Optimized scheduling method, system and device for flexible interconnection system in power distribution area and storage medium

Abstract

The invention discloses a power distribution area flexible interconnection system optimization scheduling method, system and device and a storage medium, and relates to the technical field of power system scheduling. Comprising the steps that first operation parameters and an initial scheduling window of a target transformer area are obtained based on real-time operation data of a flexible interconnection system of the power distribution transformer area, and the real-time operation parameters comprise load data of all transformer areas, distributed power output data and micro-grid interaction data; through the dynamic scheduling window based on the collaboration degree difference value, the range of the scheduling window can be dynamically adjusted in real time according to the collaboration degree of each associated transformer area and the target transformer area, when the collaboration degree difference value is large, the scheduling window is expanded, more associated transformer areas are included in the scheduling range, the collaboration effect in the area is enhanced, and when the collaboration degree difference value is small, the scheduling window is expanded. A scheduling window is reduced, and closely related transformer areas are optimized in a centralized manner, so that the adaptive capacity of the system to a complex and changeable operation environment is improved, and accurate and efficient collaborative optimization scheduling is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system dispatching, in particular to a power distribution substation flexible interconnection system optimization dispatching method, system, device and storage medium. BACKGROUND

[0002] In recent years, distributed resources such as distributed photovoltaic, energy storage, and charging piles in low-voltage power distribution substation have developed rapidly. In actual operation, there is often a large difference in load rate between adjacent power distribution substations in the same area. The load uncertainty caused by the large access of distributed photovoltaic and charging piles, and the insufficient capacity of power distribution substations will further increase the load rate deviation between adjacent power distribution substations. The large access of distributed photovoltaic, energy storage, and charging piles, and the increasing growth of data centers, communication equipment, and direct current transmission, make the current source-load-storage direct current characteristics of power distribution substations more and more obvious. By using flexible interconnection devices to interconnect adjacent power distribution substations in flexible direct current to form a flexible interconnection system, and configuring a certain capacity of energy storage, the problem of large load rate difference and load imbalance between adjacent power distribution substations can be effectively solved, and the load balancing and energy optimization between power distribution substations can be improved.

[0003] The structure mode of the traditional power distribution system and the rigid power distribution equipment are difficult to adapt to the randomness impact brought by the large access of distributed new energy and direct current charging piles of electric vehicles. On the other hand, the access of a high proportion of new elements makes the originally complex power distribution system more complex. After adding various converters, controllers and other devices, the difficulty of system operation control is further increased. Moreover, with the increasing number of nonlinear loads, precision manufacturing loads and direct current loads, users have higher and higher requirements for power quality, diversity and reliability of the power distribution system. The current mode of relying on a large number of dispersed conversion devices to supply power to direct current loads not only has high cost, but also easily causes power quality problems and reduces energy utilization efficiency.

[0004] Although the implementation of a multi-substation flexible interconnection system through flexible power electronic devices has become an effective way to solve the access and consumption of a large number of distributed resources on the power distribution side, the existing technology still has some deficiencies. Some optimization dispatching methods mainly take the active power of the power distribution transformer as the optimization object, which cannot effectively balance the imbalance between substations, and cannot solve the problem of heavy overload caused by the access of a large number of distributed resources in the power system. Moreover, the optimization dispatching method for the low-voltage power distribution substation flexible interconnection system containing multiple distributed resources generally has the problem of incomplete consideration of operation scenarios and element factors. The model construction of photovoltaic, energy storage, charging pile, flexible interconnection device, and power distribution transformer is too simple, the model applicability is poor, it is difficult to meet the global optimal solution of the operation target, and further leads to the overall operation of the power distribution substation flexible interconnection system not being economical, and the energy optimization and load balancing effect between substations being poor.

[0005] Therefore, the application provides a power distribution area flexible interconnection system optimization scheduling method, system, device and storage medium. SUMMARY

[0006] The application aims to provide a power distribution area flexible interconnection system optimization scheduling method, system, device and storage medium to solve the problems in the background art.

