Node voltage distribution control optimization method, system, equipment, medium and product of power distribution area

Abstract

The invention relates to the technical field of distributed power supply operation control of a power distribution network, and discloses a node voltage distribution control optimization method, a node voltage distribution control optimization system, node voltage distribution control optimization equipment, a node voltage distribution control optimization medium and a node voltage distribution control optimization product of a power distribution area. And taking the voltage distribution of each node in the whole domain as an initial voltage distribution condition of load flow calculation, and performing load flow calculation on the power distribution area under the condition of meeting safety constraints and a load flow equation to obtain optimal active power output and optimal reactive power output under the condition that the deviation between the voltage of each node in the whole domain of the power distribution area and a preset rated voltage is minimized. The power scheduling instruction is generated through the optimal active power output and the optimal reactive power output, and the local controller of each distributed power supply executes the power scheduling instruction, thereby achieving the global optimization of the voltage of the power distribution network through the cooperative adjustment of each distributed power supply, and effectively improving the quality and reliability of electric energy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of distributed power supply operation control of power distribution network, and particularly relates to a node voltage distribution control optimization method, system, equipment, medium and product of a power distribution area. BACKGROUND

[0002] As a key link of the power system, the voltage quality of the low-voltage power distribution area directly affects the reliability of user power supply. With the rapid increase of the penetration rate of photovoltaic and other distributed power supplies, the power flow of the power distribution network is intensified, and the risk of voltage out-of-limit is increasingly prominent.

[0003] To cope with this challenge, the low-voltage power distribution network voltage control mainly adopts three types of methods, namely local control, centralized control and distributed control. In terms of local control, the strategy based on inverter reactive power-voltage regulation does not require communication, but it is difficult to achieve global voltage optimization. Centralized control can achieve theoretical optimization with the help of optimization algorithms, but it relies on complete communication and accurate modeling, and has poor applicability in remote areas. Distributed control improves robustness through collaborative computing, but still requires continuous communication between nodes, which makes it difficult to deploy in areas with insufficient communication coverage. Therefore, the existing voltage control methods are difficult to balance global optimization and reliability in the power distribution area with limited communication conditions. SUMMARY

[0004] Therefore, in order to solve the above technical problems, the present application provides a node voltage distribution control optimization method, system, equipment, medium and product of a power distribution area.

[0005] The first aspect of the present application provides a node voltage distribution control optimization method of a power distribution area, comprising:

[0006] obtaining electrical quantity data of a grid-connected point of the power distribution area, and predicting the voltage distribution of each node in the entire domain of the power distribution area according to the electrical quantity data of the grid-connected point;

[0007] taking the voltage distribution of each node in the entire domain as an initial voltage distribution condition of power flow calculation, performing power flow calculation on the power distribution area under the condition of meeting safety constraints and power flow equations, and obtaining optimal active power output and optimal reactive power output under the condition of minimizing the deviation of the voltage of each node in the entire domain of the power distribution area from the preset rated voltage;

[0008] generating a power scheduling instruction according to the optimal active power output and the optimal reactive power output, and issuing the power scheduling instruction to the local controller of each distributed power supply, so that the local controller of each distributed power supply executes the power scheduling instruction.

[0009] Preferably, the obtaining of the electrical quantity data of the grid-connected point of the power distribution area and the prediction of the voltage distribution of each node in the entire domain of the power distribution area according to the electrical quantity data of the grid-connected point comprise:

[0010] inputting the electrical quantity data of the grid-connected point of the power distribution area into the trained voltage prediction model, so that the trained voltage prediction model outputs voltage estimation values of each node in the power distribution area except the grid-connected point; the trained voltage prediction model is obtained by training a BP neural network based on a training set composed of historical electrical quantity sample data of the grid-connected point and voltage sample data of each node except the grid-connected point;

[0011] determining the voltage distribution of each node in the power distribution area according to the predicted voltage estimation values of each node and the electrical quantity data of the grid-connected point.

[0012] Preferably, the training process of the trained voltage prediction model comprises:

[0013] obtaining historical electrical quantity sample data of the grid-connected point and corresponding voltage sample data of each node except the grid-connected point, and composing a training set;

[0014] inputting the training set into an initial BP neural network, adjusting network weights through a back propagation algorithm, and iteratively optimizing until output error meets a preset convergence condition, so that the trained voltage prediction model is obtained.

