Power distribution network maintenance method and device considering distributed power supply, electronic equipment and storage medium

Abstract

The invention discloses a power distribution network maintenance method and device considering a distributed power supply, electronic equipment and a storage medium. The method comprises the following steps: obtaining candidate maintenance line data, a topological structure diagram, a plurality of typical day data and operation cost parameters of a power distribution network and hardware parameters of wind and light storage equipment; constructing a power generation and load uncertainty model according to the plurality of typical day data of the power distribution network and a preset prediction model; solving a power generation and load uncertainty model according to the hardware parameters of the wind and light storage equipment and a preset prediction model, and generating power generation and load data of a maintenance day; constructing a power distribution network maintenance model and constraint conditions according to the operation cost parameters of the power distribution network, the hardware parameters of the wind and light storage equipment and the power generation and load data of the maintenance day; under constraint conditions, solving the power distribution network maintenance model to generate a power distribution network maintenance plan; and maintaining the power distribution network according to the power distribution network maintenance plan. According to the invention, the reliability of power distribution network maintenance can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power equipment, and in particular to a distribution network maintenance method, device, electronic equipment and storage medium taking distributed power sources into consideration. Background Art

[0002] In modern power systems, distribution networks are a key link in power transmission and distribution, and their maintenance is extremely important. With the continuous growth of power demand and the gradual aging of power components, the reliability of distribution networks faces severe challenges. If regular maintenance is not carried out, the frequency of power system failures may increase, and in severe cases, even large-scale power outages may occur, which will have a serious impact on the economy and society. Therefore, the implementation of effective maintenance strategies is particularly important to ensure the safe and stable operation of power systems.

[0003] Preventive maintenance in distribution networks refers to preventing failures from occurring by designing reasonable scheduling and maintenance measures before the failure occurs. Current preventive maintenance strategies usually take into account the impact of factors such as short-circuit current and overload current on system reliability. However, existing methods often fail to fully consider the uncertainty of power generation capacity brought by distributed power sources when performing preventive maintenance. This may lead to greater risks in the formulation and implementation of maintenance plans. For example, during preventive maintenance, the support capabilities that distributed power sources can provide during normal operation cannot be fully utilized, which may increase load loss costs and the operating costs of the entire power system. In addition, the lack of response capabilities in different scenarios will make the power system lack response strategies when encountering emergencies, thereby increasing the probability of failures. These problems not only affect the optimization of maintenance costs, but also weaken the overall reliability of the system. Summary of the invention

[0004] The embodiments of the present invention provide a distribution network maintenance method, device, electronic device and storage medium taking into account distributed power sources. By implementing the present invention, preventive maintenance of the distribution network can be achieved, effectively alleviating the problem that traditional preventive maintenance strategies fail to fully utilize the support capabilities provided by distributed power sources, thereby reducing load loss costs and operating costs, and improving the scientificity and reliability of maintenance plans.

[0005] An embodiment of the present invention provides a distribution network maintenance method considering distributed power sources, including:

[0006] Obtain candidate maintenance line data of the distribution network, topological structure diagram of the distribution network, several typical daily data of the distribution network, operation cost parameters of the distribution network, and hardware parameters of wind, solar and storage equipment; among them, the typical daily data of the distribution network includes typical daily load data of the distribution network, typical daily wind data of wind power stations, and typical daily solar radiation data of photovoltaic power stations;

[0007] According to several typical daily data of the distribution network and the preset prediction model, a power generation and load uncertainty model is constructed; wherein the preset prediction model includes a wind speed prediction model, a solar radiation prediction model and a load prediction model;

[0008] According to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, the power generation and load uncertainty model is solved to generate the power generation and load data of the maintenance day; wherein the power generation and load data of the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day;

[0009] According to the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, a distribution network maintenance model and constraints are constructed with the purpose of minimizing the total cost of the power system; wherein the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topological connectivity constraints;

[0010] Under the constraints, the distribution network maintenance model is solved to generate the distribution network maintenance plan;

[0011] The distribution network is maintained according to the distribution network maintenance plan.

[0012] Furthermore, the generation and load uncertainty model is constructed based on several typical daily data of the distribution network and a preset prediction model, including:

[0013] Performing statistical analysis on several typical day wind power data of the wind power station to determine a first average value and a first standard deviation; generating a first random Gaussian variable according to the first average value and the first standard deviation;

[0014] Performing statistical analysis on solar radiation data of several typical days of the photovoltaic power station to determine a second mean value and a second standard deviation; generating a second random Gaussian variable according to the second mean value and the second standard deviation;

[0015] Performing statistical analysis on several typical daily load data of the distribution network to determine a third mean value and a third standard deviation; generating a third random Gaussian variable according to the third mean value and the third standard deviation;

[0016] Generate predicted wind speed data of several typical days of the wind power station according to the preset wind speed prediction model;

[0017] Generate predicted solar radiation data of several typical days of the photovoltaic power station according to the preset solar radiation prediction model;

[0018] Generate several typical daily load data of the distribution network according to the preset load forecasting model;

[0019] Calculating the difference between the typical day wind data of the wind power station and the predicted wind data of the same typical day of the wind power station to generate a first prediction error of the typical day wind data of the wind power station;

[0020] Calculating the difference between the typical day solar radiation data of the photovoltaic power station and the predicted solar radiation data of the same typical day of the photovoltaic power station to generate a second prediction error of the typical day solar radiation data of the photovoltaic power station;

[0021] Calculating the difference between the typical daily load data of the distribution network and the predicted load data of the same typical day of the distribution network to generate a third prediction error of the typical daily load data of the distribution network;

[0022] A power generation and load uncertainty model is constructed according to the first prediction error, the first random Gaussian variable, the second prediction error, the second random Gaussian variable, the third prediction error and the third random Gaussian variable.