[0007] To achieve the above-mentioned purpose, the application provides the following technical solution: a power distribution area flexible interconnection system optimization scheduling method, comprising:

[0008] Based on the real-time operation data of the power distribution area flexible interconnection system, the first operation parameter of the target area and the initial scheduling window are obtained, the real-time operation parameter includes the load data of each area, the output data of the distributed power supply and the micro-grid interaction data, the first operation parameter is the key state parameter of the target area, and the initial scheduling window is set based on the historical optimization result;

[0009] Based on the initial scheduling window, the second operation parameter of a plurality of associated areas is obtained from the system, the initial scheduling window is centered on the target area, and the plurality of associated areas are located in the initial scheduling window and have a flexible interconnection relationship with the target area;

[0010] The coordination degree difference value of each second operation parameter and the first operation parameter is calculated , Wherein is the coordination degree of the ith associated area and the target area, is a preset reference coordination degree;

[0011] If the coordination degree difference value satisfies the first adjustment condition, the scheduling window is dynamically updated, and if the coordination degree difference value satisfies the second adjustment condition, the optimal scheduling strategy of the target area is calculated based on the second operation parameter of each associated area through the micro-grid system optimization model;

[0012] The dynamic updating of the scheduling window comprises: if , is the first threshold value, the scheduling window is expanded to times the original size, if , is the second threshold value, the scheduling window is reduced to times the original size;

[0013] The second adjustment condition is

[0014] The micro-grid collaborative optimization model takes the minimum total operation cost of the system as a target, and a target function is:

[0015] , wherein, is a network loss cost, is a distributed power abandoned electricity cost, is an environmental penalty cost, , , is a weight coefficient;

[0016] The constraint conditions include power balance constraints, equipment capacity constraints, micro-grid tie-line power constraints and voltage safety constraints.

[0017] As a specific scheme of one scheme of the application, the collaborative degree is calculated by the following method:

[0018] , wherein, , , are active power interaction power, reactive power interaction power and voltage deviation of the ith associated substation and the target substation respectively, , , are reference values, , , are weight coefficients and satisfy .

[0019] As a specific scheme of one scheme of the application, the optimal dispatching strategy of the target substation is calculated by the micro-grid collaborative optimization model based on the second operation parameters of each associated substation, including:

[0020] A multi-dimensional state matrix S is constructed based on the operation parameters, wherein n is the number of associated substations and m is the dimension of the state parameters;

[0021] The state matrix S is processed by dimension reduction to obtain a low-dimensional feature matrix , and W is a dimension reduction conversion matrix;

[0022] Based on the low-dimensional feature matrix , the optimal solution of the micro-grid collaborative optimization model is solved by an improved particle swarm algorithm to obtain the tie-line power regulation instruction of each distributed power processing computer.

[0023] As a specific scheme of one scheme of the application, the velocity update formula of the improved particle swarm algorithm is:

[0024] wherein w is an inertia weight, 、 、 is a learning factor, 、 、 is a [0, 1] random number, is an individual optimal position, g is a global optimal position, is a micro-grid cluster optimal position, used to reflect the synergy between micro-grids;

[0025] The inertia weight w is an adaptive adjustment formula: where t is the current iteration number, T is the maximum iteration number, 、 are the maximum and minimum inertia weights, respectively.

[0026] As a specific scheme of one scheme of the present application, the power balance constraint is specifically:

[0027] wherein, is the output of the distributed power supply in the i-th micro-grid, is the interactive power between the transformer area and the main grid, is the load of the i-th transformer area, is the network loss.

[0028] A power distribution transformer area flexible interconnection system optimization scheduling system comprises:

[0029] A data acquisition module is configured to acquire first operation parameters of a target transformer area and an initial scheduling window based on real-time operation data of the power distribution transformer area flexible interconnection system, wherein the real-time operation data includes transformer area load data, distributed power supply processing data, and micro-grid interaction data.

[0030] A cooperative analysis module is configured to acquire second operation parameters of associated transformer areas based on the initial scheduling window and calculate a cooperative degree difference value .

[0031] A window adjustment module is configured to expand the scheduling window if , and to reduce the scheduling window if .

[0032] An optimization scheduling module is configured to calculate an optimal scheduling strategy through a micro-grid cooperative optimization model if .

