Active power distribution network voltage control method and system based on data driving

Abstract

The invention provides an active power distribution network voltage control method and system based on data driving, and the method comprises the steps: inputting historical data of an active power distribution network to a load flow calculation model of a preset active power distribution network, and obtaining load flow calculation data outputted by the load flow calculation model of the active power distribution network; determining a power flow linear regression matrix equation based on data driving according to the power flow calculation data, and solving a coefficient matrix and a constant term matrix of the power flow linear regression matrix equation; inputting the to-be-regulated node voltage calculation value, the coefficient matrix and the constant term matrix to a voltage control model of a preset active power distribution network, and obtaining a power distribution network node voltage control strategy output by the voltage control model of the active power distribution network through linear programming; the voltage control model of the active power distribution network takes minimization of economic cost as an objective function. According to the method, power distribution network topology identification is not needed, voltage control design can be completed by directly using data, and the flexibility and adaptability of voltage control are improved through linear programming.

Description

Technical Field

[0001] The present invention relates to the field of distribution network operation and control technology, and in particular to a data-driven active distribution network voltage control method and system. Background Art

[0002] In the context of global warming and the dual carbon goals, a large number of renewable distributed power sources (such as photovoltaics) are connected to the distribution network, and the problem of voltage over-limit in the distribution network is becoming more and more serious, which brings great challenges to the safety control of the distribution network. At the same time, due to the complex topology of medium and low voltage distribution networks, it is difficult to collect electrical parameters, and the measurement system is not as complete as the transmission network, making it difficult for traditional distribution network control methods based on precise physical modeling to play a role. Summary of the invention

[0003] The present invention provides a data-driven active distribution network voltage control method and system to solve the defect that the traditional distribution network control method based on precise physical modeling in the prior art is difficult to play a role in medium and low voltage distribution networks. The present invention does not need to identify the distribution network topology, and can directly use data to complete the voltage control design, and improve the flexibility and adaptability of voltage control through linear programming.

[0004] The present invention provides a data-driven active distribution network voltage control method, comprising: inputting historical data of the active distribution network into a preset active distribution network flow calculation model, obtaining flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data comprises annual power generation data of distributed renewable energy, annual load data and voltage calculation values ​​of nodes to be regulated; determining a data-driven flow linear regression matrix equation according to the flow calculation data, and solving a coefficient matrix and a constant term matrix of the flow linear regression matrix equation; inputting the voltage calculation values ​​of the nodes to be regulated, the coefficient matrix and the constant term matrix into a preset active distribution network voltage control model, obtaining a distribution network node voltage control strategy output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic cost as an objective function.

[0005] According to a data-driven active distribution network voltage control method provided by the present invention, the power flow calculation model of the active distribution network includes a distributed photovoltaic output model and a load change model; the historical data of the active distribution network includes historical time data of the maximum photovoltaic power generation, historical active load data and historical reactive load data; the historical data of the active distribution network is input to the preset power flow calculation model of the active distribution network to obtain the power flow calculation data output by the power flow calculation model of the active distribution network, including: inputting the historical time data of the maximum photovoltaic power generation to the distributed photovoltaic output model to obtain the distributed photovoltaic annual power generation data output by the distributed photovoltaic output model; inputting the historical active load data and the historical reactive load data to the load change model to obtain the annual load data output by the load change model; performing power flow calculation according to the distributed photovoltaic annual power generation data and the annual load data to obtain the voltage calculation value of the node to be regulated.

[0006] According to a data-driven active distribution network voltage control method provided by the present invention, the historical active load data and the historical reactive load data are input into the load change model to obtain the annual load data output by the load change model, including: arranging the historical active load data and the historical reactive load data into a distribution network load data set in the form of a time series; the distribution network load data set includes a plurality of data points composed of the historical active load data and the historical reactive load data; randomly selecting a plurality of cluster centroids based on the K-means algorithm; calculating the Euclidean distance from each of the data points to all cluster centroids, and allocating the data points to the area closest to the cluster centroid; updating a plurality of cluster centroids according to the mean of the data points that have been aggregated in each area, returning to the step of calculating the Euclidean distance, and repeating the iterative execution until the change of the cluster centroid is less than the preset change threshold, terminating the clustering process, and obtaining the annual load data.