[0023] Furthermore, solving the power generation and load uncertainty model based on the hardware parameters of the wind, solar and storage equipment and the preset prediction model to generate the power generation and load data of the maintenance day includes:

[0024] The date of the maintenance day is input into the power generation and load uncertainty model to generate the wind data prediction error of the wind power station on the maintenance day, the solar radiation data prediction error of the photovoltaic power station on the maintenance day, and the load data prediction error of the distribution network on the maintenance day;

[0025] Input the date of the maintenance day into a preset prediction model to generate predicted wind data for the wind power station on the maintenance day, predicted solar radiation data for the photovoltaic power station on the maintenance day, and predicted load data for the distribution network on the maintenance day;

[0026] Correct the predicted wind data of the wind power station on the maintenance day according to the wind data prediction error of the wind power station on the maintenance day, and update the predicted wind data of the wind power station on the maintenance day;

[0027] Correct the predicted solar radiation data of the photovoltaic power station on the maintenance day according to the prediction error of the solar radiation data of the photovoltaic power station on the maintenance day, and update the predicted solar radiation data of the photovoltaic power station on the maintenance day;

[0028] Correct the predicted load data of the distribution network on the maintenance day according to the load data prediction error of the distribution network on the maintenance day, and update the predicted load data of the distribution network on the maintenance day;

[0029] According to the hardware parameters of the wind, solar and storage equipment and the predicted wind data of the wind power station on the maintenance day, the predicted power generation power of the wind power station on the maintenance day is generated by the following formula:

[0030]

[0031] Among them, P WT To maintain the predicted power generation of the wind power station on the day; w is the wind speed; v start is the starting wind speed of the wind turbine; v max is the rated wind speed of the wind turbine; v out is the wind speed at which the wind turbine stops; ρ is the air density; A is the area swept by the wind turbine blades; C p is the power coefficient;

[0032] According to the hardware parameters of the wind, solar and storage equipment and the predicted solar radiation data of the photovoltaic power station on the maintenance day, the predicted power generation power of the photovoltaic power station on the maintenance day is generated by the following formula:

[0033]

[0034] Among them, P PV To maintain the predicted power generation of the daily photovoltaic power station; PV is the light intensity; S PV is the effective area of ​​the photovoltaic panel; η PV is the conversion efficiency of the photovoltaic panel; α PV is the temperature coefficient of the photovoltaic panel; T em is the actual operating temperature of the photovoltaic panel; is the reference temperature of the photovoltaic panel;

[0035] The predicted load data of the distribution network on the maintenance day, the predicted power generation of the wind power station on the maintenance day, and the predicted power generation of the photovoltaic power station on the maintenance day are used as the power generation and load data on the maintenance day.

[0036] Furthermore, the distribution network maintenance model is constructed based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system, including:

[0037] Divide the maintenance day into several scenarios according to preset time intervals;

[0038] Based on the operating cost parameters of the distribution network in several scenarios, the hardware parameters of wind, solar and storage equipment, and the power generation and load data on the maintenance day, the following distribution network maintenance model is constructed:

[0039]

[0040] Where J is the total maintenance scheduling cost; Φ is the scenario set; E is the expected value operation; E Φ is the expected cost of all scenarios; C loss，s is the load loss cost under scenario s; C main is the maintenance cost; Cdeg is the degradation cost; C soc，s To maintain the cost of the battery in scenario s;

[0041] The loss costs are specifically:

[0042]

[0043] Among them, P pred，p，s (t) is the predicted electric power of area p at time t under scenario s; P p，s (t) is the planned electric power of area p at time t under scenario s; C pril，p (t) is the load loss cost coefficient of area p at time t;

[0044] The maintenance costs are specifically:

[0045]

[0046] Among them, τ j，p，q is the maintenance duration of area p and area q on path j; is the maintenance cost of area p and area q on path j during the day; is the maintenance cost of area p and area q on path j at night; T D is the maintenance cost during the day; T N For daytime maintenance costs;

[0047] The degradation cost is specifically:

[0048]

[0049] Among them, α is the weight factor of degradation cost; d j，p，q The degradation state of path j between region p and region q;

[0050] The battery maintenance cost is specifically:

[0051]

[0052] Among them, β is the weight factor; N b is the number of batteries; S bat，b，s (t) is the planned energy storage working state of battery b at time t under scenario s; is the rated capacity of battery b; σ is the target coefficient of battery capacity.

[0053] Furthermore, the topological connectivity constraint is constructed in the following manner:

[0054] According to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, the distribution network is divided to generate a plurality of connected areas for the purpose of maintaining the connectivity of each node within the area unchanged;

[0055] A topological connectivity constraint is constructed according to the connected area and the topological structure diagram of the distribution network.

[0056] Furthermore, the distribution network is divided according to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, with the purpose of maintaining the connectivity of each node in the region unchanged, to generate a number of connected areas, including:

[0057] Starting from the nodes at both ends of the candidate maintenance line of the distribution network, a recursive search is performed to traverse all unvisited nodes until all reachable nodes have been visited. During the search process, if at a certain moment it is found that the current node has been visited, the search along the edge is immediately stopped, and the search is backtracked to the previous node to continue exploring other possible paths.

[0058] All nodes visited from a starting point and their connecting lines are regarded as a connected area, thereby generating multiple connected areas.