[0033] The optimization scheduling module comprises a micro-grid cluster decision unit configured to coordinate the output plan of different micro-grids and the power distribution of the tie line.

[0034] As a specific scheme of one scheme of the present application, the optimization scheduling module comprises:

[0035] a matrix construction unit configured to construct a multi-dimensional state matrix S;

[0036] a dimension reduction processing unit configured to reduce the dimension of the state matrix S by a principal component analysis method;

[0037] an intelligent solving unit configured to solve the optimization model by using an improved particle swarm algorithm and output a scheduling scheme containing energy storage charging and discharging plans, distributed power output curves and tie-line power control instructions.

[0038] As a specific scheme of the scheme of the application, the method further comprises:

[0039] a prediction module configured to predict the future 24-hour substation load data and distributed power output data based on an LSTM neural network;

[0040] The input features of the prediction module include historical load data, meteorological data, date types and micro-grid operation mode labels.

[0041] A power distribution substation flexible interconnection system optimization scheduling device comprises a processor, a storage, and a computer program stored on the storage and executable on the processor, and the computer program, when executed by the processor, implements a power distribution substation flexible interconnection system optimization scheduling method according to any one of the above embodiments.

[0042] A computer readable storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements a power distribution substation flexible interconnection system optimization scheduling method according to any one of the above embodiments.

[0043] Compared with the prior art, the power distribution substation flexible interconnection system optimization scheduling method has the following advantages:

[0044] The power distribution substation flexible interconnection system optimization scheduling method can dynamically adjust the range of the scheduling window according to the degree of cooperation between each associated substation and the target substation, expand the scheduling window when the difference in cooperation is large, and include more associated substations in the scheduling range to strengthen the cooperative effect in the region, and when the difference in cooperation is small, the scheduling window is reduced to optimize the closely related substations, thereby improving the adaptive ability of the system to the complex and variable operating environment and achieving precise and efficient cooperative optimization scheduling.

[0045] Through the constructed micro-grid collaborative optimization model, with the minimum total operation cost of the system as the core target, multiple key factors such as network loss cost, distributed power abandoned power cost and environmental penalty cost are comprehensively considered, meanwhile, comprehensive constraint conditions such as power balance constraint, equipment capacity constraint, micro-grid tie line power constraint and voltage safety constraint are set, so that in the optimization process, not only the operation cost can be reduced, but also the safe and stable operation of the system can be ensured, and the overall operation efficiency of the flexible interconnection system of the distribution area is effectively improved.

[0046] The improved particle swarm algorithm adopted in the application introduces the optimal position parameter of the micro-grid cluster on the basis of the traditional algorithm, and adaptively adjusts the inertia weight, so that the comprehensive search and local search ability can be better balanced, and the optimization scheduling calculation efficiency and precision are improved.

[0047] Through the advanced LSTM neural network based on the newly added prediction module, multi-dimensional information such as historical load data, weather data, date type and micro-grid operation mode label can be fully utilized to predict the future 24-hour area meeting data and distributed power processing data, by combining the prediction structure with the optimization scheduling, a closed-loop system of prediction, optimization and scheduling is formed, data is provided in advance for system optimization scheduling, the ability of the system to cope with uncertainty is further enhanced, and the stability and reliable operation of the system are ensured. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 It is the overall system flowchart of the application;

[0049] Figure 2 It is the data acquisition module flowchart of the application;

[0050] Figure 3 It is the optimization scheduling device and storage medium association flowchart of the application;

[0051] Figure 4 It is the collaborative analysis module flowchart of the application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0053] It should be noted that in the description of the present application, the terms "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0054] In addition, it should be understood that the sizes of the various components shown in the drawings are not drawn in accordance with the actual proportional relationship, for example, the thickness or width of certain layers can be exaggerated relative to other layers.

[0055] It should be noted that similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined or described in one drawing, it will not need to be further specifically discussed and described in the description of subsequent drawings.

