constructing the target function before calling the target function is explained.

[0061] The target voltage item is related to the target voltage item, which can be the voltage at the head of the corresponding feeder.

[0062] Among them, the target device action penalty term is involved, which is introduced in the strategy optimization to reduce unnecessary device actions and avoid frequent adjustment of device taps. The device action penalty concept is introduced. This penalty term includes the action cost term and the tap change impact term, which aims to quantify the negative impact of frequent device actions.

[0063] Among them, the action cost term is involved, which reflects the economic cost of device actions (such as transformer tap switching, capacitor bank switching) in control. Frequent actions not only increase energy consumption, but also accelerate device wear and tear, increase maintenance and replacement costs.

[0064] Among them, the tap change impact term is involved, which specifically refers to the potential impact of device (such as transformer tap) tap change on system stability, device life and power quality. Large or frequent tap changes may cause system transient instability, affect long-term performance of devices, and cause voltage fluctuations.

[0065] In this step, a plurality of target voltage terms corresponding to a plurality of feeders are determined. When optimizing the control strategy, the ideal voltage level of each feeder needs to be determined first, as different feeders may have different optimal voltage levels due to their load characteristics, line lengths and device configurations. The setting of the target voltage term enables the system to control each feeder more finely, adapting to its specific operating conditions. The target voltage term helps maintain the feeder voltage within the optimal operating range, reducing voltage fluctuations and improving power quality. The target device action penalty term is also determined, including the action cost term and the tap change impact term corresponding to the target device. When optimizing the strategy, the penalty cost of device action also needs to be considered, including the direct economic cost of device action (action cost term) and the indirect impact on system stability, power quality and device life (tap change impact term). By quantifying the cost of device action, the AVC system can avoid unnecessary device action, thereby reducing the expenditure of the power company due to device wear and tear and maintenance. The inclusion of the tap change impact term takes into account the harm of frequent device action to its long-term performance, which helps to extend the service life of the device and reduce the risk of unexpected downtime. Reducing unnecessary device actions helps maintain system stability and avoid transient instability caused by device adjustment. By considering the above, the objective function is further constructed to ensure that the system finds the optimal control strategy that meets the requirements of voltage stability and economy, while reducing the number of device actions and costs.

[0066] As an optional embodiment, before the step of calling the target function, the method further comprises: determining the target voltage item, the reference voltage item, the network loss data item and the adjustment weight item corresponding to each of the plurality of feeders; for each of the plurality of feeders, determining the square of the difference between the target voltage item and the reference voltage item corresponding to each of the plurality of feeders to obtain the corresponding voltage difference square item; determining the product of the voltage difference square item corresponding to each of the plurality of feeders and the adjustment weight item corresponding to each of the plurality of feeders to obtain the corresponding voltage adjustment item; and determining the sum of the voltage adjustment item corresponding to each of the plurality of feeders and the network loss data item to obtain the voltage function corresponding to each of the plurality of feeders.

[0067] In this embodiment, the process of determining the voltage function corresponding to each of the plurality of feeders is illustrated.

[0068] As an optional embodiment, before the step of calling the target constraint corresponding to the target function, the method further comprises: determining the extreme value voltage item, wherein the extreme value voltage item is an item corresponding to the extreme value voltage determined from the operating voltage item corresponding to each of the plurality of feeders; determining the voltage deviation amount item corresponding to each of the plurality of feeders at the predetermined time; determining the voltage upper limit value item and the voltage lower limit value item corresponding to each of the plurality of feeders according to the extreme value voltage item and the voltage deviation amount item corresponding to each of the plurality of feeders; and determining the voltage eligibility rate constraint according to the voltage upper limit value item and the voltage lower limit value item corresponding to each of the plurality of feeders.

[0069] In this embodiment, the process of determining the voltage eligibility rate constraint is illustrated.

[0070] The reference voltage item is involved, which sets the ideal voltage level and reflects the voltage requirements of the power system in the ideal state. The reference voltage item can be determined based on historical data, load prediction, equipment capacity and other factors.

[0071] The adjustment weight item is involved, which is a coefficient used to balance voltage adjustment and economic operation in system control. The adjustment weight item reflects the priority and importance between different performances under certain operating conditions, such as the priority and importance between voltage stability and economy.

[0072] The voltage difference square item is involved, which is the square of the difference between the target voltage item and the reference voltage item, and measures the deviation degree of the actual voltage state from the ideal state.