[0059] Furthermore, the power balance constraint is:

[0060]

[0061] The power output constraint is:

[0062]

[0063] Among them, W p is the number of power generation units in region p; P k，p，s (t) is the power generated or consumed by the kth power generation, power consumption or energy storage component in area p at time t under scenario s;

[0064] The power upper and lower limits are:

[0065]

[0066] Among them, P min，k is the minimum power of the kth power generation, power consumption or energy storage component; P max，k is the maximum power of the kth power generation, power consumption or energy storage component;

[0067] The maintenance cost constraint is:

[0068]

[0069] in, is the maximum maintenance cost during the daytime period set at time t; is the maximum maintenance cost of the night time period set at time t;

[0070] The maintenance duration constraint is:

[0071]

[0072] The maintenance operation continuity constraint is:

[0073]

[0074] Among them, Δ j，p，q (t-1) is whether the path j of area p and area q performs maintenance operation at time t-1;

[0075] The battery status constraints are:

[0076] S bat，b (t) = η dis S bat，b (t-1)+η char P char，， b(t),

[0077]

[0078] Among them, η char is the charging power; dis is the discharge power; η char P char，b (t) is the charge capacity;

[0079] The battery capacity constraint is:

[0080]

[0081] in, is the minimum allowed battery capacity; is the maximum allowed battery capacity;

[0082] The topological connectivity constraints are:

[0083]

[0084] Among them, δ p，q (t) is the connectivity variable between region p and region q at time t; Δ j，p，q (t) is whether the path j in area p and area q performs maintenance operation at time t; t d is the upper limit of the time range; p and q are area identifiers; n z is the total number of distribution network areas; Θ p，q are all paths between area p and area q.

[0085] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0086] An embodiment of the present invention provides a distribution network maintenance device taking distributed power sources into consideration, comprising: a data acquisition module, a power generation and load uncertainty model construction module, a power generation and load uncertainty solving module, a distribution network maintenance model construction module, a distribution network maintenance plan generation module and a distribution network maintenance module.

[0087] The data acquisition module is used to acquire candidate maintenance line data of the distribution network, a topological structure diagram of the distribution network, several typical daily data of the distribution network, operating cost parameters of the distribution network, and hardware parameters of wind, solar and storage devices; wherein the typical daily data of the distribution network includes typical daily load data of the distribution network, typical daily wind data of the wind power station, and typical daily solar radiation data of the photovoltaic power station;

[0088] The power generation and load uncertainty model construction module is used to construct a power generation and load uncertainty model based on a number of typical daily data of the distribution network and a preset prediction model; wherein the preset prediction model includes a wind speed prediction model, a solar radiation prediction model and a load prediction model;

[0089] The power generation and load uncertainty solving module is used to solve the power generation and load uncertainty model according to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, and generate the power generation and load data of the maintenance day; wherein the power generation and load data of the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day;

[0090] The distribution network maintenance model construction module is used to construct a distribution network maintenance model and constraints based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system; wherein the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topology connectivity constraints;

[0091] The distribution network maintenance plan generation module is used to solve the distribution network maintenance model under constraint conditions and generate a distribution network maintenance plan;

[0092] The distribution network maintenance module is used to maintain the distribution network according to the distribution network maintenance plan.

[0093] Based on the above method embodiment, the present invention provides a corresponding electronic device embodiment.

[0094] An embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the distribution network maintenance method taking into account distributed power sources as described in any one of the above method embodiments can be implemented.

[0095] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0096] An embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the distribution network maintenance method considering distributed power sources as described in any one of the above method embodiments can be implemented.

[0097] Compared with the prior art, the present invention has the following beneficial effects:

[0098] The embodiment of the present invention provides a distribution network maintenance method, device, electronic device and storage medium considering distributed power sources. The method constructs a power generation and load uncertainty model and generates power generation and load data on the maintenance day through typical daily data of the distribution network; finally, based on the operation cost parameters of the distribution network, the power generation and load data on the maintenance day, the topological connectivity constraints and the hardware parameters of the wind, solar and storage devices, the distribution network maintenance model and the constraints related to the distribution network maintenance model are constructed with the purpose of minimizing the total cost of the power system; under the constraints, the distribution network maintenance model is solved to generate a distribution network maintenance plan; according to the distribution network maintenance plan, the distribution network is maintained.

[0099] The present invention constructs a power generation and load uncertainty model, comprehensively considering the uncertainty of power generation capacity of distributed power sources such as wind power and photovoltaic power and the fluctuation of distribution network load, and can accurately predict the power generation and load data of the maintenance day, effectively alleviating the problem that traditional preventive maintenance strategies fail to fully utilize the support capabilities of distributed power sources, thereby reducing load loss costs and operating costs, and improving the scientificity and reliability of maintenance plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] Figure 1 It is a flowchart of a distribution network maintenance method considering distributed power sources provided by an embodiment of the present invention.

[0101] Figure 2 (a) is a schematic diagram of a maintenance case 1 based on an IEEE-34 node network provided by an embodiment of the present invention; Figure 2 (b) is a schematic diagram of maintenance case 2 based on an IEEE-34 node network provided by an embodiment of the present invention; Figure 2 (c) is a schematic diagram of maintenance case 3 based on IEEE-34 node network provided by an embodiment of the present invention; Figure 2(d) is a schematic diagram of maintenance case 4 based on an IEEE-34 node network provided by an embodiment of the present invention; Figure 2 (e) is a schematic diagram of maintenance case 5 based on IEEE-34 node network provided by an embodiment of the present invention.

[0102] Figure 3 It is a structural schematic diagram of a distribution network maintenance device taking distributed power sources into consideration provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0103] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0104] like Figure 1 As shown, an embodiment of the present invention provides a distribution network maintenance method considering distributed power sources, which at least includes the following steps:

[0105] Step S1, obtaining candidate maintenance line data of the distribution network, a topological structure diagram of the distribution network, several typical daily data of the distribution network, operating cost parameters of the distribution network, and hardware parameters of wind, solar and storage equipment;

[0106] It should be noted here that the typical day data of the distribution network includes the typical day load data of the distribution network, the typical day wind data of the wind power station and the typical day solar radiation data of the photovoltaic power station;

[0107] The sampling interval and sampling frequency can be flexibly set according to the actual situation. In one embodiment, data collection is based on a sampling interval of one day and a sampling frequency of one hour. For example, in a typical day, distribution network load data, wind power data of wind power stations, and solar radiation data of photovoltaic power stations are collected at 0:00, 1:00, 2:00...24:00. This detailed data collection method helps to comprehensively analyze the operation status of the distribution network in a typical day and its impact on wind, solar and storage equipment, thereby providing a scientific basis for subsequent maintenance decisions.