[0015] Preferably, the training process of the trained voltage prediction model further comprises:

[0016] performing electromagnetic transient simulation on the operating condition of the power distribution area under operating conditions of multiple different loads and multiple different distributed power sources;

[0017] sampling electrical quantity simulation data of the grid-connected point in the electromagnetic transient simulation as historical electrical quantity sample data of the grid-connected point, and collecting voltage simulation data of each node except the grid-connected point in the electromagnetic transient simulation as voltage sample data.

[0018] Preferably, the voltage distribution of each node in the power distribution area is used as an initial voltage distribution condition for power flow calculation, and power flow calculation is performed on the power distribution area under the condition of meeting safety constraints and power flow equations, so that optimal active power output and optimal reactive power output under the condition of minimizing the deviation of the voltage of each node in the power distribution area from a preset rated voltage are obtained, comprising:

[0019] establishing a nonlinear optimization model with the minimization of the deviation of the voltage of each node from the preset rated voltage as an optimization objective, and constructing constraint conditions of the optimization objective according to safety constraints and power flow equations;

[0020] The voltage distribution of all nodes in the entire domain is used as the initial voltage condition and substituted into the nonlinear optimization model. The active and reactive power output variables of each distributed power source are adjusted so that the optimization objective gradually converges. Under the constraint conditions, the optimal active power output command and optimal reactive power output of each distributed power source are obtained.

[0021] Preferably, the expression of the nonlinear optimization model is:

[0022]

[0023] In the formula, U is the objective function value. n Let U0 be the node voltage amplitude of the nth node in the distribution transformer area, and N be the rated voltage amplitude. bus For the distribution radio station area node set, For the constraints to be satisfied, p j q j Let be the active and reactive power injected into the j-th node, respectively. , Let P be the active and reactive power injected into the branch terminal node k at the j-th node, respectively, and let δ(j) be the set of branch terminal nodes starting from node j. ij Q ij Let i represent the active power and reactive power of the branch with node i as the first node and node j as the last node, respectively, and let π(j) be the set of first and last nodes of the branch with node j as the last node. ij X ij Let i be the branch resistance and reactance values ​​with i as the first terminal node and j as the last terminal node, respectively. ij Let P be the square of the branch current magnitude with node i as the first terminal node and node j as the last terminal node. DG,j Q DG,j P represents the active and reactive power of the distributed generation connected to the distribution network at node j, respectively. L,j Q L,j v represents the active and reactive power of the load connected to the j-th node, respectively. i v is the square of the node voltage magnitude of the i-th node. j The square of the node voltage amplitude at the j-th node Inject the maximum active power output of the i-th node into the DG. Inject the upper limit of reactive power output of the i-th node into the DG. This represents the lower limit of the node voltage amplitude at the i-th node. This represents the upper limit of the node voltage amplitude at the i-th node. This represents the upper limit of the branch current amplitude with i as the first terminal node and j as the last terminal node.

[0024] Secondly, the present invention also provides a node voltage distribution control optimization system for a distribution transformer area, comprising:

[0025] The data acquisition module is used to acquire electrical quantity data of the grid connection point of the distribution transformer area, and predict the voltage distribution of each node in the entire distribution transformer area based on the electrical quantity data of the grid connection point.

[0026] The power optimization module is used to take the voltage distribution of all nodes in the entire domain as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, it performs power flow calculation on the distribution substation area to obtain the optimal active power output and optimal reactive power output that minimizes the deviation of the voltage of all nodes in the entire distribution substation area from the preset rated voltage.

[0027] The power scheduling module is used to generate a power scheduling instruction based on the optimal active power output and the optimal reactive power output, and to send the power scheduling instruction to the local controller of each distributed power source, so that the local controller of each distributed power source executes the power scheduling instruction.

[0028] Thirdly, the present invention also provides an electronic device, the electronic device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the node voltage distribution control optimization method for the distribution radio area as described in the first aspect.

[0029] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the steps of the node voltage distribution control optimization method for the distribution substation as described in the first aspect.

[0030] Fifthly, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein, when the program instructions are executed by a computer, the computer performs the steps of the node voltage distribution control optimization method for the distribution substation as described in the first aspect.