[0056] The present application provides a technical solution: a power distribution area flexible interconnection system optimization scheduling method, comprising:

[0057] Based on the real-time data of the power distribution area flexible interconnection system, the first operation parameter of the target area and the initial scheduling window are obtained, wherein the real-time operation parameter includes the load data of each area (such as the load value of a certain area at a certain time is 800kW), the output data of distributed power (such as the output of a certain photovoltaic power station at the same period is 300kW) and the interactive data of micro-grid (such as the active power interaction between a certain micro-grid and the target area is 150kW), the first operation parameter is the key state parameter of the target area, including voltage (such as 0.4KV), current (such as 1200A), power factor (such as 0.92) and the like, and the initial scheduling window is set based on the historical optimization result, for example, according to the optimization experience under the same running scene in the past month, the initial scheduling window is set to cover 5 associated areas within a radius of 3km range centered on the target area.

[0058] In the present application, based on the initial scheduling window, the second operation parameter of the plurality of associated areas is obtained from the system, the initial scheduling window is centered on the target area, and the plurality of associated areas are located within the initial scheduling window and have a flexible interconnection relationship with the target area, for example, the load data (750kW, 820kW, 780kW, 850kW, 720kW respectively), the output data of distributed power (280kW, 320kW, 250kW, 350kW, 260kW respectively) and the interactive data (the active power interaction is 130kW, 160kW, 140kW, 170kW, 120kW respectively) with the target area of the above-mentioned 5 associated areas are obtained as the second operation parameter.

[0059] Calculate the degree of coordination difference between each second operating parameter and the first operating parameter. ,in Let i be the degree of coordination between the i-th associated station area and the target station area. To establish a baseline degree of coordination, in this application, the preferred baseline degree of coordination is 0.85. The calculation method is as follows:

[0060] ,in, , , These represent the active power exchange, reactive power exchange, and voltage deviation between the i-th associated transformer area and the target transformer area, respectively. , , As the baseline value, , , The weighting coefficients are satisfied. In this application, , , The preferred reference value is , , , , , The preferred weighting coefficients are as follows: , , For example, taking a certain associated station area as an example, if , , ,but synergy difference .

[0061] If the coordination difference meets the first adjustment condition, the scheduling window is dynamically updated; if the second adjustment condition is met, the optimal scheduling strategy for each target distribution area is calculated based on the second operating parameters of each associated distribution area through the microgrid collaborative optimization model.

[0062] The first adjustment conditions include ( (As the first threshold, set to 0.2) and ( The second threshold is set to 0.1, and ).like Then expand the scheduling window to its original size. times, if Then shrink the scheduling window to its original size. For example, the difference in coordination degree between certain related transformer substations. , The enlarged scheduling window size is then 1 / 3 of the original size. If the difference in the degree of coordination of a certain related distribution area is multiples, , The size of the reduced scheduling window is ( ) times the original size. =0.2 times).

[0063] The second adjustment condition is At this point, based on the second operating parameters of each associated distribution area, the optimal scheduling strategy for the target distribution area is calculated through the microgrid collaborative optimization model, specifically including:

[0064] A multi-dimensional state matrix S is constructed based on the second operating parameter. Where n is the number of associated transformer substations (e.g., 5), m is the number of status parameter dimensions (e.g., 6 dimensions such as load, distributed power supply, and interactive power), then S is... The matrix consists of state parameter values ​​corresponding to each associated transformer area.

[0065] The state matrix S is reduced in dimensionality to obtain a low-dimensional feature matrix. , W is the dimensionality reduction transformation matrix (which can be determined by principal component analysis). For example, by reducing the 6-dimensional state parameters to 3 dimensions through principal component analysis, we obtain W as... The matrix, for The low-dimensional feature matrix.

[0066] Based on low-dimensional feature matrix By improving the particle swarm optimization algorithm, the optimal solution of the microgrid collaborative optimization model is obtained, and the output plan of each distributed power source and the power control command of the tie line are obtained.