[0108] Step S2: constructing a power generation and load uncertainty model based on several typical daily data of the distribution network and a preset prediction model;

[0109] Specifically, the preset prediction models include wind speed prediction model, solar radiation prediction model and load prediction model; these prediction models are obtained by combining historical data analysis with machine learning algorithms to ensure that they can effectively reflect the actual operating conditions. The wind speed prediction model is mainly constructed based on historical wind speed data and meteorological data. Time series analysis methods (such as ARIMA model) or machine learning algorithms (such as random forest, support vector machine, etc.) can be used to model the law of wind speed change. In addition, meteorological factors (such as temperature, air pressure and humidity, etc.) are combined to improve the accuracy of wind speed prediction. The solar radiation prediction model is usually based on historical solar radiation data, meteorological conditions and geographical information. Regression analysis or deep learning models (such as LSTM) are used to capture the law of solar radiation changes over time. In addition, considering the impact of cloud and meteorological changes on solar radiation, the robustness of the model is improved by introducing meteorological forecast data. The load prediction model is constructed based on historical load data, and time series methods or machine learning methods (such as neural networks, regression analysis, etc.) are used to identify the periodicity and trend of load changes.

[0110] Through the construction of the above three models, the uncertainty of power generation and load can be effectively reflected, providing reliable data support for the optimized operation and maintenance decisions of the distribution network.

[0111] In a preferred embodiment, the generation and load uncertainty model is constructed based on several typical daily data of the distribution network and a preset prediction model, including:

[0112] Performing statistical analysis on several typical day wind power data of the wind power station to determine a first average value and a first standard deviation; generating a first random Gaussian variable according to the first average value and the first standard deviation;

[0113] Performing statistical analysis on solar radiation data of several typical days of the photovoltaic power station to determine a second mean value and a second standard deviation; generating a second random Gaussian variable according to the second mean value and the second standard deviation;

[0114] Performing statistical analysis on several typical daily load data of the distribution network to determine a third mean value and a third standard deviation; generating a third random Gaussian variable according to the third mean value and the third standard deviation;

[0115] Generate predicted wind speed data of several typical days of the wind power station according to the preset wind speed prediction model;

[0116] Generate predicted solar radiation data of several typical days of the photovoltaic power station according to the preset solar radiation prediction model;

[0117] Generate several typical daily load data of the distribution network according to the preset load forecasting model;

[0118] Calculating the difference between the typical day wind data of the wind power station and the predicted wind data of the same typical day of the wind power station to generate a first prediction error of the typical day wind data of the wind power station;

[0119] Calculating the difference between the typical day solar radiation data of the photovoltaic power station and the predicted solar radiation data of the same typical day of the photovoltaic power station to generate a second prediction error of the typical day solar radiation data of the photovoltaic power station;

[0120] Calculating the difference between the typical daily load data of the distribution network and the predicted load data of the same typical day of the distribution network to generate a third prediction error of the typical daily load data of the distribution network;

[0121] A power generation and load uncertainty model is constructed according to the first prediction error, the first random Gaussian variable, the second prediction error, the second random Gaussian variable, the third prediction error and the third random Gaussian variable.

[0122] In a preferred embodiment, the power generation and load uncertainty model is constructed by an ARMA model, specifically:

[0123]

[0124] Among them, X(k) is the prediction error of load demand, wind speed and solar radiation in stage k, that is, the prediction error set in stage k; Y(k) is the random Gaussian variable of load demand, wind speed and solar radiation in stage k; p g is the number of autoregressive terms in the model; q g is the number of moving average terms; ρ m is the coefficient of the autoregressive term; θ n is the coefficient of the moving average term; k is the stage identifier; ρ is the constant term;

[0125] The prediction error X(k) of the load demand, wind speed and solar radiation at stage k is specifically:

[0126] X(k)=[X L (k)+X W (k)+X P (k)] T

[0127] Among them, X W (k) is the prediction error of wind speed at stage k, i.e., the first prediction error; X P (k) is the prediction error of solar radiation at stage k, i.e., the second prediction error; X L (k) is the prediction error of load demand at stage k, i.e., the third prediction error.

[0128] The random Gaussian variables Y(k) of the load demand, wind speed and solar radiation at stage k are specifically:

[0129] Y(k)=[Y L (k)+Y W (k)+Y P (k)] T

[0130] Among them, Y W (k) is the unpredictable random volatility of wind speed at stage k, i.e., the first random Gaussian variable; Y P (k) is the unpredictable random volatility of solar radiation at stage k, i.e., the second random Gaussian variable; Y L (k) is the unpredictable random volatility of load demand in stage k, i.e., the third random Gaussian variable.

[0131] The ARMA model is fitted by using several typical daily data of the distribution network and a preset prediction model. Finally, multiple possible scenarios can be generated by using the ARMA model for modeling. Each scenario reflects the load demand, wind speed and solar radiation conditions that may occur at a certain moment in the future.

[0132] Step S3: Solve the power generation and load uncertainty model according to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, and generate the power generation and load data of the maintenance day;

[0133] It should be explained here that the power generation and load data on the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day;

[0134] In an optional embodiment, solving the power generation and load uncertainty model based on the hardware parameters of the wind, solar and storage equipment and a preset prediction model to generate power generation and load data on the maintenance day includes:

[0135] The date of the maintenance day is input into the power generation and load uncertainty model to generate the wind data prediction error of the wind power station on the maintenance day, the solar radiation data prediction error of the photovoltaic power station on the maintenance day, and the load data prediction error of the distribution network on the maintenance day; these errors reflect the possible gap between the actual situation and the prediction, providing a basis for the subsequent correction of the prediction data.