[0031] As can be seen from the above technical solution, this invention predicts the voltage distribution of all nodes in the distribution substation by using electrical quantity data at the grid connection point, and uses the voltage distribution of all nodes in the substation as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, power flow calculation is performed on the distribution substation to obtain the optimal active power output and optimal reactive power output that minimize the deviation of the voltage of all nodes in the distribution substation from the preset rated voltage. Power dispatch instructions are generated by the optimal active power output and optimal reactive power output, so that the local controllers of each distributed power source execute the power dispatch instructions, thereby minimizing the deviation of the voltage of all nodes in the distribution substation from the preset rated voltage, while ensuring system safety and power flow balance. Through the coordinated adjustment of each distributed power source, the global optimization of the distribution network voltage is achieved, effectively improving power quality and reliability. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is an application environment diagram of a node voltage distribution control optimization method for a distribution radio station provided in an embodiment of the present invention;

[0034] Figure 2 A flowchart of a node voltage distribution control optimization method for a distribution radio area provided in an embodiment of the present invention;

[0035] Figure 3 This is a schematic diagram of the distribution substation structure of a distributed power source provided in an embodiment of the present invention;

[0036] Figure 4 A schematic diagram of a typical BP neural network structure provided in an embodiment of the present invention;

[0037] Figure 5 A flowchart illustrating the training process of a BP neural network provided in an embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram of a 9-node power distribution system with communication provided in an embodiment of the present invention;

[0039] Figure 7 This is a comparison diagram of the voltages at various nodes of the system under the method proposed in this embodiment of the invention and existing methods;

[0040] Figure 8 This is a schematic diagram of the structure of a node voltage distribution control optimization system for a distribution radio area provided in an embodiment of the present invention;

[0041] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0042] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] The node voltage distribution control optimization method for distribution radio areas provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be integrated onto server 102 or placed on the cloud or other network servers. Terminal 101 or server 102 acquires electrical quantity data of the grid-connected points of the distribution substation, predicts the voltage distribution of all nodes in the entire distribution substation based on the electrical quantity data of the grid-connected points, uses the voltage distribution of all nodes in the entire substation as the initial voltage distribution condition for power flow calculation, and performs power flow calculation on the distribution substation while satisfying safety constraints and power flow equations, obtaining the optimal active power output and optimal reactive power output that minimize the deviation between the voltage of all nodes in the entire distribution substation and the preset rated voltage; generates power dispatch instructions based on the optimal active power output and optimal reactive power output, and sends the power dispatch instructions to the local controllers of each distributed power source, causing the local controllers of each distributed power source to execute the power dispatch instructions.

[0044] Terminal 101 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets.

[0045] Server 102 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0046] like Figure 2 As shown, this application provides a method for optimizing node voltage distribution control in a distribution substation, which is then applied to... Figure 1 Taking terminal 101 or server 102 as an example, the explanation includes the following steps S1 to S3. Wherein:

[0047] Step S1: Obtain the electrical quantity data of the grid connection point of the distribution substation, and predict the voltage distribution of each node in the entire distribution substation based on the electrical quantity data of the grid connection point.

[0048] Among them, such as Figure 3 As shown, assuming node n is the grid connection point of the distributed power source, u n i n-1,n and i n,n+1 Z represents the instantaneous node voltage, input current, and output current information collected from grid connection point n, respectively. n,n+1 Let DG be the branch line impedance with n as the first terminal node and n+1 as the last terminal node. p For the p-th distributed generation to be connected to the distribution network, S L,n S represents the apparent power of the load connected to the distribution network at the nth node. refp The apparent power command value of the p-th distributed generation is the grid connection point, which is the common connection point of the distribution substation and is used for power exchange between the distributed generation and the main grid. The electrical quantity data of the grid connection point are measured in real time by the local controller of each distributed generation (DG). The electrical quantity data includes voltage amplitude, current amplitude, active power and reactive power.

[0049] By estimating the voltage distribution of other nodes besides the grid connection point using the electrical quantity data of the grid connection point, a trained neural network model can be used to process the electrical quantity data of the grid connection point. Finally, the electrical quantity data of the grid connection point and the voltage distribution of other nodes besides the grid connection point are combined to form the voltage distribution of all nodes in the entire distribution substation area.

[0050] Step S2: Using the voltage distribution of all nodes in the entire distribution area as the initial voltage distribution condition for power flow calculation, and under the condition of satisfying the safety constraints and power flow equations, perform power flow calculation on the distribution area to obtain the optimal active power output and optimal reactive power output that minimize the deviation between the voltage of all nodes in the entire distribution area and the preset rated voltage.