[0067] The microgrid collaborative optimization model aims to minimize the total system operating cost, and its objective function is:

[0068] ,in, For network loss costs (e.g., if the network loss power is 20kW, the electricity price is 0.6 yuan / (kW·h), and the operating time is 1 hour, then...) ), The cost of curtailing distributed power generation (if a distributed power generation curtails 10kW, the electricity price is 0.5 yuan / (kW·h), and the operating time is 1 hour, then...) ), Environmental penalty costs (e.g., the penalty cost for pollutant emissions during a certain period is 8 yuan). , , Weighting coefficients ( , , If .

[0069] The constraint conditions include power balance constraints, device capacity constraints, micro-grid tie-line power constraints and voltage safety constraints, wherein the power balance constraints are specifically For example, there are three micro-grids in a certain area, and the distributed power output is 200kW, 180kW and 220kW, respectively, the substation and the main grid interact with 100kW, and the load of each substation is 300kW, 250kW and 230kW, respectively, and the network loss is 20kW, then , , , 600+100=780+20, which satisfies the power balance constraint.

[0070] The speed update formula of the improved particle swarm algorithm is:

[0071] wherein w is the inertia weight, , , is a learning factor, in the present application, preferably, , , , is a [0, 1] random number (such as , , ), is the individual optimal position, g is the global optimal position, is the optimal position of the micro-grid cluster, and the adaptive adjustment formula of the inertia weight w is:

[0072] wherein t is the current iteration number (such as 50 times), T is the maximum iteration number (such as 200 times), , are the maximum and minimum inertia weights (such as , ), then .

[0073] A flexible interconnection system optimization scheduling system of a power distribution substation, the system comprises a data acquisition module, a collaborative analysis module, a window adjustment module, an optimization scheduling module and a prediction module;

[0074] The data acquisition module is configured to acquire first operation parameters of a target transformer area and an initial scheduling window based on real-time operation data of the flexible interconnection system of the transformer area, wherein the real-time operation data includes load data of each transformer area, output data of a distributed power supply, and micro-grid interaction data. For example, the relevant data is collected and transmitted in real time by smart meters installed in each transformer area, distributed power supply monitoring devices, and micro-grid interaction interfaces. The data acquisition frequency can be set to 15 minutes per time to ensure the real-time and accuracy of the data.

[0075] The collaborative analysis module is configured to acquire second operation parameters of associated transformer areas based on the initial scheduling window and calculate a collaborative degree difference. The module receives the initial scheduling window information and real-time operation data of the associated transformer areas transmitted by the data acquisition module, automatically calculates the collaborative degree and the collaborative degree difference between each associated transformer area and the target transformer area according to a preset collaborative degree calculation method, and transmits the calculation results to the window scheduling module and the optimal scheduling module.

[0076] The window scheduling module is configured to adjust the scheduling window according to the collaborative degree difference. If the collaborative degree difference is greater than 0, the scheduling window is expanded according to a preset formula. If the collaborative degree difference is less than 0, the scheduling window is reduced. The window scheduling module is configured to adjust the scheduling window according to the collaborative degree difference. If the collaborative degree difference is greater than 0, the scheduling window is expanded according to a preset formula. If the collaborative degree difference is less than 0, the scheduling window is reduced.

[0077] The optimal scheduling module is configured to calculate an optimal scheduling strategy through a micro-grid collaborative optimization model when the collaborative degree difference satisfies The optimal scheduling module is configured to calculate an optimal scheduling strategy through a micro-grid collaborative optimization model when the collaborative degree difference satisfies

[0078] The matrix construction unit is configured to construct a multi-dimensional state matrix S based on the second operation parameters of the associated transformer areas transmitted by the collaborative analysis module. For example, six-dimensional state parameters of five associated transformer areas are arranged into a 5x6 matrix.

[0079] The dimension reduction processing unit is configured to reduce the dimension of the state matrix S by principal component analysis. First, the covariance matrix of the matrix S is calculated, and then the eigenvalues and eigenvectors of the covariance matrix are solved. The first k eigenvectors are selected according to the contribution rate of the eigenvalues to form a dimension reduction conversion matrix W. Finally, the low-dimensional matrix is obtained by multiplying the state matrix S and W.