[0007] According to a data-driven active distribution network voltage control method provided by the present invention, the data-driven power flow linear regression matrix equation is: in, U is the calculated value of the voltage of the node to be regulated, P is the annual active load data, Q is the annual reactive load data, A is the coefficient matrix, C is the constant term matrix.

[0008] According to a data-driven active distribution network voltage control method provided by the present invention, the objective function of the voltage control model of the active distribution network is: in, F is the objective function, T is the number of control cycles, t For time, is the voltage deviation additional cost coefficient, is the average node voltage deviation of the system in the tth control cycle, To mobilize the cost of energy storage compensation, The cost of photovoltaic active power compensation, The cost of photovoltaic reactive power compensation, The cost of reactive power compensation for capacitors, The energy storage active power adjusted to control the voltage, The photovoltaic active power adjusted when controlling the voltage, The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. The reactive power provided by the capacitors that are adjusted to control the voltage, is the average node voltage deviation of the system in the entire control cycle, N is the number of distribution network nodes, For Node i The voltage, For the standard voltage range, is the lower limit of node voltage operation, It is the upper limit of node voltage operation.

[0009] According to a data-driven active distribution network voltage control method provided by the present invention, the constraints of the voltage control model of the active distribution network include energy storage charging and discharging power constraints, energy storage capacity constraints, photovoltaic inverter constraints and line capacitor constraints; The energy storage charging and discharging power constraint is: The energy storage capacity constraint is: The PV inverter constraints are: The line capacitor constraint is: in, is the minimum allowable charging and discharging power of energy storage, is the maximum allowable charging and discharging power of energy storage, For the i Energy storage t The output power at the moment, For the iEnergy storage t The energy storage capacity at the moment, is the minimum capacity of energy storage, is the maximum capacity of energy storage, For the i The rated capacity of the energy storage, For the i Energy storage t -1 moment of energy storage capacity, For the i The charging and discharging efficiency of the energy storage is For the i PV inverters t The maximum adjustable reactive power of the photovoltaic inverter at any moment, The photovoltaic active power adjusted when controlling the voltage, for t The active power output by the photovoltaic inverter at any moment, For the i The rated capacity of each PV inverter is The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. is the maximum reactive power that the capacitor can provide, The reactive power provided by the capacitors that are adjusted to control the voltage, is the power system frequency, is the capacitance value, For Node i voltage.

[0010] The present invention also provides a data-driven active distribution network voltage control system, comprising: a flow calculation module, used to input the historical data of the active distribution network into a preset flow calculation model of the active distribution network, and obtain the flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data includes the annual power generation data of distributed renewable energy, the annual load data and the voltage calculation value of the node to be regulated; an equation solving module, used to determine the data-driven flow linear regression matrix equation according to the flow calculation data, and solve the coefficient matrix and the constant term matrix of the flow linear regression matrix equation; a voltage control module, used to input the voltage calculation value of the node to be regulated, the coefficient matrix and the constant term matrix into the preset voltage control model of the active distribution network, and obtain the distribution network node voltage control strategy output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic cost as the objective function.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the data-driven active distribution network voltage control method as described above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the data-driven active distribution network voltage control method as described in any one of the above is implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned data-driven active power distribution network voltage control methods.

[0014] The present invention provides a data-driven active distribution network voltage control method and system, the method comprising: inputting historical data of the active distribution network into a preset active distribution network flow calculation model, obtaining flow calculation data output by the flow calculation model of the active distribution network; determining a data-driven flow linear regression matrix equation according to the flow calculation data, and solving the coefficient matrix and constant term matrix of the flow linear regression matrix equation; inputting the voltage calculation value of the node to be regulated, the coefficient matrix and the constant term matrix into the preset active distribution network voltage control model, obtaining the distribution network node voltage control strategy output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic cost as the objective function. The present invention does not need to identify the topology of the distribution network, can directly use data to complete the voltage control design, and improves the flexibility and adaptability of voltage control through linear programming. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of the data-driven active distribution network voltage control method provided by the present invention.

[0017] Figure 2 It is a seasonal photovoltaic power generation curve diagram after clustering provided by the present invention.

[0018] Figure 3 This is the annual active load variation curve diagram provided by the present invention.

[0019] Figure 4This is the reactive load variation curve diagram provided by the present invention throughout the year.

[0020] Figure 5 This is the IEEE33 topology diagram provided by the present invention.

[0021] Figure 6 This is a three-dimensional diagram of node voltage before planning provided by the present invention.