[0051] In this approach, the voltage distribution of all nodes across the entire distribution area is used as the initial voltage distribution condition for power flow calculation. Under the strict constraints of node power balance, safe voltage amplitude range, and line capacity limitations, the interior-point method is employed to solve this nonlinear optimization problem. By adjusting the active and reactive power outputs of each distributed power source, the sum of squares of the deviations between the voltage amplitudes of all nodes in the distribution area after power flow calculation and the rated voltage is minimized, thereby achieving optimized voltage distribution control. Ultimately, the optimal active and reactive power outputs of each distributed power source are obtained.

[0052] Step S3: Generate power dispatch instructions based on the optimal active power output and optimal reactive power output, and send the power dispatch instructions to the local controllers of each distributed power source so that the local controllers of each distributed power source can execute the power dispatch instructions.

[0053] The process involves generating power dispatch commands based on optimal active and reactive power outputs, and then distributing these commands to the corresponding distributed generation (DG) local controllers via a communication network. This ensures that each DG unit can adjust its output power in real time. Upon receiving the command, the local controller performs closed-loop control based on the current operating status and the command target value, dynamically adjusting the active and reactive power outputs of the inverter to achieve rapid suppression of voltage deviations.

[0054] It should be noted that the embodiments of this application predict the voltage distribution of all nodes in the entire distribution substation by using electrical quantity data at the grid connection point, and use the voltage distribution of all nodes in the entire substation as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, power flow calculation is performed on the distribution substation to obtain the optimal active power output and optimal reactive power output that minimize the deviation of the voltage of all nodes in the entire distribution substation from the preset rated voltage. Power dispatch instructions are generated by the optimal active power output and optimal reactive power output, so that the local controllers of each distributed power source execute the power dispatch instructions, thereby minimizing the deviation of the voltage of all nodes in the entire distribution substation from the preset rated voltage, while ensuring system safety and power flow balance. Through the coordinated adjustment of each distributed power source, the global optimization of the distribution network voltage is achieved, effectively improving power quality and reliability.

[0055] In some embodiments, acquiring electrical quantity data of the grid connection point of the distribution substation and predicting the voltage distribution of all nodes in the distribution substation based on the electrical quantity data of the grid connection point includes: inputting the electrical quantity data of the grid connection point of the distribution substation into a trained voltage prediction model, so that the trained voltage prediction model outputs the voltage estimates of all nodes in the distribution substation except the grid connection point; the trained voltage prediction model is obtained by training a BP neural network based on a training set composed of historical electrical quantity sample data of the grid connection point and voltage sample data of all nodes except the grid connection point; and determining the voltage distribution of all nodes in the distribution substation based on the predicted voltage estimates of other nodes and the electrical quantity data of the grid connection point.

[0056] The training process for the well-trained voltage prediction model is as follows:

[0057] Historical electrical quantity sample data of the grid connection point and voltage sample data of other nodes corresponding to the transformer are obtained and formed into a training set. The training set is input into the initial BP neural network, and the network weights are adjusted through the backpropagation algorithm. The optimization is iteratively performed until the output error meets the preset convergence condition, and the trained voltage prediction model is obtained.

[0058] A BP (Back Propagation Neural Network) is a type of multi-layer feedforward neural network, such as... Figure 4As shown, the BP neural network consists of a three-layer structure: the first layer is the input layer, the second layer is the hidden layer, and the third layer is the output layer. The obtained dataset is fed into the neural network for training. Wherein, W... ij W is the set of weight coefficients between the input layer and the hidden layer. jk This is the set of weight coefficients between the input layer and the hidden layer. For a DG local controller with node n incorporated, the input of the neural network is Σ. local_n The output is the voltage information of all nodes in the distribution substation area except for the current node, that is, the node voltage amplitude and phase angle of all nodes in the distribution substation area excluding the current node. The training steps of the BP neural network are as follows: Figure 5 As shown, historical electrical quantity data of the grid connection point is input into the hidden layer through the input layer, processed by the activation function, and then passed to the output layer to output the estimated voltage values ​​of each node. The error between the output value and the actual sample value is calculated. If the convergence condition is not met, the error is propagated back along the network to update the weight coefficient W. ij and W jk The training process is repeated iteratively until the model output accuracy meets the target. After training, the voltage prediction model can receive electrical quantity data from the grid connection point in real time and quickly output the voltage estimation results of each node in the distribution substation area, realizing dynamic prediction of the voltage distribution across the entire area.