[0136] Input the date of the maintenance day into a preset prediction model to generate predicted wind data for the wind power station on the maintenance day, predicted solar radiation data for the photovoltaic power station on the maintenance day, and predicted load data for the distribution network on the maintenance day;

[0137] Correct the predicted wind data of the wind power station on the maintenance day according to the wind data prediction error of the wind power station on the maintenance day, and update the predicted wind data of the wind power station on the maintenance day;

[0138] Correct the predicted solar radiation data of the photovoltaic power station on the maintenance day according to the prediction error of the solar radiation data of the photovoltaic power station on the maintenance day, and update the predicted solar radiation data of the photovoltaic power station on the maintenance day;

[0139] According to the load data prediction error of the distribution network on the maintenance day, the predicted load data of the distribution network on the maintenance day is corrected, and the predicted load data of the distribution network on the maintenance day is updated; by introducing the random volatility of the data, it is ensured that the prediction result is closer to the actual situation.

[0140] According to the hardware parameters of the wind, solar and storage equipment and the predicted wind data of the wind power station on the maintenance day, the predicted power generation power of the wind power station on the maintenance day is generated by the following formula:

[0141]

[0142] Among them, P WT To maintain the predicted power generation of the wind power station on the day; w is the wind speed; v start is the starting wind speed of the wind turbine; v max is the rated wind speed of the wind turbine; v out is the wind speed at which the wind turbine stops; ρ is the air density; A is the area swept by the wind turbine blades; C p is the power coefficient;

[0143] According to the hardware parameters of the wind, solar and storage equipment and the predicted solar radiation data of the photovoltaic power station on the maintenance day, the predicted power generation power of the photovoltaic power station on the maintenance day is generated by the following formula:

[0144]

[0145] Among them, P PV To maintain the predicted power generation of the daily photovoltaic power station; PV is the light intensity; S PV is the effective area of ​​the photovoltaic panel; η PV is the conversion efficiency of the photovoltaic panel; α PV is the temperature coefficient of the photovoltaic panel; T em is the actual operating temperature of the photovoltaic panel; is the reference temperature of the photovoltaic panel;

[0146] The predicted load data of the distribution network on the maintenance day, the predicted power generation of the wind power station on the maintenance day, and the predicted power generation of the photovoltaic power station on the maintenance day are used as the power generation and load data on the maintenance day.

[0147] Step S4: construct a distribution network maintenance model and constraints based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the goal of minimizing the total cost of the power system;

[0148] Specifically, the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topology connectivity constraints;

[0149] Optionally, the distribution network maintenance model is constructed based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system, including:

[0150] Divide the maintenance day into several scenarios according to preset time intervals;

[0151] Based on the operating cost parameters of the distribution network in several scenarios, the hardware parameters of wind, solar and storage equipment, and the power generation and load data on the maintenance day, the following distribution network maintenance model is constructed:

[0152]

[0153] Among them, Δ j，p，q (t) is whether the maintenance operation is performed on path j between area p and area q at time t; J is the total cost of maintenance scheduling; Φ is the set of scenarios; E is the expected value operation; E Φ is the expected cost of all scenarios; C loss，s is the load loss cost under scenario s; C main is the maintenance cost; C deg is the degradation cost; C soc，s The battery maintenance cost under scenario s; the distribution network maintenance model aims to formulate the optimal maintenance plan by taking into account the uncertainty of distributed power sources under the condition of known candidate maintenance line data of the distribution network, using optimization solution, and taking the lowest cost as the goal. For example, at time t, which maintenance operations need to be performed, how long they need to be performed, where they need to be performed, etc., and at time t+1, which maintenance operations need to be performed. By dynamically adjusting the load power, maintenance cycle, equipment degradation status and battery status in different time periods, an optimized maintenance plan is formulated.

[0154] The loss costs are specifically:

[0155]

[0156] Among them, P pred，p，s (t) is the predicted electric power of area p at time t under scenario s; P p，s (t) is the planned electric power of area p at time t under scenario s; C pril，p (t) is the load loss cost coefficient of area p at time t; t dis the upper limit of the time range; n z is the total number of distribution network areas;

[0157] The maintenance costs are specifically:

[0158]

[0159] Among them, τ j，p，q is the maintenance duration of area p and area q on path j; is the maintenance cost of area p and area q on path j during the day; is the maintenance cost of area p and area q on path j at night; T D is the maintenance cost during the day; T N is the maintenance cost during the day; p and q are the area identifiers; Θ p，q are all paths between area p and area q.

[0160] The degradation cost is specifically:

[0161]

[0162] Among them, α is the weight factor of degradation cost; d j，p，q The degradation state of path j between region p and region q;

[0163] The degradation state is estimated through on-site monitoring data (such as temperature, vibration, etc.), the age of equipment use, and load conditions.

[0164] The battery maintenance cost is specifically:

[0165]

[0166] Among them, β is the weight factor; N b is the number of batteries; S bat，b，s (t) is the planned energy storage working state of battery b at time t under scenario s; is the rated capacity of battery b; σ is the target coefficient of battery capacity.

[0167] In a preferred embodiment, the topological connectivity constraint is constructed in the following manner:

[0168] According to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, the distribution network is divided to generate a plurality of connected areas for the purpose of maintaining the connectivity of each node within the area unchanged;

[0169] A topological connectivity constraint is constructed according to the connected area and the topological structure diagram of the distribution network.

[0170] Specifically, according to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, the distribution network is divided to generate a plurality of connected areas for the purpose of maintaining the connectivity of each node within the area unchanged, including:

[0171] Starting from the nodes at both ends of the candidate maintenance line of the distribution network, a recursive search is performed to traverse all unvisited nodes until all reachable nodes have been visited. During the search process, if at a certain moment it is found that the current node has been visited, the search along the edge is immediately stopped, and the search is backtracked to the previous node to continue exploring other possible paths.

[0172] All nodes visited from a starting point and their connecting lines are regarded as a connected region, thereby generating multiple connected regions. Here, the recursive search can be performed using the depth-first search method.