[0022] Figure 7 This is a three-dimensional diagram of node voltage after planning provided by the present invention.

[0023] Figure 8 It is a structural schematic diagram of the data-driven active distribution network voltage control system provided by the present invention.

[0024] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0026] As the penetration rate of renewable distributed power sources increases significantly, it brings more flexibility and controllability to active distribution networks. However, the uncertainty and volatility of distributed power output may also lead to voltage over-limit problems, which seriously affects the safe and stable operation of distribution networks.

[0027] Please refer to Figure 1 , Figure 1 A schematic flow chart of the data-driven active distribution network voltage control method provided by the present invention.

[0028] The purpose of the present invention is to meet the voltage control requirements of high-penetration photovoltaic in modern power distribution systems. Since the electrical parameters of medium and low voltage distribution networks are often not collected and the measurement system is not as complete as that of the transmission network, it is difficult to apply the power flow method of the transmission network based on the admittance matrix to the medium and low voltage distribution network in practice. In view of this, the present invention provides a data-driven active distribution network voltage control method, comprising: 101: Inputting historical data of the active distribution network into a preset power flow calculation model of the active distribution network, and obtaining power flow calculation data output by the power flow calculation model of the active distribution network; the power flow calculation data includes annual power generation data of distributed renewable energy, annual load data and voltage calculation values ​​of nodes to be regulated.

[0029] As a preferred embodiment, the power flow calculation model of the active distribution network includes a distributed photovoltaic output model and a load change model; the historical data of the active distribution network includes historical time data of the maximum photovoltaic power generation, historical active load data and historical reactive load data; the historical data of the active distribution network is input into the power flow calculation model of the preset active distribution network to obtain the power flow calculation data output by the power flow calculation model of the active distribution network, including: inputting the historical time data of the maximum photovoltaic power generation into the distributed photovoltaic output model to obtain the distributed photovoltaic annual power generation data output by the distributed photovoltaic output model; inputting the historical active load data and the historical reactive load data into the load change model to obtain the annual load data output by the load change model; performing power flow calculation according to the distributed photovoltaic annual power generation data and the annual load data to obtain the voltage calculation value of the node to be regulated.

[0030] As a preferred embodiment, historical active load data and historical reactive load data are input into a load change model to obtain annual load data output by the load change model, including: organizing the historical active load data and historical reactive load data into a distribution network load data set in the form of a time series; the distribution network load data set includes a number of data points consisting of historical active load data and historical reactive load data; randomly selecting a number of cluster centroids based on a K-means algorithm; calculating the Euclidean distance from each data point to all cluster centroids, and assigning the data points to the area closest to the cluster centroid; updating a number of cluster centroids according to the mean of the data points that have been aggregated in each area, returning to the step of calculating the Euclidean distance, and repeating the iterative execution until the change in the cluster centroid is less than a preset change threshold, terminating the clustering process, and obtaining the annual load data.

[0031] In this embodiment, photovoltaic power generation is used as an example for description. Of course, the method of the present invention is also applicable to new energy power generation such as wind power generation and hydropower generation.

[0032] The photovoltaic power generation system directly converts solar energy into DC power. When connected to the grid, the current control inverter converts DC power into AC power with the same frequency and phase as the distribution network and connects it to the grid. The photovoltaic grid-connected system inverter mainly adopts voltage source current control. It only needs to control the inverter output current to track the grid voltage to achieve the purpose of parallel operation. When the photovoltaic power source is connected to the grid, the power factor can be kept at 1. In the power flow calculation, only the active power can be considered and it can be processed as a PQ node.

[0033] Please refer to Figure 2 , Figure 2 This is a clustered seasonal photovoltaic power generation curve diagram provided by the present invention.

[0034] Input the historical time data of the maximum photovoltaic power generation into the distributed photovoltaic output model, and obtain the distributed photovoltaic annual power generation data output by the distributed photovoltaic output model, which satisfies the relationship: in, For time t of photovoltaic power generation, is the maximum power of photovoltaic power generation, is the time point when the maximum power generation occurs (historical time data), which depends on the peak time of local radiation. To indicate the speed at which power generation decreases from the maximum value, the illumination time is controlled. is a natural constant, approximately equal to 2.71828, is a constant used to convert radiation values ​​into power generation, for example, taking into account factors such as the efficiency of photovoltaic modules and system losses. is the local maximum radiation value.

