Multi-element load grid-connected parameter setting method, device and equipment

Abstract

The application provides a multi-element load grid-connected parameter setting method, device and equipment, and relates to the technical field of power distribution network operation control. The method comprises the following steps: obtaining current power data and current load data determined based on photovoltaic output power in a target power distribution network; wherein the current load data comprises load data of electric vehicles and load data of flexible load; constructing a multi-element load grid-connected parameter model according to the current power data and the current load data to obtain a current setting parameter expected value; calculating an index value between the current setting parameter expected value and a current setting parameter actual value; if the index value is not less than a critical threshold value, setting the grid-connected parameter of the target power distribution network based on power data, load data and the current setting parameter expected value at the next moment. The application does not need frequent manual intervention, can dynamically and adaptively adjust the grid-connected parameter according to the power distribution network working condition, adapts to the complex scene of coexistence of multi-element load and new energy, and guarantees long-term stable and efficient operation of the system.

Description

Technical Field

[0001] This invention relates to the field of power distribution network operation and control technology, and in particular to a method, apparatus and equipment for setting parameters for multi-load grid connection. Background Technology

[0002] Against the backdrop of achieving global energy transition and low-carbon goals, the development and utilization of renewable energy has become a core development direction in the energy sector. Distributed photovoltaic (PV) power, as a significant form of renewable energy, has seen its installed capacity in distribution networks continuously expand due to its clean and renewable characteristics. Simultaneously, energy storage technology is constantly developing, and distributed energy storage devices can effectively address the intermittency and volatility issues of PV power generation, enabling the spatial and temporal transfer of electricity and improving energy utilization efficiency. The rapid popularization of electric vehicles has made them important adjustable loads in distribution networks, and their charging and discharging behavior has a profound impact on the power balance and stable operation of the grid. Furthermore, flexible loads such as smart air conditioners, with their adjustable and interruptible characteristics, can flexibly adjust power consumption according to grid demand, providing new means for optimizing grid operation. The emergence of PV-storage-charging-utilization systems integrates multiple functions such as PV power generation, energy storage, electric vehicle charging and discharging, and flexible load regulation, becoming a key link in building new power systems and achieving efficient energy utilization.

[0003] Photovoltaic power generation is intermittent and volatile. Large-scale integration can lead to voltage fluctuations and frequency deviations in the distribution network. Specifically, the charging and discharging behavior of distributed energy storage can affect the power balance of the grid; random charging of electric vehicles may exacerbate the peak-valley load difference; and the regulation capacity of flexible loads such as air conditioning has not been fully utilized. These factors severely impact the economic efficiency and stability of the distribution network. Currently, optimization research on the grid integration of photovoltaic, energy storage, charging, and photovoltaic loads mainly focuses on control strategies for single devices or local optimization. Traditional voltage and frequency tuning methods for distribution networks are difficult to adapt to the dynamic changes under high-proportion renewable energy integration, resulting in low grid operating efficiency and potentially even safety issues. Summary of the Invention

[0004] This invention provides a method, apparatus, and equipment for setting parameters for multi-load grid connection, in order to solve the problem that traditional voltage and frequency setting methods for distribution networks are difficult to adapt to dynamic changes under the access of high proportions of renewable energy, resulting in low grid operating efficiency.

[0005] In a first aspect, embodiments of the present invention provide a method for setting multi-load grid connection parameters, including: Acquire current power data and current load data in the target distribution network based on photovoltaic output power; wherein, the current load data includes load data of electric vehicles and load data of flexible loads; Based on the current power data and current load data, a multi-dimensional load grid connection parameter model is constructed to obtain the expected values ​​of the current setting parameters; Calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are adjusted based on the power data, load data and the expected value of the current setting parameters at the next time step.

[0006] In one possible implementation, a multi-variable load grid connection parameter model is constructed based on current power data and current load data to obtain the expected values ​​of the current setting parameters, including: Based on the current power data and current load data, construct a multi-dimensional load grid connection parameter model; A radial basis function neural network is used to solve the multi-element load grid connection parameter model; Based on the solution results, the expected values ​​of the current tuning parameters are obtained.

[0007] In one possible implementation, if the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are adjusted based on the power data, load data, and expected values ​​of the current setting parameters at the next time step, including: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are tuned based on the expected value of the current tuning parameters, and the hidden layer activation function of the radial basis function neural network is updated based on the power data and load data at the next moment after tuning; wherein, the center position of the hidden layer activation function and the update of the basis function width, as well as the weight of the grid connection parameters, are determined based on the expected value of the current tuning parameters. Based on the updated radial basis function neural network, the multi-variable load grid connection parameter model is solved until the obtained index value is less than the critical threshold.