[0173] In a preferred embodiment, the power balance constraint is:

[0174]

[0175] The power output constraint is:

[0176]

[0177] The power upper and lower limits are:

[0178]

[0179] The maintenance cost constraint is:

[0180]

[0181] The maintenance duration constraint is:

[0182]

[0183] The maintenance operation continuity constraint is:

[0184]

[0185] The battery status constraints are:

[0186] S bat，b (t) = η dis S bat，b (t-1)+η char P char，b (t),

[0187]

[0188] The battery capacity constraint is:

[0189]

[0190] The topological connectivity constraints are:

[0191]

[0192] Among them, W p is the number of power generation units in region p; P k，p，s (t) is the power generated or consumed by the kth power generation, power consumption or energy storage component in area p at time t under scenario s; P min，k is the minimum power of the kth power generation, power consumption or energy storage component; P max，k is the maximum power of the kth power generation, power consumption or energy storage component; is the maximum maintenance cost during the daytime period set at time t; is the maximum maintenance cost of the night time period set at time t; Δ j，p，q (t-1) is whether the path j in area p and area q performs maintenance operation at time t-1; η char is the charging power; dis is the discharge power; η char P char，b (t) is the charge capacity; is the minimum allowed battery capacity; is the maximum capacity of the battery allowed; p，q (t) is the connectivity variable between region p and region q at time;

[0193] The maximum maintenance cost during the daytime period set at time t The maximum maintenance cost during the daytime period set at time t The maintenance cost of area p and area q on path j during the day The maintenance cost of area p and area q on path j at night The maintenance duration τ between area p and area q on path j j,p,q These are known quantities set by the power company or operator.

[0194] Step S5: Under the constraint conditions, solving the distribution network maintenance model and generating a distribution network maintenance plan;

[0195] In a preferred embodiment, the above model is solved using a particle swarm optimization algorithm to generate a distribution network maintenance plan, including: the planned energy storage working state S of battery b at time t in scenario s bat，b，s (t), whether region p and region q perform maintenance operation on path j at time t Δ j，p，q (t), the planned electric power P of area p at time t under scenario sp，s (t).

[0196] Step S6: Maintain the distribution network according to the distribution network maintenance plan.

[0197] In a preferred embodiment, based on the IEEE-34 node network, five groups of different maintenance operations are selected as research cases. In each group of cases, the uncertainty of the power generation of distributed power sources and the scenarios of different load demands are considered. The network structures and maintenance operations of these five cases are as follows: Figure 2 As shown, the specific parameters related to the maintenance operation are shown in Appendix 1, where the rated power generation of distributed power source 1, distributed power source 2, distributed power source 3, and distributed power source 4 are 100kW, 150kW, 200kW, and 150kW, respectively. The comparison method adopted by the present invention does not consider the support capacity of distributed power sources and batteries. Finally, the load loss cost obtained through the experiment is listed in detail in Appendix 2.

[0198] Among them, Appendix 1 is:

[0199]

[0200] Among them, Appendix 2 is:

[0201] Case Load loss cost of the proposed method Comparison of load loss costs of methods 1 124.8 167.87 2 454.18 533.65 3 200.49 215.13 4 227.98 247.14 5 0 0

[0202] It can be seen from Appendix 1 and Appendix 2 that although the maintenance operations in Case 4 and Case 5 have the same duration, the load loss costs caused are different due to the differences in the locations and paths where these operations are performed. For example, when performing maintenance work, although the maintenance operations in Case 4 and Case 5 have the same duration, due to the differences in the paths where the execution locations are located, the maintenance operations in Case 4 affect a larger load area than the maintenance operations in Case 5, resulting in higher load losses. In addition, the analysis also shows that in various scenarios, the load loss costs of the proposed method are reduced by 35%, 17.5%, 7.3% and 8.4% respectively compared to the comparative methods. The results verify the effectiveness and efficiency of the present invention in reducing the load loss costs during maintenance after taking into account the support capabilities of distributed power sources in preventive maintenance.

[0203] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0204] like Figure 3 As shown, an embodiment of the present invention provides a distribution network maintenance device taking into account distributed power sources, including: a data acquisition module, a power generation and load uncertainty model construction module, a power generation and load uncertainty solving module, a distribution network maintenance model construction module, a distribution network maintenance plan generation module and a distribution network maintenance module.

[0205] The data acquisition module is used to acquire candidate maintenance line data of the distribution network, a topological structure diagram of the distribution network, several typical daily data of the distribution network, operating cost parameters of the distribution network, and hardware parameters of wind, solar and storage devices; wherein the typical daily data of the distribution network includes typical daily load data of the distribution network, typical daily wind data of the wind power station, and typical daily solar radiation data of the photovoltaic power station;

[0206] The power generation and load uncertainty model construction module is used to construct a power generation and load uncertainty model based on a number of typical daily data of the distribution network and a preset prediction model; wherein the preset prediction model includes a wind speed prediction model, a solar radiation prediction model and a load prediction model;

[0207] The power generation and load uncertainty solving module is used to solve the power generation and load uncertainty model according to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, and generate the power generation and load data of the maintenance day; wherein the power generation and load data of the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day;

[0208] The distribution network maintenance model construction module is used to construct a distribution network maintenance model and constraints based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system; wherein the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topology connectivity constraints;

[0209] The distribution network maintenance plan generation module is used to solve the distribution network maintenance model under constraint conditions and generate a distribution network maintenance plan;

[0210] The distribution network maintenance module is used to maintain the distribution network according to the distribution network maintenance plan.

[0211] It should be noted that the embodiments of the device described above correspond to the above embodiments of the present invention, and can implement any of the methods described above in the present invention. In addition, the embodiments of the above-mentioned device are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0212] Based on the above method embodiment of the present invention, a corresponding electronic device embodiment is provided.

[0213] An embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the distribution network maintenance method considering distributed power sources described in any one of the present invention is implemented, or, when the processor executes the computer program, the functions of the modules in the above-mentioned device embodiments are implemented.