[0035] Please refer to Figure 3 , Figure 3 The present invention provides a full-year load variation curve diagram.

[0036] Please refer to Figure 4 , Figure 4 The present invention provides a year-round reactive load variation curve diagram.

[0037] Input historical active load data and historical reactive load data into the load change model to obtain the annual load data output by the load change model; the load change model uses the K-means algorithm to cluster the load curves of the past few years to calculate the annual active load and annual reactive load respectively.

[0038] Specifically, the historical active load data and historical reactive load data are organized into a distribution network load data set in the form of time series. ; The distribution network load data set includes several data points consisting of historical active load data and historical reactive load data. It's time point t of active and reactive loads.

[0039] Random Selection j Initial centroid (Right now , ), calculate each data point Euclidean distance to all centroids and assign the data point to the region of the nearest cluster centroid middle: in, d is the Euclidean distance, Cluster is the area where the cluster centroid is located, argmin j The step used to find the nearest cluster center for each data point.

[0040] For each cluster area j , update the cluster centroid by calculating the mean of all data points in the current cluster area: in, n is the number of iterations, For the n The iteration j Cluster centroids ( , ), For the n +1 iteration j Cluster centroids ( , ), , ) is the n The data points of the sub-cluster, For clustering j The number of data points in the region.

[0041] If for each cluster area, the change of the cluster centroid is less than the preset change threshold , then convergence, the clustering process ends, and the annual active load is obtained Reactive load Finally, the voltage calculation value of the node to be regulated is obtained through power flow calculation ; If it does not converge, continue iterating.

[0042] 102: Determine the data-driven power flow linear regression matrix equation based on the power flow calculation data, and solve the coefficient matrix and constant term matrix of the power flow linear regression matrix equation.

[0043] As a preferred embodiment, the power flow linear regression matrix equation based on data driving is: in, U is the calculated value of the node voltage, P is the annual active load data, Q is the annual reactive load data, A is the coefficient matrix, C is the constant term matrix.

[0044] In this embodiment, in order to obtain a more accurate solution, the power flow calculation data is divided into months, and a power flow linear regression matrix equation driven by data is determined.

[0045] in, A is the regression equation coefficient matrix, C is the constant term matrix, , is the node net load matrix (load minus the active power of distributed power sources. The distributed power sources connected in this patent are photovoltaic, so only active power needs to be considered). When the node is connected to photovoltaic i Node net load, is the node active load, The active power generated by the photovoltaic power generation connected to the node. If there is no distributed power supply at the node, the net load of the node is the annual active load. Reactive load There are 8760 hours in a year (please refer to Table 1). Taking the number of hours in a month as the breakpoint, write the linear regression equation for the data of different months.

[0046] Table 1 is a time interval table

[0047] The least squares method is used to fit and solve the data-driven power flow linear regression matrix equation.

[0048] make , then the regression equation is: in, Error sum of squares, matrix is the set matrix of known quantities, is the model prediction value matrix during the fitting process, is the unknown quantity set matrix, and They are the active net load and reactive net load at time t respectively.

[0049] It should be noted that PLR (Polynomial Logistic Regression) is a statistical modeling method that aims to capture linear features in different intervals by dividing data into multiple intervals (segments). This method is very friendly to the temporal characteristics of data and helps to identify behavioral relationships in different time periods.

[0050] 103: Input the calculated value of the node voltage to be regulated, the coefficient matrix and the constant term matrix to the preset voltage control model of the active distribution network, and obtain the voltage control strategy of the distribution network node output by the linear programming of the voltage control model of the active distribution network; the voltage control model of the active distribution network takes minimizing the economic cost as the objective function.

[0051] As a preferred embodiment, the objective function of the voltage control model of the active power distribution network is: in, F is the objective function, T is the number of control cycles, t For time, is the voltage deviation additional cost coefficient, is the average node voltage deviation of the system in the tth control cycle, To mobilize the cost of energy storage compensation, The cost of photovoltaic active power compensation, The cost of photovoltaic reactive power compensation, The cost of reactive power compensation for capacitors, The energy storage active power adjusted to control the voltage, The photovoltaic active power adjusted when controlling the voltage, The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. The reactive power provided by the capacitors that are adjusted to control the voltage, is the average node voltage deviation of the system in the entire control cycle, N is the number of distribution network nodes, For Node i The voltage, For the standard voltage range, is the lower limit of node voltage operation, It is the upper limit of node voltage operation.