[0080] ​The intelligent solution unit uses an improved particle swarm algorithm to solve the optimization model, and outputs a scheduling scheme containing energy storage discharge plan, distributed power output curve and tie line power control instructions, for example, according to the optimization structure, the charge and discharge plan of a certain energy storage device within the next 24 hours is formulated (such as discharging from 8:00 to 12:00, discharging power 100kW, charging from 20:00 to 6:00 the next day, charging power 80kW), the output curve of a certain distributed photovoltaic power station (changes with solar intensity, reaches the maximum value of 350kW at 12 o'clock noon) and the power control instructions of each tie line (such as the transmission power of a certain tie line is 120kW from 9:00 to 11:00). The optimization scheduling module also includes a microgrid cluster decision unit for coordinating the output plan of different microgrids and the allocation of tie line power, for example, when the output of a certain microgrid is insufficient, other microgrids with sufficient output are coordinated to transmit power to it through the tie line to ensure the stable operation of each microgrid and the whole system.

[0081] The prediction module is used to predict the load data and distributed power output data of the transformer area in the next 24 hours based on the LSTM neural network, and the input features of the prediction module include historical load data (such as hourly load data in the past month), meteorological data (such as temperature, light intensity, wind speed, etc.), date type (such as weekdays, weekends, holidays) and microgrid operation mode label (such as grid-connected operation, off-grid operation). Through the training of a large amount of historical data, the LSTM neural network can learn the change rule of load and distributed power output, so as to realize accurate prediction, for example, predicting that the load of a certain transformer area at 10:00 the next day is 850kW, and the output of a certain photovoltaic power station at 12:00 the next day is 320kW.

[0082] A power distribution area flexible interconnection system optimization scheduling device, the device includes a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program is executed by the processor to realize the above-mentioned power distribution area flexible interconnection system optimization scheduling method, for example, the processor can use Intel Core i7 series processor, the storage can use 8GB DDR4 memory and 512GB SSD solid state disk, the device realizes data acquisition, calculation, analysis and scheduling instruction generation functions by installing corresponding operating system (such as Windows 10) and software program.

[0083] A computer readable storage medium, the storage medium stores a computer program, the computer program is executed by a processor to realize the power distribution substation flexible interconnection system optimization scheduling method, the computer readable storage medium can be a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk and various storage program codes, for example, the computer program is stored in the U disk, when it is needed to use, the U disk is inserted into the computer or the corresponding device, the processor reads the computer program in the U disk and executes, thereby realizing the optimization scheduling of the power distribution substation flexible interconnection system.

[0084] In the embodiment of the present application, it needs to be clear that the system determines the target substation first when running, and obtains its key running parameters (such as voltage, current, power factor, etc. first running parameters), and the initial scheduling is constructed with the target substation as the center (based on the historical optimization result to set the range), but the initial window has already contained multiple associated substation with flexible interconnection relationship with the target substation, and not only for a single substation to carry out scheduling, the system calculates the coordination difference of each associated substation and the target substation through the collaborative analysis module , according to the relationship between and the threshold value , the scheduling window is dynamically adjusted: when the coordination degree is large), the scheduling window is expanded to times of the original size, and more associated substation is included to strengthen the coordination, when (the coordination degree is small), the window is reduced to times of the original size, and focuses on the closely associated substation, when , the optimal strategy is calculated based on the parameters of multiple substation, it can be seen that the scheduling range always covers multiple substation, and dynamically changes.

[0085] The microgrid coordination optimization model takes the minimum of the total system operation cost as the target, comprehensively considers the network loss cost, the abandoned power cost and the environmental penalty cost of all the substation included in the scheduling range, and the constraint conditions also cover the power balance and equipment capacity of multiple substation, finally realizes the overall optimization of multiple substation in the region, rather than the independent optimization of a single substation.

[0086] The data acquisition module configured by the system acquires the core data such as load data, distributed power output data and interactive power of each substation through intelligent electric meters, DG monitoring terminals, microgrid interaction interfaces and other hardware, the acquisition frequency is 15 minutes / time, and the data accuracy is controlled within ±0.5%. The module has a standardized data output interface (IEC61850 protocol commonly used in power system can be adapted), which provides a basis for uploading data to the scheduling station.