[0214] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0215] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0216] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0217] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0218] Based on the above method embodiment, the present invention provides a storage medium embodiment;

[0219] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute any of the above-mentioned distribution network maintenance methods considering distributed power sources of the present invention.

[0220] Wherein, the above storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0221] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0222] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A distribution network maintenance method considering distributed power sources, characterized in that: include: Obtain candidate maintenance line data of the distribution network, topological structure diagram of the distribution network, several typical daily data of the distribution network, operation cost parameters of the distribution network, and hardware parameters of wind, solar and storage equipment; among them, the typical daily data of the distribution network includes typical daily load data of the distribution network, typical daily wind data of wind power stations, and typical daily solar radiation data of photovoltaic power stations; According to several typical daily data of the distribution network and the preset prediction model, a power generation and load uncertainty model is constructed; wherein the preset prediction model includes a wind speed prediction model, a solar radiation prediction model and a load prediction model; According to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, the power generation and load uncertainty model is solved to generate the power generation and load data of the maintenance day; wherein the power generation and load data of the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day; According to the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, a distribution network maintenance model and constraints are constructed with the purpose of minimizing the total cost of the power system; wherein the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topological connectivity constraints; Under the constraints, the distribution network maintenance model is solved to generate the distribution network maintenance plan; The distribution network is maintained according to the distribution network maintenance plan.

2. The method for maintaining a distribution network taking distributed power sources into consideration according to claim 1, characterized in that: The generation and load uncertainty model is constructed based on several typical daily data of the distribution network and a preset prediction model, including: Performing statistical analysis on several typical day wind power data of the wind power station to determine a first average value and a first standard deviation; generating a first random Gaussian variable according to the first average value and the first standard deviation; Performing statistical analysis on solar radiation data of several typical days of the photovoltaic power station to determine a second mean value and a second standard deviation; generating a second random Gaussian variable according to the second mean value and the second standard deviation; Performing statistical analysis on several typical daily load data of the distribution network to determine a third mean value and a third standard deviation; generating a third random Gaussian variable according to the third mean value and the third standard deviation; Generate predicted wind speed data of several typical days of the wind power station according to the preset wind speed prediction model; Generate predicted solar radiation data of several typical days of the photovoltaic power station according to the preset solar radiation prediction model; Generate several typical daily load data of the distribution network according to the preset load forecasting model; Calculating the difference between the typical day wind data of the wind power station and the predicted wind data of the same typical day of the wind power station to generate a first prediction error of the typical day wind data of the wind power station; Calculating the difference between the typical day solar radiation data of the photovoltaic power station and the predicted solar radiation data of the same typical day of the photovoltaic power station to generate a second prediction error of the typical day solar radiation data of the photovoltaic power station; Calculating the difference between the typical daily load data of the distribution network and the predicted load data of the same typical day of the distribution network to generate a third prediction error of the typical daily load data of the distribution network; A power generation and load uncertainty model is constructed according to the first prediction error, the first random Gaussian variable, the second prediction error, the second random Gaussian variable, the third prediction error and the third random Gaussian variable.

3. The method for maintaining a distribution network taking distributed power sources into consideration according to claim 2, characterized in that: The method solves the power generation and load uncertainty model based on the hardware parameters of the wind, solar and storage equipment and the preset prediction model, and generates the power generation and load data of the maintenance day, including: The date of the maintenance day is input into the power generation and load uncertainty model to generate the wind data prediction error of the wind power station on the maintenance day, the solar radiation data prediction error of the photovoltaic power station on the maintenance day, and the load data prediction error of the distribution network on the maintenance day; Input the date of the maintenance day into a preset prediction model to generate predicted wind data for the wind power station on the maintenance day, predicted solar radiation data for the photovoltaic power station on the maintenance day, and predicted load data for the distribution network on the maintenance day; Correct the predicted wind data of the wind power station on the maintenance day according to the wind data prediction error of the wind power station on the maintenance day, and update the predicted wind data of the wind power station on the maintenance day; Correct the predicted solar radiation data of the photovoltaic power station on the maintenance day according to the prediction error of the solar radiation data of the photovoltaic power station on the maintenance day, and update the predicted solar radiation data of the photovoltaic power station on the maintenance day; Correct the predicted load data of the distribution network on the maintenance day according to the load data prediction error of the distribution network on the maintenance day, and update the predicted load data of the distribution network on the maintenance day; According to the hardware parameters of the wind, solar and storage equipment and the predicted wind data of the wind power station on the maintenance day, the predicted power generation power of the wind power station on the maintenance day is generated by the following formula: Among them, P WT To maintain the predicted power generation of the wind power station on the day; w is the wind speed; v start is the starting wind speed of the wind turbine; v max is the rated wind speed of the wind turbine; v out is the wind speed at which the wind turbine stops; ρ is the air density; A is the area swept by the wind turbine blades; C p is the power coefficient; According to the hardware parameters of the wind, solar and storage equipment and the predicted solar radiation data of the photovoltaic power station on the maintenance day, the predicted power generation power of the photovoltaic power station on the maintenance day is generated by the following formula: Among them, P PV To maintain the predicted power generation of the daily photovoltaic power station; PV is the light intensity; S PV is the effective area of ​​the photovoltaic panel; η PV is the conversion efficiency of the photovoltaic panel; α PV is the temperature coefficient of the photovoltaic panel; T em is the actual operating temperature of the photovoltaic panel; is the reference temperature of the photovoltaic panel; The predicted load data of the distribution network on the maintenance day, the predicted power generation of the wind power station on the maintenance day, and the predicted power generation of the photovoltaic power station on the maintenance day are used as the power generation and load data on the maintenance day.