[0052] As a preferred embodiment, the constraints of the voltage control model of the active distribution network include energy storage charging and discharging power constraints, energy storage capacity constraints, photovoltaic inverter constraints and line capacitor constraints; The energy storage charging and discharging power constraints are: The energy storage capacity constraint is: The PV inverter constraints are: The line capacitor constraint is: in, is the minimum allowable charging and discharging power of energy storage, is the maximum allowable charging and discharging power of energy storage, For the i Energy storage t The output power at the moment, For the iEnergy storage t The energy storage capacity at the moment, is the minimum capacity of energy storage, is the maximum capacity of energy storage, For the i The rated capacity of the energy storage, For the i Energy storage t -1 moment of energy storage capacity, For the i The charging and discharging efficiency of the energy storage is For the i PV inverters t The maximum adjustable reactive power of the photovoltaic inverter at any moment, The photovoltaic active power adjusted when controlling the voltage, for t The active power output by the photovoltaic inverter at any moment, For the i The rated capacity of each PV inverter is The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. is the maximum reactive power that the capacitor can provide, The reactive power provided by the capacitors that are adjusted to control the voltage, is the power system frequency, is the capacitance value, For Node i voltage.

[0053] When it is positive, it means the energy storage is in charging state. When it is negative, it means that the energy storage is in a discharging state, and the energy storage cannot be charged and discharged at the same time; Typically 50Hz.

[0054] According to the data-driven power flow linear regression matrix equation and the voltage control model of the active distribution network, the commercial solver gurobi is used to solve the problem. By adjusting the voltage calculated value of the node to be regulated, the voltage regulation method with the lowest cost can be obtained.

[0055] It should be noted that LP (Linear Programming) is to decompose the optimization problem into linear programming sub-problems and then solve them one by one.

[0056] Gurobi solver has excellent solving performance and efficient algorithm design, which enables it to quickly handle large-scale linear programming (LP), mixed integer programming (MIP) and other mathematical optimization problems. Gurobi's optimization solving speed far exceeds many similar tools, especially when facing complex problems, it can effectively reduce the solution time, which is especially important for real-time decision-making and dynamic programming.

[0057] Of course, the solver may also be a cplex solver, and the present invention does not make any special limitation here.

[0058] Please refer to Figure 5 , Figure 5 The IEEE33 topology diagram provided by the present invention.

[0059] Taking the standard example IEEE33 node as an example, nodes 13, 18, 22, 25, and 33 are equipped with 1MW photovoltaic panels and energy storage integrated devices.

[0060] Please refer to Figure 6 , Figure 6 This is a three-dimensional diagram of node voltage before planning provided by the present invention.

[0061] On a typical day, before planning, the node voltage exceeds the upper limit and the lower limit.

[0062] Please refer to Figure 7 , Figure 7 This is a three-dimensional diagram of node voltage after planning provided by the present invention.

[0063] Using this monthly linear regression equation, linear programming is performed based on node voltage sensitivity and power regulation cost. Since the cost of regulating reactive power is low, reactive power compensation is given priority, and the voltage deviation is added with a cost coefficient. Set to the maximum value of the cost coefficient so that the node voltage is always within the specified range. , 0.95 and 1.05 respectively. The three-dimensional diagram of the node voltage after adjustment shows that on this typical day, only photovoltaic inverters and line capacitors were used for reactive power compensation during the adjustment process, which effectively controlled the node voltage within the specified range, and the reactive power adjustment amount and adjustment node could be solved.

[0064] The data-driven active distribution network voltage control system provided by the present invention is described below. The data-driven active distribution network voltage control system described below and the data-driven active distribution network voltage control method described above can refer to each other.

[0065] Please refer to Figure 8 , Figure 8 A schematic structural diagram of the data-driven active distribution network voltage control system provided by the present invention.

[0066] The present invention also provides a data-driven active distribution network voltage control system, including: a flow calculation module 801, which is used to input the historical data of the active distribution network into a preset flow calculation model of the active distribution network, and obtain the flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data includes the annual power generation data of distributed renewable energy, the annual load data and the voltage calculation value of the node to be regulated; an equation solving module 802, which is used to determine the data-driven flow linear regression matrix equation according to the flow calculation data, and solve the coefficient matrix and the constant term matrix of the flow linear regression matrix equation; a voltage control module 803, which is used to input the voltage calculation value of the node to be regulated, the coefficient matrix and the constant term matrix into the preset voltage control model of the active distribution network, and obtain the voltage control strategy of the distribution network node output by the linear programming of the voltage control model of the active distribution network; the voltage control model of the active distribution network takes minimizing the economic cost as the objective function.