[0008] In one possible implementation, a multi-dimensional load grid connection parameter model is constructed based on current power data and current load data, including: With the goal of balancing load power supply and demand, a multi-dimensional load grid connection parameter model is constructed based on current power data and current load data; The multi-load grid connection parameter model is as follows:

[0009] In the formula, This represents a multi-load grid connection parameter model. , and These represent the grid connection parameters for photovoltaic-integrated energy storage nodes, photovoltaic-integrated electric vehicle nodes, and photovoltaic-integrated flexible load nodes, respectively. , and Let represent the power functions of a photovoltaic-integrated energy storage node, a photovoltaic-integrated electric vehicle node, and a photovoltaic-integrated flexible load node, respectively. , and These represent the sets of energy storage nodes containing photovoltaics, the sets of electric vehicle nodes containing photovoltaics, and the sets of flexible load nodes containing photovoltaics, respectively.

[0010] In one possible implementation, current power data and current load data, determined based on photovoltaic output power, are obtained in the target distribution network, including: Construct a photovoltaic-storage-charging-utilization system model that satisfies the first preset constraint condition; wherein, the photovoltaic-storage-charging-utilization system model includes a photovoltaic-integrated energy storage node power model, a photovoltaic-integrated electric vehicle node power model, and a photovoltaic-integrated flexible load node power model; Based on the power model of the energy storage node containing photovoltaics, obtain the current power data of the target distribution network determined based on the photovoltaic output power; Based on the power model of electric vehicle nodes with photovoltaics and the power model of flexible load nodes with photovoltaics, the current load data of the target distribution network determined by photovoltaic output power is obtained.

[0011] In one possible implementation, the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter is calculated, including: Based on the index function formula, calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; The index function formula is used to characterize the square of the difference between the expected value of the current tuning parameter and the actual value of the current tuning parameter.

[0012] In one possible implementation, if the index value is not less than a critical threshold, the method further includes: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network will not be tuned, and the expected value of the current tuning parameters will be output as the optimal tuning parameters.

[0013] In one possible implementation, after setting the grid connection parameters of the target distribution network without tuning if the index value is not less than the critical threshold, and outputting the expected value of the tuning parameters as the optimal tuning parameters, the following is also included: The optimal tuning parameter, the index value corresponding to the optimal tuning parameter, and the error level determined based on the index value corresponding to the optimal tuning parameter are used as a set of historical tuning data. Determine whether the error level of each set of historical setting data meets the preset standard; otherwise, set the grid connection parameters of the target distribution network based on the current power data and the current load data. And / or, when the cumulative value of the indicator within a preset time period is greater than the preset cumulative threshold, an error compensation factor is determined based on the historical tuning data within the preset time period, and the critical threshold is adjusted based on the error compensation factor.

[0014] Secondly, embodiments of the present invention provide a multi-load grid connection parameter setting device, comprising: The acquisition module is used to acquire current power data and current load data in the target distribution network, which are determined based on photovoltaic output power; wherein, the current load data includes load data of electric vehicles and load data of flexible loads; The module is used to construct a multi-dimensional load grid connection parameter model based on the current power data and the current load data, so as to obtain the expected values ​​of the current setting parameters; The calculation module is used to calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; The tuning module is used to tune the grid connection parameters of the target distribution network based on the power data, load data, and expected values ​​of the current tuning parameters at the next moment if the index value is not less than the critical threshold.