4. The method for maintaining a distribution network taking distributed power sources into consideration according to claim 3, characterized in that: The distribution network maintenance model is constructed based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system, including: Divide the maintenance day into several scenarios according to preset time intervals; Based on the operating cost parameters of the distribution network in several scenarios, the hardware parameters of wind, solar and storage equipment, and the power generation and load data on the maintenance day, the following distribution network maintenance model is constructed: Where J is the total maintenance scheduling cost; Φ is the scenario set; E is the expected value operation; E Φ is the expected cost of all scenarios; C loss，s is the load loss cost under scenario s; C main is the maintenance cost; C deg is the degradation cost; C soc，s To maintain the cost of the battery in scenario s; The loss costs are specifically: Among them, P pred，p，s (t) is the predicted electric power of area p at time t under scenario s; P p，s (t) is the planned electric power of area p at time t under scenario s; C pril，p (t) is the load loss cost coefficient of area p at time t; The maintenance costs are specifically: Among them, τ j，p，q is the maintenance duration of area p and area q on path j; is the maintenance cost of area p and area q on path j during the day; is the maintenance cost of area p and area q on path j at night; T D is the maintenance cost during the day; T N For daytime maintenance costs; The degradation cost is specifically: Among them, α is the weight factor of degradation cost; d j，p，q The degradation state of path j between region p and region q; The battery maintenance cost is specifically: Among them, β is the weight factor; N b is the number of batteries; S bat，b，s (t) is the planned energy storage working state of battery b at time t under scenario s; is the rated capacity of battery b; σ is the target coefficient of battery capacity.

5. The method for maintaining a distribution network taking distributed power sources into consideration according to claim 4, characterized in that: The topology connectivity constraints are constructed in the following way: According to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, the distribution network is divided to generate a plurality of connected areas for the purpose of maintaining the connectivity of each node within the area unchanged; A topological connectivity constraint is constructed according to the connected area and the topological structure diagram of the distribution network.

6. The distribution network maintenance method considering distributed power sources according to claim 5, wherein the distribution network is divided according to the topological structure diagram of the distribution network and the candidate maintenance line data of the distribution network, with the purpose of maintaining the connectivity of each node in the region unchanged, to generate a plurality of connected regions, including: Starting from the nodes at both ends of the candidate maintenance line of the distribution network, a recursive search is performed to traverse all unvisited nodes until all reachable nodes have been visited. During the search process, if at a certain moment it is found that the current node has been visited, the search along the edge is immediately stopped, and the search is backtracked to the previous node to continue exploring other possible paths. All nodes visited from a starting point and their connecting lines are regarded as a connected area, thereby generating multiple connected areas.

7. The method for maintaining a distribution network taking distributed power sources into consideration according to claim 6, characterized in that: The power balance constraint is: The power output constraint is: Among them, W p is the number of power generation units in region p; P k，p，s (t) is the power generated or consumed by the kth power generation, power consumption or energy storage component in area p at time t under scenario s; The power upper and lower limits are: Among them, P min，k is the minimum power of the kth power generation, power consumption or energy storage component; P max，k is the maximum power of the kth power generation, power consumption or energy storage component; The maintenance cost constraint is: in, is the maximum maintenance cost during the daytime period set at time t; is the maximum maintenance cost of the night time period set at time t; The maintenance duration constraint is: The maintenance operation continuity constraint is: Among them, Δ j，p，q (t-1) is whether the path j of area p and area q performs maintenance operation at time t-1; The battery status constraints are: Among them, η char is the charging power; dis is the discharge power; η char P char，b (t) is the charge capacity; The battery capacity constraint is: in, is the minimum allowed battery capacity; is the maximum allowed battery capacity; The topological connectivity constraints are: Among them, δ p，q (t) is the connectivity variable between region p and region q at time t; Δ j，p，q (t) is whether the path j in area p and area q performs maintenance operation at time t; t d is the upper limit of the time range; p and q are area identifiers; n z is the total number of distribution network areas; Θ p，q are all paths between area p and area q.

8. A distribution network maintenance device considering distributed power sources, characterized in that: include: Data acquisition module, generation and load uncertainty model building module, generation and load uncertainty solving module, distribution network maintenance model building module, distribution network maintenance plan generation module and distribution network maintenance module; The data acquisition module is used to acquire candidate maintenance line data of the distribution network, a topological structure diagram of the distribution network, several typical daily data of the distribution network, operating cost parameters of the distribution network, and hardware parameters of wind, solar and storage devices; wherein the typical daily data of the distribution network includes typical daily load data of the distribution network, typical daily wind data of the wind power station, and typical daily solar radiation data of the photovoltaic power station; The power generation and load uncertainty model construction module is used to construct a power generation and load uncertainty model based on a number of typical daily data of the distribution network and a preset prediction model; wherein the preset prediction model includes a wind speed prediction model, a solar radiation prediction model and a load prediction model; The power generation and load uncertainty solving module is used to solve the power generation and load uncertainty model according to the hardware parameters of the wind, solar and storage equipment and the preset prediction model, and generate the power generation and load data of the maintenance day; wherein the power generation and load data of the maintenance day include the predicted power generation of the wind power station on the maintenance day, the predicted power generation of the photovoltaic power station on the maintenance day, and the predicted load of the distribution network on the maintenance day; The distribution network maintenance model construction module is used to construct a distribution network maintenance model and constraints based on the operating cost parameters of the distribution network, the hardware parameters of the wind, solar and storage equipment, and the power generation and load data on the maintenance day, with the purpose of minimizing the total cost of the power system; wherein the constraints include power balance constraints, power output constraints, power upper and lower limit constraints, maintenance cost constraints, maintenance duration constraints, maintenance operation continuity constraints, battery status constraints, battery capacity constraints and topology connectivity constraints; The distribution network maintenance plan generation module is used to solve the distribution network maintenance model under constraint conditions and generate a distribution network maintenance plan; The distribution network maintenance module is used to maintain the distribution network according to the distribution network maintenance plan.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the distribution network maintenance method taking into account distributed power sources as described in any one of claims 1 to 7 can be implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement the distribution network maintenance method considering distributed power sources as described in any one of claims 1 to 7.

Images