[0073] The voltage adjustment item is involved, which is the product of the voltage difference square item and the adjustment weight item, and is a key parameter of the system when considering the balance between voltage deviation and economic operation. The size of the voltage adjustment item reflects the urgency and cost of adjusting the voltage deviation.

[0074] In this step, by determining and processing the target voltage term, the reference voltage term, the network loss data term, and the adjustment weight term, the process of constructing the voltage function provides multiple considerations for the system, enabling it to quantify the economic cost of voltage adjustment and the efficiency loss of power transmission based on real-time and predicted data. This not only optimizes the voltage adjustment strategy and improves the economic operation efficiency of the power system, but also enhances the stability and power quality of the system through explicit control objectives and deviation identification, avoiding excessive adjustment of equipment and effectively prolonging the service life of equipment, providing a solid technical foundation for intelligent operation of the power system.

[0075] As an optional embodiment, determining the voltage deviation amount corresponding to each of the plurality of feeders at the predetermined time comprises: determining a maximum absolute deviation proportion term based on the extreme voltage term and the reference voltage term; determining a feeder capacity term corresponding to each of the plurality of feeders and a load change amount term at the predetermined time; and determining the voltage deviation amount corresponding to each of the plurality of feeders at the predetermined time based on the maximum absolute deviation proportion term, the feeder capacity term corresponding to each of the plurality of feeders, and the load change amount term at the predetermined time.

[0076] In this embodiment, the process of determining the voltage deviation amount corresponding to each of the plurality of feeders at the predetermined time is described.

[0077] Here, the predetermined time refers to a specific future time window for system prediction and control decision-making, which can be consistent with the future time based on load prediction, such as 15-30 minutes.

[0078] Here, the extreme voltage term refers to the maximum or minimum value that the feeder voltage may reach within the predetermined time. This value is crucial for assessing voltage stability and can help the system determine whether there is a risk of voltage exceeding the limit.

[0079] Here, the reference voltage term refers to the standard voltage level of the system under normal operating conditions, usually set at the midpoint of the voltage qualified interval, and is the basis for measuring voltage deviation.

[0080] Here, the maximum absolute deviation proportion term refers to the proportion of the calculated voltage deviation amount relative to the reference voltage, representing the severity of voltage fluctuations and used to quantify voltage stability.

[0081] Here, the feeder capacity term refers to the maximum power capacity that each feeder can carry.

[0082] Here, the load change amount term refers to the increase or decrease in feeder load (i.e., power demand) relative to the current time within the predetermined time window, used to assess the dynamic changes in load.

[0083] Wherein, the voltage deviation amount term is involved, which is the deviation amount of the actual voltage of the feeder from the reference voltage at a predetermined time. The voltage deviation amount term is the key basis for the AVC system to adjust the action of the equipment (such as the tap, the capacitor bank) to maintain the voltage stability.

[0084] As an optional embodiment, before the target function is called, the following steps are further included: for each feeder, determining a target voltage term corresponding to each feeder respectively, and determining an active power injection term, a reactive power injection term, and a resistance term of a line section of adjacent nodes corresponding to each node on each feeder respectively; and determining a network loss data term corresponding to each feeder respectively according to the target voltage term corresponding to each feeder respectively, the active power injection term, the reactive power injection term, and the resistance term of the line section of the adjacent nodes corresponding to each node on each feeder.

[0085] In this embodiment, the process of determining the network loss data term corresponding to each feeder respectively is illustrated.

[0086] Wherein, the target voltage term is involved, which refers to the voltage level of the starting point of each feeder, which is usually the point connected to the substation or the upper power grid, and the voltage value is affected by the regulation of the upper power grid or the substation.

[0087] Wherein, the active power injection term and the reactive power injection term are involved, which respectively represent the active power (actual consumed energy) and the reactive power (energy used to establish magnetic field and electric field, which is not directly converted into useful work) injected by each node in the feeder. These data reflect the load characteristics and power demand of the node.

[0088] Wherein, the resistance term of the line section of adjacent nodes is involved, which represents the resistance value of the line between two adjacent nodes in the power grid, and is one of the key parameters for calculating the energy loss (network loss) in power transmission.

[0089] Based on the above embodiments and optional embodiments, an optional implementation is provided, which is specifically described as follows.