[0067] Fig. 9 An example of a structural diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor (processor) 901, a communication interface (Communications Interface) 902, a memory (memory) 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904. The processor 901 can call the logic instructions in the memory 903 to execute the data-driven active distribution network voltage control method, which includes: inputting the historical data of the active distribution network into the preset active distribution network flow calculation model to obtain the flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data includes the annual power generation data of distributed new energy, the annual load data and the voltage calculation value of the node to be regulated; determining the data-driven flow linear regression matrix equation according to the flow calculation data, and solving the coefficient matrix and constant term matrix of the flow linear regression matrix equation; inputting the voltage calculation value of the node to be regulated, the coefficient matrix and the constant term matrix into the preset active distribution network voltage control model, and obtaining the distribution network node voltage control strategy output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic cost as the objective function.

[0068] In addition, the logic instructions in the above-mentioned memory 903 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0069] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the data-driven active distribution network voltage control method provided by the above methods. The method includes: inputting historical data of the active distribution network into a preset active distribution network flow calculation model to obtain flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data includes annual power generation data of distributed new energy, annual load data and voltage calculation values ​​of nodes to be regulated; determining a data-driven flow linear regression matrix equation according to the flow calculation data, and solving the coefficient matrix and constant term matrix of the flow linear regression matrix equation; inputting the voltage calculation values, coefficient matrix and constant term matrix of the nodes to be regulated into the preset active distribution network voltage control model to obtain the distribution network node voltage control strategy output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic costs as the objective function.

[0070] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the data-driven active distribution network voltage control method provided by the above-mentioned methods, the method comprising: inputting historical data of the active distribution network into a preset flow calculation model of the active distribution network, and obtaining flow calculation data output by the flow calculation model of the active distribution network; the flow calculation data comprises annual power generation data of distributed renewable energy, annual load data and voltage calculation values ​​of nodes to be regulated; determining a data-driven flow linear regression matrix equation according to the flow calculation data, and solving the coefficient matrix and constant term matrix of the flow linear regression matrix equation; inputting the voltage calculation values, coefficient matrix and constant term matrix of the nodes to be regulated into the preset voltage control model of the active distribution network, and obtaining the voltage control strategy of the distribution network nodes output by the voltage control model of the active distribution network using linear programming; the voltage control model of the active distribution network takes minimizing economic cost as the objective function.

[0071] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units 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. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0072] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data-driven active distribution network voltage control method, characterized in that: include: Inputting historical data of the active distribution network into a preset power flow calculation model of the active distribution network, and obtaining power flow calculation data output by the power flow calculation model of the active distribution network; the power flow calculation data includes annual power generation data of distributed renewable energy, annual load data and voltage calculation values ​​of nodes to be regulated; Determine a data-driven power flow linear regression matrix equation according to the power flow calculation data, and solve the coefficient matrix and constant term matrix of the power flow linear regression matrix equation; The calculated value of the node voltage to be regulated, the coefficient matrix and the constant term matrix are input into a preset voltage control model of an active distribution network to obtain a distribution network node voltage control strategy output by linear programming using the voltage control model of the active distribution network; the voltage control model of the active distribution network takes minimizing economic cost as an objective function.

2. The data-driven active distribution network voltage control method according to claim 1, characterized in that: The power flow calculation model of the active distribution network includes a distributed photovoltaic output model and a load change model; the historical data of the active distribution network includes historical time data of the maximum photovoltaic power generation, historical active load data and historical reactive load data; The inputting of historical data of the active distribution network into a preset power flow calculation model of the active distribution network to obtain power flow calculation data output by the power flow calculation model of the active distribution network includes: Inputting historical time data of the maximum photovoltaic power generation into the distributed photovoltaic output model to obtain distributed photovoltaic annual power generation data output by the distributed photovoltaic output model; Inputting the historical active load data and the historical reactive load data into the load change model to obtain the annual load data output by the load change model; A power flow calculation is performed according to the distributed photovoltaic annual power generation data and the annual load data to obtain a calculated value of the node voltage to be regulated.