[0059] In some embodiments, the training process of the trained voltage prediction model further includes:

[0060] Electromagnetic transient simulations were performed on the operating conditions of the distribution transformer area under multiple different loads and multiple different distributed power sources. The electrical quantity simulation data of the grid connection point in the electromagnetic transient simulation was sampled as the historical electrical quantity sample data of the grid connection point, and the voltage simulation data of each node other than the grid connection point in the electromagnetic transient simulation was collected as the voltage sample data.

[0061] Specifically, load operating conditions are created by changing the load power; distributed power source operating conditions are created by changing the output power of the distributed power source. Under these different load and distributed power source operating conditions, a distribution network impedance model is built in Simulink for simulation. Each node is connected to a constant power load. The created operating conditions are placed into the simulation, i.e., the active and reactive power of the load and the output power of the distributed power source are changed. The simulation results are recorded to obtain the time-series sampling data of voltage amplitude, phase angle, current amplitude of each branch, active power and reactive power of each node. A complete training sample set is constructed, and the sample data is normalized and then input into a BP neural network.

[0062] In some embodiments, the voltage distribution of all nodes in the entire distribution area is used as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, power flow calculation is performed on the distribution area to obtain the optimal active power output and optimal reactive power output that minimizes the deviation of the voltage of all nodes in the entire distribution area from the preset rated voltage. This includes: establishing a nonlinear optimization model with minimizing the deviation of the node voltage from the preset rated voltage as the optimization objective, and constructing the constraint conditions of the optimization objective according to the safety constraints and power flow equations; substituting the voltage distribution of all nodes in the entire distribution area as the initial voltage condition into the nonlinear optimization model, adjusting the active and reactive power output variables of each distributed power source, so that the optimization objective gradually converges, and obtaining the optimal active power output command and optimal reactive power output of each distributed power source under the condition of satisfying the constraints.

[0063] The expression for the nonlinear optimization model is as follows:

[0064]

[0065] In the formula, U is the objective function value. n Let U0 be the node voltage amplitude of the nth node in the distribution transformer area, and N be the rated voltage amplitude. bus For the distribution radio station area node set, For the constraints to be satisfied, p j q j Let be the active and reactive power injected into the j-th node, respectively. , Let P be the active and reactive power injected into the branch terminal node k at the j-th node, respectively, and let δ(j) be the set of branch terminal nodes starting from node j. ij Q ij Let i represent the active power and reactive power of the branch with node i as the first node and node j as the last node, respectively, and let π(j) be the set of first and last nodes of the branch with node j as the last node. ij X ij Let i be the branch resistance and reactance values ​​with i as the first terminal node and j as the last terminal node, respectively. ij Let P be the square of the branch current magnitude with node i as the first terminal node and node j as the last terminal node. DG,j Q DG,j P represents the active and reactive power of the distributed generation connected to the distribution network at node j, respectively. L,j Q L,j v represents the active and reactive power of the load connected to the j-th node, respectively. i v is the square of the node voltage magnitude of the i-th node. j The square of the node voltage amplitude at the j-th node Inject the maximum active power output of the i-th node into the DG. Inject the upper limit of reactive power output of the i-th node into the DG. This represents the lower limit of the node voltage amplitude at the i-th node. This represents the upper limit of the node voltage amplitude at the i-th node. This represents the upper limit of the branch current amplitude with i as the first terminal node and j as the last terminal node.

[0066] Understandably, under the premise of meeting the system's safe operation constraints, this model achieves precise coordinated control of the active and reactive power output of distributed power sources by solving a nonlinear optimization problem that minimizes the voltage deviation of all nodes, effectively suppressing voltage over-limit phenomena and improving the voltage quality and operational stability of the distribution area.

[0067] The node voltage distribution control optimization method for distribution radio areas proposed in this application can avoid the need for communication between nodes and achieve communication-free global voltage control. The following is a calculation example based on the node voltage distribution control optimization method for distribution radio areas proposed in this application.