[0090] In the related art, in the prior art, the multi-agent collaborative control method based on reinforcement learning (such as MADDPG) can realize the hierarchical collaboration of the substation and the distribution network, but still has the following limitations: first, the load dynamic trend prediction ability is lacking, which leads to that the control strategy lags behind the actual working condition change; second, when the multi-feed line collaborative control is performed, the voltage qualified rate is taken as a single optimization target, and the influence of the economic difference of different feed lines on the network loss is not fully considered. In addition, the traditional method lacks fine modeling in the device action frequency constraint and multi-objective trade-off, which easily leads to the conflict between local optimization and global economic target. Therefore, an intelligent voltage control method fusing load prediction and economic optimization is urgently needed to improve the forward-looking decision-making ability and comprehensive economy of the main network AVC system. That is, the traditional method relies on the current time measurement data for decision-making, lacks the load trend prediction ability, and leads to that the control instruction lags behind the actual working condition change, especially in the random fluctuation scene of new energy output, the device frequent action and short-time voltage over-limit problem is prominent. On the other hand, the existing collaborative optimization model does not fully consider the differentiated economic needs of multi-feed lines, and adopts a unified voltage threshold or a fixed economic weight coefficient, which leads to that the high penetration rate photovoltaic feeder is forced to transmit reactive power in reverse to meet the voltage constraint, causing the network loss to surge. And the traditional method, the prediction result and the control strategy are still in a decoupled state, only as offline reference data, and do not form a closed-loop optimization mechanism, which is difficult to dynamically correct the economic voltage target and device action time sequence.

[0091] In view of this, the method for dynamically optimizing the main network AVC strategy based on the load prediction result provided in the optional embodiment of the present application solves the problem of performance decline of the traditional method caused by response lag and economic insufficiency by constructing a closed-loop control architecture of "prediction data driven-multi-objective collaborative optimization". By taking the load prediction result as the prior information of the AVC strategy optimization, the economic voltage reference value is dynamically corrected and the device action time sequence planning is guided, so that the advanced regulation and global economic optimization are realized. Figure 2 The flow chart of the strategy execution method determined by the optional embodiment of the present application is shown in Figure 2 As shown in the figure, the following will be introduced:

[0092] S1, obtain the power grid state data corresponding to the target power grid system at the current time, wherein the target power grid system comprises a target device, the target device comprises a transformer tap, a capacitor bank, and the power grid state data comprises transformer tap position data T i OLTC , capacitor bank switching state data T i CB Optionally, the power grid state data can further comprise transformer low-voltage side bus voltage data Vr and transformer high-voltage side reactive power data Qr.

[0093] S2, obtain load prediction data corresponding to each feeder in a predetermined future time period;

[0094] As can be received 15-30 minutes of future load curve (including active / reactive power prediction value) provided by external load forecasting system, which is combined with real-time measurement data (voltage, power factor, device state) to form an extended state space. Specifically, define the state vector:

[0095]

[0096] Where: Vr, Qr are the transformer low-voltage side bus, high-voltage side reactive power; T i OLTC , T i CB The current transformer tap, capacitor bank current tap; Ppred, Qpred are the load prediction value in the future time step; ΔPerror is the historical prediction error average.

[0097] S3, call the objective function corresponding to the target AVC power grid system , and the target constraint corresponding to the objective function, wherein the objective function aims to minimize the total network loss, the target constraint includes voltage qualification constraint, and the objective function includes voltage function (also referred to as single feeder economic voltage model) corresponding to each feeder , network loss data item , target voltage item , and target device action penalty item The corresponding voltage function is a function with the minimum network loss of the corresponding feeder as the target, which is used to determine the corresponding operating voltage, and the target device action penalty item includes the action cost item corresponding to the target device and the tap change impact item.

[0098] The objective function is In the case of the original overall feeder economy target (network loss minimization) and voltage qualification constraint, the network loss data item for analyzing the economy of each feeder separately and the device action frequency penalty item are introduced.

[0099] For the above function, wherein, V(k) represents the head voltage level of the kth feeder, V(k) represents the nominal voltage, the ideal reference voltage that the system expects to reach, L(k) is the network loss on the kth feeder, , is the economy weight, the heavier the load of the feeder, the smaller the corresponding weight, V(k) represents the voltage function of the kth feeder, N(i) represents the action frequency of capacitor bank i, represents the number of times of transformer i operation.