[0015] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0016] In this embodiment of the invention, the power and load data used in traditional methods for setting parameters are not determined by considering the photovoltaic output power. This can easily lead to low control accuracy and poor photovoltaic absorption rate due to the disconnect between parameters and dynamic photovoltaic output, and it cannot adapt to high-proportion photovoltaic grid connection scenarios, resulting in equipment risks and economic losses. To solve this problem, and considering that the optimization research for multi-load grid connection of photovoltaic, energy storage, charging and utilization in traditional methods mainly focuses on the control strategy of a single device or local optimization, this embodiment of the invention uses the current photovoltaic power data and the current load data including electric vehicles and flexible loads as the basis for setting. This can dynamically match the photovoltaic output with the actual load demand, and at the same time, combine multiple types of loads to meet the needs of scenarios where high-proportion new energy and multi-load coexist, improving control accuracy and avoiding supply and demand imbalance. Furthermore, by modeling based on the current power and multi-load data, the expected value of the setting parameters can accurately match the current operating state of the distribution network, avoiding adaptation deviations caused by relying on fixed parameters or historical data, and improving the timeliness and rationality of the parameters. By calculating the index values ​​of expected and actual values, parameter deviations can be monitored in real time. If the deviation exceeds a critical threshold, adjustments can be made promptly based on data from the next moment. This allows for rapid responses to fluctuations in photovoltaic output and load changes, reducing the risk of voltage or frequency fluctuations and equipment failures caused by parameter mismatches. In this way, frequent manual intervention is unnecessary, enabling grid-connected parameters to dynamically and adaptively adjust according to the operating conditions of the distribution network. This adapts to complex scenarios where diverse loads and new energy sources coexist, ensuring the long-term stable and efficient operation of the system. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the implementation of the multi-load grid connection parameter setting method provided in this embodiment of the invention. Figure 2 This is a power distribution network node topology diagram provided in an embodiment of the present invention; Figure 3 This is a comparison chart of the per-unit voltage values ​​of distribution network nodes before and after photovoltaic grid connection, provided in an embodiment of the present invention. Figure 4 This is a comparison diagram of reactive power in the distribution network when only photovoltaic access is considered and when both photovoltaic charging and usage are considered, provided by an embodiment of the present invention. Figure 5 This is a schematic diagram comparing the expected value and the actual value provided in an embodiment of the present invention; Figure 6 This is a graph showing the tuning process of multi-load grid connection parameters in a simulation example provided in this embodiment of the invention. Figure 7 This is a schematic diagram of the structure of the multi-load grid connection parameter setting device provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart illustrating the implementation of the multi-load grid connection parameter setting method provided in this embodiment of the invention, as follows: Figure 1 As shown, the method includes: Step 110: Obtain the current power data and current load data in the target distribution network based on the photovoltaic output power; wherein, the current load data includes the load data of electric vehicles and the load data of flexible loads.

[0020] Traditional methods collect current power and load data from the target distribution network that are not determined by considering photovoltaic output power and are not related to photovoltaics themselves. This embodiment, however, obtains the corresponding data by constructing a photovoltaic-storage-charging-utilization system model with first preset constraints; wherein the photovoltaic-storage-charging-utilization system model includes a photovoltaic-integrated energy storage node power model, a photovoltaic-integrated electric vehicle node power model, and a photovoltaic-integrated flexible load node power model.

[0021] Accordingly, the current power data is determined based on the power model of the energy storage node containing photovoltaics; the current load data is determined based on the power model of the electric vehicle node containing photovoltaics and the power model of the flexible load node containing photovoltaics, respectively.

[0022] Step 120: Based on the current power data and current load data, construct a multi-element load grid connection parameter model to obtain the expected values ​​of the current setting parameters.

[0023] In order to achieve accurate calculation of the setting parameters, this embodiment comprehensively considers the correlation between the current power data and the multi-load, as well as the influence relationship with photovoltaics, and constructs a multi-load grid connection parameter model that meets the second preset constraint condition with the goal of balancing the power supply and demand of the load.

[0024] The multi-load grid connection parameter model is as follows:

[0025] In the formula, This represents a multi-load grid connection parameter model. , and These represent the grid connection parameters for photovoltaic-integrated energy storage nodes, photovoltaic-integrated electric vehicle nodes, and photovoltaic-integrated flexible load nodes, respectively. , and Let represent the power functions of a photovoltaic-integrated energy storage node, a photovoltaic-integrated electric vehicle node, and a photovoltaic-integrated flexible load node, respectively. , and These represent the sets of energy storage nodes containing photovoltaics, the sets of electric vehicle nodes containing photovoltaics, and the sets of flexible load nodes containing photovoltaics, respectively.

[0026] Accordingly, the second preset constraint can be:

[0027] In the formula, Indicates the number of photovoltaic nodes. and These represent the number of discharge energy storage nodes and the number of charge energy storage nodes, respectively. and These represent the number of electric vehicles discharging and the number of electric vehicles charging, respectively. For the first n The node at the th t Photovoltaic active power at any given time; For the first m Active power of a photovoltaic-integrated energy storage node; For the first m The active power of a photovoltaic-equipped electric vehicle; For the first m Active power of a photovoltaic-integrated energy storage node during charging; For the first m The active power of a photovoltaic-equipped electric vehicle; For the first m Active power of a flexible load node containing photovoltaics; for n The node at the th t Photovoltaic reactive power at any given time; for t Time of the first j Reactive power of a photovoltaic-integrated energy storage node; for t Time of the first k Reactive power of an electric vehicle node containing photovoltaics; for t Time of the first m Reactive power of flexible load nodes containing photovoltaics; The active power of photovoltaics under maximum power point tracking control; Indicates network reactive power loss. express t Time of the first j The upper limit of reactive power of a photovoltaic-integrated energy storage node. express t Time of the first k The upper limit of reactive power of a photovoltaic-equipped electric vehicle node. express t Time of the first mThe upper limit of reactive power of a flexible load node containing photovoltaics.