[0068] To test this invention, a simulation model was built in MATLAB / Simulink, such as... Figure 6 Taking the 9-node power distribution system shown as an example, this paper calculates and analyzes the coordinated control of system voltage by multiple distributed generation (DG) units, where Z... ij Let S be the branch current with node i as the starting point and node j as the ending point. DG1 and DG2 are two grid-connected distributed power sources. Ln Let represent the apparent power of the load connected to the nth node. In this example, the voltage level is 0.4kV, and the 3rd and 7th nodes are each connected to a power generation generator (DG). The DGs communicate with each other via power line carrier, and their capacity is set to 30kW. System parameters are shown in Tables 1 and 2.

[0069] Table 1. Topology parameter settings for the 9 nodes

[0070]

[0071] Table 2

[0072] Simulation algorithm parameter settings

[0073]

[0074] To demonstrate the effectiveness and superiority of this invention, the following comparative scenarios need to be set up under this operating condition:

[0075] 1) The proposed distributed control based on neural network estimation collaboration;

[0076] 2) Traditional distributed control;

[0077] 3) Centralized control method.

[0078] Simulation results are as followsFigure 7 As shown, the root mean square error (RMSE) of the voltage at each node in the traditional distributed control system is 0.0068 pu, while the RMSE of the neural network-estimated collaborative control system is 0.0052 pu, a reduction of 23.53%. Furthermore, the node voltage distribution control optimization method for distribution substations proposed in this application achieves similar control effects on the system voltage as the centralized control method. This verifies that the neural network estimation mechanism, by capturing the implicit coupling relationships between nodes, can guide the coordinated adjustment of DG output under limited communication conditions, effectively improving voltage balance.

[0079] Based on the same inventive concept, this application also provides a node voltage distribution control optimization system for a distribution substation to implement the node voltage distribution control optimization method for the distribution substation mentioned above.

[0080] The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of the node voltage distribution control optimization system embodiment of one or more distribution substations provided below can be found in the limitations of the node voltage distribution control optimization method of distribution substations above, and will not be repeated here.

[0081] like Figure 8 As shown in the figure, this application provides a node voltage distribution control optimization system for a distribution transformer area, including:

[0082] The data acquisition module 100 is used to acquire electrical quantity data of the grid connection point of the distribution transformer area and predict the voltage distribution of each node in the entire distribution transformer area based on the electrical quantity data of the grid connection point.

[0083] The power optimization module 200 is used to take the voltage distribution of all nodes in the entire distribution area as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, it performs power flow calculation on the distribution area to obtain the optimal active power output and optimal reactive power output that minimizes the deviation of the voltage of all nodes in the entire distribution area from the preset rated voltage.

[0084] The power scheduling module 300 is used to generate power scheduling instructions based on the optimal active power output and the optimal reactive power output, and to send the power scheduling instructions to the local controllers of each distributed power source so that the local controllers of each distributed power source can execute the power scheduling instructions.

[0085] In some embodiments, the data acquisition module 100 is configured to:

[0086] The electrical quantity data of the grid connection point of the distribution substation is input into the trained voltage prediction model, so that the trained voltage prediction model outputs the voltage estimate of each node in the distribution substation except the grid connection point. The trained voltage prediction model is obtained by training the BP neural network with a training set composed of historical electrical quantity sample data of the grid connection point and voltage sample data of each node except the grid connection point.

[0087] Based on the predicted voltage estimates of other nodes and the electrical quantity data of the grid connection point, the voltage distribution of all nodes in the entire distribution substation area is determined.

[0088] In some embodiments, the training process of the trained voltage prediction model is as follows:

[0089] Obtain historical electrical quantity sample data of the grid connection point and voltage sample data of other nodes corresponding to the device, and form a training set;

[0090] The training set is input into the initial BP neural network, and the network weights are adjusted through the backpropagation algorithm. The optimization is iterated until the output error meets the preset convergence condition, and the trained voltage prediction model is obtained.

[0091] In some embodiments, the training process of the trained voltage prediction model further includes:

[0092] Electromagnetic transient simulations were performed on the operating conditions of the distribution transformer area under multiple different loads and multiple different distributed power sources.

[0093] The electrical quantity simulation data of the grid connection point in the electromagnetic transient simulation is sampled as the historical electrical quantity sample data of the grid connection point, and the voltage simulation data of each node other than the grid connection point in the electromagnetic transient simulation is collected as the voltage sample data.

[0094] In some embodiments, the power optimization module 200 is used for:

[0095] A nonlinear optimization model is constructed with the goal of minimizing the deviation between the node voltage and the preset rated voltage, and the constraints of the optimization goal are constructed based on safety constraints and power flow equations.