[0100] It should be noted that the target constraint can include, in addition to the voltage qualification constraint, a voltage safety constraint, an operation time interval constraint, a maximum number of daily operations of equipment constraint, etc.

[0101] S4, according to the grid state data, solving the target function under the target constraint to obtain an execution strategy corresponding to the target grid system, wherein the execution strategy includes a transformer tap position strategy and a capacitor bank switching strategy.

[0102] It should be noted that before calling the target function, it also includes:

[0103] determining a target voltage item corresponding to each of the plurality of feeders , a reference voltage item , a network loss data item and an adjustment weight item ;

[0104] For each feeder, determine the square of the difference between the target voltage item corresponding to each of the plurality of feeders and the reference voltage item to obtain a corresponding voltage difference term ;

[0105] determining the product of the voltage difference term corresponding to each of the plurality of feeders and the corresponding adjustment weight item to obtain a corresponding voltage adjustment item ;

[0106] determining the sum of the voltage adjustment item corresponding to each of the plurality of feeders and the network loss data item to obtain a voltage function corresponding to each of the plurality of feeders .

[0107] It should be noted that before calling the target function, it also includes:

[0108] For each feeder, determine the target voltage item corresponding to each of the plurality of feeders , the active power injection item corresponding to each of the plurality of nodes on each feeder , the reactive power injection item , and the resistance item of the adjacent node line segment ;

[0109] determining the network loss data item corresponding to each of the plurality of feeders Wherein, I is a node on the kth feeder, and Nk represents a node set on the kth feeder.

[0110] It should be noted that before the target constraint corresponding to the target function is called, the following steps are further included:

[0111] According to the extreme voltage term and the voltage deviation amount term corresponding to each of the plurality of feeders , the voltage upper limit value term corresponding to each of the plurality of feeders and the voltage lower limit value term are determined.

[0112] As , wherein, and are the voltage lower limit value and the voltage upper limit value of the AVC system at time t, the minimum value of the economic reference voltage of all feeders at time t; the maximum value of the economic reference voltage of all feeders at time t; is the dynamically adjusted voltage deviation amount.

[0113] According to the voltage upper limit value term and the voltage lower limit value term corresponding to each of the plurality of feeders, the voltage qualification rate constraint is determined.

[0114] It should be noted that before the target constraint corresponding to the target function is called, the following steps are further included:

[0115] The extreme voltage term is determined, wherein the extreme voltage term is a term in which the corresponding voltage is an extreme voltage, determined from the operating voltage terms corresponding to each of the plurality of feeders;

[0116] According to the extreme voltage term and the reference voltage term , the maximum absolute deviation proportion term is determined, such as .

[0117] The feeder capacity term corresponding to each of the plurality of feeders and the load change amount term at a predetermined time are determined.

[0118] According to the maximum absolute deviation proportion term, and the feeder capacity term corresponding to each of the plurality of feeders and the load change amount term at a predetermined time, the voltage deviation amount term corresponding to each of the plurality of feeders at the predetermined time is determined .

[0119] As , wherein, is the reference voltage deviation; and α, β are weight coefficients; is the load change amount at time t; is the feeder capacity; The maximum absolute deviation of all feeder economic reference voltages from the nominal voltage Un, if the calculated voltage lower limit value is less than the minimum safe voltage value of the distribution system, the minimum safe voltage value is selected as the voltage lower limit value.

[0120] It should be noted that after the execution strategy is determined, the key indicators such as the voltage and power factor of the main network after execution can be continuously monitored to evaluate the control effect. Collect data during execution, such as the number of device actions and the amount of network loss change, as input for subsequent model optimization. Iterative model and strategy adjustment. For example, according to the evaluation results, the parameters of the load prediction model and the weight coefficients α and β in the economic voltage model can be adjusted to improve the prediction accuracy and the flexibility of the control strategy.

[0121] The optimized parameters can then be used to recalculate the AVC strategy and form a new prediction-optimization-control closed loop. Check if the end of the preset control period is reached or specific exit conditions are met (such as stable grid state, no longer need frequent adjustment). If the termination condition is not met, return to the initial step and perform the next round of data collection and state space initialization. If the termination condition is met, it indicates that the current control period has been completed, and the process ends. This process not only embodies the comprehensiveness and systematicness of the technical solution of the present application, but also ensures that the AVC control system can continuously adjust the strategy through the prediction-optimization-control closed loop in the load fluctuation environment, thereby maintaining the efficient and economic operation of the power grid, prolonging the service life of the equipment, and enhancing the system's ability to accommodate new energy.