[0087] The final output of the optimization scheduling module, such as the energy storage charging and discharging plan, distributed power output curve, and tie-line power control instruction, belongs to the core monitoring content of the power dispatching station. The optimization scheduling module of the system is directly linked with the distribution station control system, while the dispatching station of the power supply company can realize data interaction with the station control system through the distribution network SCADA system (data acquisition and monitoring control system) to obtain the dispatching scheme and execution feedback.

[0088] The distribution station flexible interconnection system optimization scheduling equipment" contains a processor, a memory, and a computer program, which supports remote communication with the superior dispatching system. From the perspective of standardized design of the power system, such equipment usually integrates a 4G / 5G or optical fiber communication module, which can actively upload real-time data (such as the operating parameters of each station area, ΔC calculation results) and dispatching schemes to the dispatching station of the power supply company, realizing centralized monitoring.

[0089] The optimization scheduling module contains a "matrix construction unit, dimension reduction processing unit, and intelligent solving unit", which is the core decision-making unit of the entire system and is not distributed in each terminal device of the station area. The core task of the matrix construction unit is to process multi-station area data, which necessarily relies on the computing power and data aggregation capacity of the centralized platform.

[0090] The core work of the matrix construction unit is to construct a multi-dimensional state matrix , where n is the number of associated station areas, and m is the dimension of the state parameters. The matrix elements cover all the parameters of the associated station areas, such as load, distributed power output, interaction power, and voltage deviation. These data need to be collected by the data acquisition module and transmitted to the platform. The single station area device can only collect its own data and cannot obtain the operating parameters of other station areas, so it cannot independently construct a multi-station area state matrix.

[0091] The complete work link of the matrix construction unit is:

[0092] The data acquisition module collects the operating parameters of the target station area and associated station areas; the collaborative analysis module calculates ΔC and determines the final dispatching range; the matrix construction unit constructs the state matrix S based on the parameters of all station areas within the range; after dimension reduction processing, the intelligent solving unit solves the optimal solution through the improved particle swarm algorithm to generate a unified dispatching scheme; the dispatching scheme is issued to the photovoltaic, energy storage devices, and tie-line control equipment of each station area through the platform, realizing the coordinated regulation of multiple devices.

[0093] If the matrix construction function is dispersed in each station area device, it will lead to independent decision-making of each station area, which cannot consider the flexible interconnection relationship and power interaction constraints between station areas, which is contrary to the core goal of "multi-station area collaborative optimization". The centralized platform can realize global data sharing and unified calculation, ensuring that the dispatching scheme meets the goal of minimizing the total operating cost of the system, while meeting the global constraints such as power balance and voltage safety.

[0094] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since various modifications can be made by those skilled in the art, without departing from the spirit and scope of the application, which are defined by the appended claims and their equivalents.

Claims

1. A power distribution district flexible interconnection system optimal scheduling method, characterized in that, The method comprises the following steps: Based on the real-time operation data of the flexible interconnection system of the power distribution area, the first operation parameter and the initial scheduling window of the target area are obtained, the real-time operation data includes the load data of each area, the distributed power output data and the micro-grid interaction data, the first operation parameter is the key state parameter of the target area, and the initial scheduling window is set based on the historical optimization result; Based on the initial scheduling window, the second operation parameter of the plurality of associated areas is obtained from the system, the initial scheduling window is centered on the target area, and the plurality of associated areas are located in the initial scheduling window and have a flexible interconnection relationship with the target area; calculating a difference of the degree of synergy of each second operating parameter and the first operating parameter , wherein is the degree of synergy of the ith associated station area and the target station area, is a preset reference degree of synergy; If the coordination difference value satisfies the first adjustment condition, the scheduling window is dynamically updated, if the coordination difference value satisfies the second adjustment condition, the optimal scheduling strategy of the target station area is calculated through the micro-grid system optimization model based on the second operation parameter of each associated station area. The dynamic updating of the scheduling window comprises: if , is the first threshold, expanding the scheduling window to times of the original size, if , is the second threshold, reducing the scheduling window to times of the original size; the second adjustment condition is The micro-grid collaborative optimization model takes the minimum total system operation cost as the target, and the objective function is: , wherein, is the network loss cost, is the distributed power abandoned electricity cost, is the environmental penalty cost, , , is the weight coefficient; The constraint conditions include power balance constraint, equipment capacity constraint, micro-grid tie-line power constraint and voltage safety constraint.