[0096] The voltage distribution of each node in the entire domain is used as the initial voltage condition and substituted into the nonlinear optimization model. The active and reactive power output variables of each distributed power source are adjusted so that the optimization objective gradually converges. Under the constraint conditions, the optimal active power output command and optimal reactive power output of each distributed power source are obtained.

[0097] In some embodiments, the expression for the nonlinear optimization model is:

[0098]

[0099] In the formula, U is the objective function value. n Let U0 be the node voltage amplitude of the nth node in the distribution transformer area, and N be the rated voltage amplitude. bus For the distribution radio station area node set, For the constraints to be satisfied, p j q j Let be the active and reactive power injected into the j-th node, respectively. , Let P be the active and reactive power injected into the branch terminal node k at the j-th node, respectively, and let δ(j) be the set of branch terminal nodes starting from node j. ij Q ij Let i represent the active power and reactive power of the branch with node i as the first node and node j as the last node, respectively, and let π(j) be the set of first and last nodes of the branch with node j as the last node. ij X ij Let i be the branch resistance and reactance values ​​with i as the first terminal node and j as the last terminal node, respectively. ij Let P be the square of the branch current magnitude with node i as the first terminal node and node j as the last terminal node. DG,j Q DG,j P represents the active and reactive power of the distributed generation connected to the distribution network at node j, respectively. L,j Q L,j v represents the active and reactive power of the load connected to the j-th node, respectively. i v is the square of the node voltage magnitude of the i-th node. j The square of the node voltage amplitude at the j-th node Inject the maximum active power output of the i-th node into the DG. Inject the upper limit of reactive power output of the i-th node into the DG. This represents the lower limit of the node voltage amplitude at the i-th node. This represents the upper limit of the node voltage amplitude at the i-th node. This represents the upper limit of the branch current amplitude with i as the first terminal node and j as the last terminal node.

[0100] like Figure 9 As shown, this application provides an electronic device. The electronic device 10 includes a memory 20 and a processor 30. The memory 20 stores a computer program. When the computer program is executed by the processor 30, the processor 30 performs the steps of the node voltage distribution control optimization method for the distribution radio area as described in the above embodiment.

[0101] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed, implements the steps of the node voltage distribution control optimization method for the distribution radio area as described in the above embodiments.

[0102] This application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the node voltage distribution control optimization method for the distribution substation as described in the above embodiments.

[0103] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, electronic devices, computer storage media, and computer program products described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0104] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] In the several embodiments provided by this invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0109] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of the present invention through a computer device (which may be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0110] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing node voltage distribution control in a distribution transformer area, characterized in that, include: Obtain electrical quantity data of grid connection points in the distribution substation, and predict the voltage distribution of all nodes in the entire distribution substation based on the electrical quantity data of the grid connection points; Using the voltage distribution of all nodes in the entire region as the initial voltage distribution condition for power flow calculation, and under the condition of satisfying safety constraints and power flow equations, power flow calculation is performed on the distribution substation area to obtain the optimal active power output and optimal reactive power output that minimize the deviation of the voltage of all nodes in the entire distribution substation area from the preset rated voltage. Power scheduling instructions are generated based on the optimal active power output and the optimal reactive power output, and the power scheduling instructions are sent to the local controllers of each distributed power source so that the local controllers of each distributed power source execute the power scheduling instructions.

2. The node voltage distribution control optimization method for a distribution transformer area according to claim 1, characterized in that, The step of acquiring electrical quantity data at the grid connection point of the distribution substation and predicting the voltage distribution of all nodes in the entire distribution substation based on the electrical quantity data at the grid connection point includes: The electrical quantity data of the grid connection point of the distribution substation is input into the trained voltage prediction model, so that the trained voltage prediction model outputs the voltage estimate of each node in the distribution substation except for the grid connection point; the trained voltage prediction model is obtained by training a BP neural network based on a training set composed of historical electrical quantity sample data of the grid connection point and voltage sample data of each node except for the grid connection point. Based on the predicted voltage estimates of other nodes and the electrical quantity data of the grid connection point, the voltage distribution of all nodes in the distribution substation is determined.

3. The node voltage distribution control optimization method for a distribution transformer area according to claim 2, characterized in that, The training process of the trained voltage prediction model is as follows: Obtain historical electrical quantity sample data of the grid connection point and voltage sample data of other nodes corresponding to the device, and form a training set; The training set is input into the initial BP neural network, and the network weights are adjusted through the backpropagation algorithm. The optimization is iteratively performed until the output error meets the preset convergence condition, thus obtaining the trained voltage prediction model.