[0122] Through the above optional implementation, the present application addresses the problems of traditional AVC systems caused by load fluctuation response lag, such as frequent device action, increased network loss, and limited new energy accommodation. By embedding load prediction results into a multi-feeder collaborative optimization model, a prediction-optimization-control closed loop architecture is designed to dynamically adjust the main network AVC strategy. This method uses load prediction data to guide device action timing planning and dynamically correct economic voltage reference values, significantly reducing control lag and improving system operation economy and equipment life. At least the following beneficial effects can be achieved: Through dynamic voltage deviation calculation, multi-feeder joint optimization model, device action suppression strategy, and parameter adaptive mechanism, the deficiencies of traditional AVC systems in flexibility, economy, equipment life, and adaptability are solved. The combination of these technical means makes the present application exhibit significant advantages in complex grid environments.

[0123] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0124] Those skilled in the art can clearly understand from the description of the foregoing embodiments that the method according to the foregoing embodiments can be implemented by means of software and a necessary general hardware platform, and of course, it can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, or a network device) to execute the method of each embodiment of the present application.

[0125] Embodiment 2

[0126] According to the embodiments of the present application, a device for implementing the above-mentioned power grid system strategy determination method is also provided, Figure 3 is a structural block diagram of the power grid system strategy determination device according to the embodiments of the present application, as Figure 3 shown, the device includes an acquisition module 302, a calling module 304 and a determination module 306, which will be described in detail below.

[0127] The acquisition module 302 is configured to acquire power grid state data corresponding to a target power grid system at a current time, wherein the target power grid system includes a target device, the target device includes a transformer tap, a capacitor bank, the power grid state data includes transformer tap position data, and capacitor bank switching state data;

[0128] The calling module 304 is connected to the acquisition module 302 and is configured to call a target function corresponding to the target power grid system and a target constraint corresponding to the target function, wherein the target function aims to minimize total network loss, the target constraint includes a voltage eligibility rate constraint, and the target function includes a voltage function corresponding to each of a plurality of feeder lines and a network loss data item, the corresponding voltage function is a function aiming to minimize the network loss of the corresponding feeder line, and is used to determine a corresponding operating voltage;

[0129] The determining module 306 is connected to the calling module 304, and is configured to solve a target function under a target constraint according to the power grid state data, to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy comprises a position strategy of a transformer tap and a capacitor bank switching strategy.

[0130] It should be noted that the obtaining module 302, the calling module 304 and the determining module 306 correspond to steps S102 to S106 in the method for determining a strategy of a power grid system, and the multiple modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above embodiment 1.

[0131] Embodiment 3

[0132] According to another aspect of the embodiments of the present application, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the method for determining a strategy of a power grid system according to any one of the above.

[0133] Embodiment 4

[0134] According to another aspect of the embodiments of the present application, a computer-readable storage medium is also provided, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the method for determining a strategy of a power grid system according to any one of the above.

[0135] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0136] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0137] In the several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the device embodiment described above is only schematic. For example, the division of the units can be a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0138] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0139] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0140] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical scheme of the present application or the part of the present application which contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0141] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for determining a strategy of a power grid system, characterized by, The method comprises: obtaining power grid state data corresponding to a target power grid system at a current time, wherein the target power grid system comprises a target device, the target device comprises a transformer tap and a capacitor bank, and the power grid state data comprises transformer tap position data and capacitor bank switching state data; obtaining a target function corresponding to the target power grid system and a target constraint corresponding to the target function, wherein the target function aims to minimize total network loss, the target constraint comprises a voltage eligibility rate constraint, and the target function comprises voltage functions corresponding to a plurality of feeders respectively and network loss data items, the corresponding voltage function is a function aiming to minimize network loss of the corresponding feeder and used to determine a corresponding operating voltage; solving the target function under the target constraint according to the power grid state data to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy comprises a position strategy of the transformer tap and a capacitor bank switching strategy. Before the target function is obtained, the method further comprises: determining target voltage items corresponding to the plurality of feeders respectively and a target device action penalty item, wherein the target device action penalty item comprises an action cost item corresponding to the target device respectively and a gear change impact item; and constructing the target function according to the target device action penalty item and the voltage functions, the network loss data items and the target voltage items corresponding to the plurality of feeders respectively.