3. The data-driven active distribution network voltage control method according to claim 2, characterized in that: The inputting the historical active load data and the historical reactive load data into the load change model to obtain the annual load data output by the load change model includes: Arranging the historical active load data and the historical reactive load data into a distribution network load data set in the form of a time series; the distribution network load data set includes a plurality of data points consisting of the historical active load data and the historical reactive load data; Based on the K-means algorithm, several cluster centroids are randomly selected; the Euclidean distance from each data point to all cluster centroids is calculated, and the data points are distributed to the area closest to the cluster centroid; according to the mean of the data points that have been clustered in each area, several cluster centroids are updated, and the step of calculating the Euclidean distance is returned, and it is iterated repeatedly until the change of the cluster centroid is less than the preset change threshold, and the clustering process is terminated to obtain the annual load data.

4. The data-driven active distribution network voltage control method according to claim 1, characterized in that: The data-driven power flow linear regression matrix equation is: in, U is the calculated value of the voltage of the node to be regulated, P is the annual active load data, Q is the annual reactive load data, A is the coefficient matrix, C is the constant term matrix.

5. The data-driven active distribution network voltage control method according to claim 1, characterized in that: The objective function of the voltage control model of the active distribution network is: in, F is the objective function, T is the number of control cycles, t For time, is the voltage deviation additional cost coefficient, is the average node voltage deviation of the system in the tth control cycle, To mobilize the cost of energy storage compensation, The cost of photovoltaic active power compensation, The cost of photovoltaic reactive power compensation, The cost of reactive power compensation for capacitors, The energy storage active power adjusted to control the voltage, The photovoltaic active power adjusted when controlling the voltage, The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. The reactive power provided by the capacitors that are adjusted to control the voltage, is the average node voltage deviation of the system in the entire control cycle, N is the number of distribution network nodes, For Node i The voltage, For the standard voltage range, is the lower limit of node voltage operation, It is the upper limit of node voltage operation.

6. The data-driven active distribution network voltage control method according to any one of claims 1 to 5, characterized in that: The constraints of the voltage control model of the active distribution network include energy storage charging and discharging power constraints, energy storage capacity constraints, photovoltaic inverter constraints and line capacitor constraints; The energy storage charging and discharging power constraint is: The energy storage capacity constraint is: The PV inverter constraints are: The line capacitor constraint is: in, is the minimum allowable charging and discharging power of energy storage, is the maximum allowable charging and discharging power of energy storage, For the i Energy storage t The output power at the moment, For the i Energy storage t The energy storage capacity at the moment, is the minimum capacity of energy storage, is the maximum capacity of energy storage, For the i The rated capacity of the energy storage, For the i Energy storage t -1 moment of energy storage capacity, For the i The charging and discharging efficiency of the energy storage is For the i PV inverters t The maximum adjustable reactive power of the photovoltaic inverter at any moment, The photovoltaic active power adjusted when controlling the voltage, for t The active power output by the photovoltaic inverter at any moment, For the i The rated capacity of each PV inverter is The reactive power provided by the photovoltaic inverter to adjust the voltage when controlling the voltage. is the maximum reactive power that the capacitor can provide, The reactive power provided by the capacitors that are adjusted to control the voltage, is the power system frequency, is the capacitance value, For Node i voltage.

7. A data-driven active distribution network voltage control system, characterized in that: include: A power flow calculation module, used to input the historical data of the active distribution network into a preset power flow calculation model of the active distribution network, and obtain the power flow calculation data output by the power flow calculation model of the active distribution network; the power flow calculation data includes the annual power generation data of distributed renewable energy, the annual load data and the voltage calculation value of the node to be regulated; An equation solving module, used for determining a data-driven power flow linear regression matrix equation according to the power flow calculation data, and solving a coefficient matrix and a constant term matrix of the power flow linear regression matrix equation; A voltage control module is used to input the calculated value of the node voltage to be regulated, the coefficient matrix and the constant term matrix into a preset voltage control model of an active distribution network, and obtain a distribution network node voltage control strategy output by a linear programming method using the voltage control model of the active distribution network; the voltage control model of the active distribution network takes minimizing economic costs as an objective function.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the data-driven active power distribution network voltage control method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the data-driven active power distribution network voltage control method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data-driven active power distribution network voltage control method according to any one of claims 1 to 6 is implemented.

Images