2. The optimal dispatching method of a flexible interconnection system of a power distribution area according to claim 1, characterized in that: The synergy degree The calculation method is: wherein, , , are the active power, the reactive power and the voltage deviation of the ith associated substation with the target substation, respectively, , , are reference values, , , are weight coefficients and satisfy .

3. The optimal dispatching method of a flexible interconnection system of a power distribution area according to claim 1, characterized in that: The optimal scheduling strategy of the target area is calculated through the micro-grid collaborative optimization model based on the second operation parameter of each associated area, which comprises: constructing a multi-dimension state matrix S based on the operation parameters, wherein n is the number of associated transformer stations, and m is the dimension of the state parameters. The state matrix S is reduced in dimension to obtain a low-dimensional feature matrix , , W is a dimension reduction conversion matrix; Low-dimensional feature matrix The optimal solution of the micro-grid collaborative optimization model is solved by improving the particle swarm algorithm, and the tie-line power regulation instructions of each distributed power processing computer are obtained.

4. The optimal dispatching method of a flexible interconnection system of a power distribution area according to claim 3, characterized in that: The speed update formula of the improved particle swarm algorithm is: wherein w is an inertia weight, , , is a learning factor, , , is a [0, 1] random number, is an individual optimal position, g is a global optimal position, is a micro-grid cluster optimal position, used to reflect the collaborative relationship between micro-grids; The inertia weight w is adaptively adjusted by the formula: where t is the current iteration number, T is the maximum iteration number, , and wmax, wminare the maximum and minimum inertia weight, respectively.

5. The optimal dispatching method of a flexible interconnection system of a power distribution area according to claim 1, characterized in that: The power balance constraint is specifically: wherein, is the output of distributed generation in the ith micro-grid, is the interaction power between the substation and the main grid, is the load of the ith substation, is the network loss.

6. A power distribution zone flexible interconnection system optimal dispatching system, characterized in that, The method comprises the following steps: The data acquisition module is used to obtain the first operation parameter and the initial scheduling window of the target area based on the real-time operation data of the flexible interconnection system of the power distribution area, and the real-time operation data includes the load data of each area, the distributed power processing data and the micro-grid interaction data; A cooperative analysis module is configured to acquire second operating parameters of associated base stations based on the initial scheduling window, and calculate a cooperative degree difference value ; a window adjusting module, configured to enlarge the scheduling window if reduce the scheduling window if The optimization scheduling module is configured to calculate an optimal scheduling strategy through a micro-grid collaborative optimization model if , The optimization scheduling module comprises a micro-grid cluster decision unit for coordinating the output plan of different micro-grids and the tie-line power allocation.

7. The optimal dispatching system for flexible interconnection of power distribution zones according to claim 6, characterized in that: The optimization scheduling module comprises: A matrix construction unit is used to construct a multi-dimensional state matrix S; A dimension reduction processing unit is used to reduce the dimension of the state matrix S through principal component analysis; An intelligent solving unit is used to solve the optimization model by using an improved particle swarm algorithm, and output a scheduling scheme including a storage charging and discharging plan, a distributed power output curve and a tie-line power control instruction.

8. The optimal dispatching system for flexible interconnection of power distribution zones according to claim 6, characterized in that, Further comprising: A prediction module is used to predict the area load data and the distributed power output data in the next 24 hours based on an LSTM neural network; The input features of the prediction module include historical load data, meteorological data, date type and micro-grid operation mode label.

9. A power distribution zone flexible interconnection system optimal dispatching device, characterized in that, The computer program stored in the storage and executable on the processor is executed by the processor to implement the power distribution area flexible interconnection system optimization scheduling method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that, The computer program stored in the storage and executable on the processor is executed by the processor to implement the power distribution area flexible interconnection system optimization scheduling method according to any one of claims 1 to 5.

Images