2. The method of claim 1, wherein, Solving the target function under the target constraint according to the power grid state data to obtain an execution strategy corresponding to the target power grid system comprises: obtaining a predetermined future time period and load prediction data corresponding to the plurality of feeders respectively; solving the target function under the target constraint according to the power grid state data and the load prediction data to obtain an execution strategy corresponding to the target power grid system.

3. The method of claim 1, wherein, Before the target function is obtained, the method further comprises: determining target voltage items, reference voltage items, network loss data items and adjustment weight items corresponding to the plurality of feeders respectively; for each feeder, determining a square of a difference between the target voltage item and the reference voltage item corresponding to the feeder to obtain a corresponding voltage difference square item; determining a product of the voltage difference square item corresponding to each feeder and the corresponding adjustment weight item to obtain a corresponding voltage adjustment item; determining a sum of the voltage adjustment item corresponding to each feeder and the network loss data item to obtain voltage functions corresponding to the plurality of feeders respectively.

4. The method of claim 1, wherein, Before the target constraint corresponding to the target function is obtained, the method further comprises: determining an extreme value voltage item, wherein the extreme value voltage item is an item in which a corresponding voltage is an extreme value voltage among operating voltage items corresponding to the plurality of feeders respectively; determining voltage deviation amount items corresponding to the plurality of feeders respectively at a predetermined time; determining voltage upper limit value items and voltage lower limit value items corresponding to the plurality of feeders respectively according to the extreme value voltage item and the voltage deviation amount items corresponding to the plurality of feeders respectively; determining the voltage eligibility rate constraint according to the voltage upper limit value items and the voltage lower limit value items corresponding to the plurality of feeders respectively.

5. The method of claim 4, wherein, Determine the voltage deviation amount corresponding to each of the plurality of feeders at the predetermined time, comprising: Determine the maximum absolute deviation ratio according to the extreme value voltage and the reference voltage; Determine the feeder capacity corresponding to each of the plurality of feeders and the load change amount at the predetermined time; Determine the voltage deviation amount corresponding to each of the plurality of feeders at the predetermined time according to the maximum absolute deviation ratio, the feeder capacity corresponding to each of the plurality of feeders and the load change amount at the predetermined time.

6. The method according to any one of claims 1 to 5, characterized in that, Before calling the objective function, it also includes: For each feeder, determine the target voltage corresponding to each feeder, the active power injection corresponding to each node on each feeder, the reactive power injection, and the resistance of the adjacent node line segment; Determine the network loss data corresponding to each of the plurality of feeders according to the target voltage corresponding to each of the plurality of feeders, the active power injection corresponding to each node on each feeder, the reactive power injection, and the resistance of the adjacent node line segment.

7. A strategy determination device of a power grid system, characterized by comprising: It includes: An acquisition module is configured to acquire power grid state data corresponding to a target power grid system at a current time, wherein the target power grid system includes a target device, the target device includes a transformer tap changer and a capacitor bank, and the power grid state data includes transformer tap changer position data and capacitor bank switching state data; An calling module is configured to call an objective function corresponding to the target power grid system and a target constraint corresponding to the objective function, wherein the objective function aims to minimize total network loss, the target constraint includes a voltage eligibility rate constraint, and the objective function includes a voltage function corresponding to each of a plurality of feeders and network loss data, the corresponding voltage function is a function aiming to minimize the network loss of the corresponding feeder, and is used to determine a corresponding operating voltage; A determination module is configured to solve the objective function under the target constraint according to the power grid state data to obtain an execution strategy corresponding to the target power grid system, wherein the execution strategy includes a transformer tap changer position strategy and a capacitor bank switching strategy. The calling module is configured to determine a target voltage corresponding to each of the plurality of feeders and a target device action penalty, wherein the target device action penalty includes an action cost corresponding to each of the target devices and a gear change impact; and the objective function is constructed according to the target device action penalty, the voltage function corresponding to each of the plurality of feeders, the network loss data, and the target voltage.

8. An electronic device, comprising: It includes: A processor; A memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the power grid system strategy determination method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can execute the power grid system strategy determination method of any one of claims 1-6.

Images