4. The node voltage distribution control optimization method for a distribution transformer area according to claim 3, characterized in that, The training process of the trained voltage prediction model also includes: Electromagnetic transient simulations were performed on the operating conditions of the distribution transformer area under multiple different loads and multiple different distributed power sources. The electrical quantity simulation data of the grid connection point in the electromagnetic transient simulation is sampled as the historical electrical quantity sample data of the grid connection point, and the voltage simulation data of each node other than the grid connection point in the electromagnetic transient simulation is collected as the voltage sample data.

5. The node voltage distribution control optimization method for a distribution transformer area according to claim 1, characterized in that, The process involves using the voltage distribution of all nodes in the entire distribution area as the initial voltage distribution condition for power flow calculation. Under the conditions of satisfying safety constraints and power flow equations, power flow calculation is performed on the distribution area to obtain the optimal active power output and optimal reactive power output that minimize the deviation of the voltage of all nodes in the entire distribution area from the preset rated voltage. This includes: A nonlinear optimization model is constructed with the goal of minimizing the deviation between the node voltage and the preset rated voltage, and the constraints of the optimization goal are constructed based on safety constraints and power flow equations. The voltage distribution of all nodes in the entire domain is used as the initial voltage condition and substituted into the nonlinear optimization model. The active and reactive power output variables of each distributed power source are adjusted so that the optimization objective gradually converges. Under the constraint conditions, the optimal active power output command and optimal reactive power output of each distributed power source are obtained.

6. The node voltage distribution control optimization method for a distribution transformer area according to claim 5, characterized in that, The expression for the nonlinear optimization model is: In the formula, U is the objective function value. n Let U0 be the node voltage amplitude of the nth node in the distribution transformer area, and N be the rated voltage amplitude. bus For the distribution radio station area node set, For the constraints to be satisfied, p j q j Let be the active and reactive power injected into the j-th node, respectively. , Let P be the active and reactive power injected into the branch terminal node k at the j-th node, respectively, and let δ(j) be the set of branch terminal nodes starting from node j. ij Q ij Let i represent the active power and reactive power of the branch with node i as the first node and node j as the last node, respectively, and let π(j) be the set of first and last nodes of the branch with node j as the last node. ij X ij Let i be the branch resistance and reactance values ​​with i as the first terminal node and j as the last terminal node, respectively. ij Let P be the square of the branch current magnitude with node i as the first terminal node and node j as the last terminal node. DG,j Q DG,j P represents the active and reactive power of the distributed generation connected to the distribution network at node j, respectively. L,j Q L,j v represents the active and reactive power of the load connected to the j-th node, respectively. i v is the square of the node voltage magnitude of the i-th node. j The square of the node voltage amplitude at the j-th node Inject the maximum active power output of the i-th node into the DG. Inject the upper limit of reactive power output of the i-th node into the DG. This represents the lower limit of the node voltage amplitude at the i-th node. This represents the upper limit of the node voltage amplitude at the i-th node. This represents the upper limit of the branch current amplitude with i as the first terminal node and j as the last terminal node.

7. A node voltage distribution control and optimization system for a distribution transformer area, characterized in that, include: The data acquisition module is used to acquire electrical quantity data of the grid connection point of the distribution transformer area, and predict the voltage distribution of each node in the entire distribution transformer area based on the electrical quantity data of the grid connection point. The power optimization module is used to take the voltage distribution of all nodes in the entire domain as the initial voltage distribution condition for power flow calculation. Under the condition of satisfying safety constraints and power flow equations, it performs power flow calculation on the distribution substation area to obtain the optimal active power output and optimal reactive power output that minimizes the deviation of the voltage of all nodes in the entire distribution substation area from the preset rated voltage. The power scheduling module is used to generate a power scheduling instruction based on the optimal active power output and the optimal reactive power output, and to send the power scheduling instruction to the local controller of each distributed power source, so that the local controller of each distributed power source executes the power scheduling instruction.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor performs the steps of the node voltage distribution control optimization method for a distribution radio area as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the node voltage distribution control optimization method for a distribution radio area as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the steps of the node voltage distribution control optimization method for a distribution substation as described in any one of claims 1-6.

Images