[0028] Optionally, the current desired setting parameter values ​​include at least one of the desired voltage setting value and the desired frequency setting value.

[0029] Step 130: Calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter.

[0030] In this embodiment, the expected value of the current tuning parameter and the actual value of the current tuning parameter are input into a predetermined index function formula to calculate the corresponding index value.

[0031] The index function formula is used to characterize the square of the difference between the expected value and the actual value of the current tuning parameter. Accordingly, the index function formula is:

[0032] In the formula, express t The expected value of the current tuning parameters at time t. express t The actual value of the current tuning parameter at any given time.

[0033] Step 140: If the index value is not less than the critical threshold, then the grid connection parameters of the target distribution network are adjusted based on the power data, load data and the expected value of the current setting parameters at the next time moment.

[0034] In this embodiment, when the index value is not less than the critical threshold, the actual setting parameters required for the target distribution network to be connected to the grid are too far apart from the current actual setting parameters. At this time, the grid connection setting parameters are seriously mismatched with the actual operating conditions, which will directly lead to a series of problems such as equipment safety risks, grid instability, and power quality deterioration.

[0035] To solve this problem, when the index value is not less than the critical threshold, the grid connection setting parameters are adjusted based on the obtained expected value of the current setting parameters. Then, based on the power data and load data at the next moment after the setting, the expected value of the setting parameters at the next moment is obtained. The above judgment process is repeated until the obtained index value is less than the critical threshold and the setting is stopped.

[0036] Therefore, this embodiment uses current photovoltaic power data and current load data including electric vehicles and flexible loads as the basis for setting. This allows for dynamic matching of photovoltaic output with actual load demand. Furthermore, by combining multiple load types, it can meet the needs of scenarios with a high proportion of renewable energy and diverse loads, improving control accuracy and preventing supply-demand imbalances. Moreover, by modeling based on current power and diverse load data, the resulting expected values ​​of the setting parameters accurately match the current operating state of the distribution network, avoiding adaptation deviations caused by relying on fixed parameters or historical data, and improving the timeliness and rationality of the parameters. By calculating the index values ​​of expected and actual values, parameter deviations can be monitored in real time. If the deviation exceeds a critical threshold, adjustments can be made promptly based on the data from the next moment, quickly responding to photovoltaic output fluctuations and load changes, reducing the risk of voltage or frequency fluctuations and equipment failures caused by parameter mismatches. In this way, frequent manual intervention is unnecessary, allowing grid-connected parameters to dynamically and adaptively adjust according to the distribution network conditions, adapting to complex scenarios with diverse loads and renewable energy, and ensuring long-term stable and efficient system operation.

[0037] In an optional embodiment, the power model of the photovoltaic-integrated energy storage node in step 110 includes a model under charging state and a model under discharging state. When the energy storage device is in discharging state, the power model of the photovoltaic-integrated energy storage node is:

[0038] In the formula, and These represent energy storage nodes containing photovoltaics. j Active power and reactive power, This represents the photovoltaic active power under maximum power point tracking control. express t Apparent power of photovoltaic inverter at all times.

[0039] When the energy storage device is in a charging state, the power model of the energy storage node containing photovoltaics is as follows:

[0040] In the formula, and These represent energy storage nodes containing photovoltaics. j Active power and reactive power, This represents the active power of photovoltaic power under maximum power point tracking control.

[0041] The node power model for electric vehicles with photovoltaics is as follows:

[0042] In the formula, and They represent t Time of the first kThe active and reactive power of each electric vehicle node.

[0043] The power model for flexible load nodes containing photovoltaics is as follows;

[0044] In the formula, and They represent t Time of the first m Active and reactive power of each flexible load node.

[0045] The first constraint, which is also the photovoltaic output constraint related to photovoltaics, corresponds to the power of the photovoltaic inverter:

[0046] In the formula, express t Apparent power of photovoltaic inverter at all times express t Reactive power of photovoltaic inverter at all times and These represent the lower and upper limits of the apparent power of a photovoltaic inverter, respectively. and These represent the lower and upper limits of the active power of the photovoltaic inverter, respectively.

[0047] Distributed energy storage devices are subject to charging and discharging constraints during charging and discharging, and their charging and discharging model is as follows:

[0048] In the formula, express t Time of the first j The state of charge of each energy storage node Indicates the energy storage loss coefficient. and These represent the energy storage charging efficiency and the discharging efficiency, respectively. and They represent t Time of the first j Discharge power and charging power of each energy storage node and They represent t Time of the first j The upper and lower limits of the state of charge of each energy storage node. and These represent the lower and upper limits of energy storage charging efficiency, respectively. and These represent the lower and upper limits of energy storage discharge efficiency, respectively.

[0049] The load data of electric vehicles is subject to charging and discharging constraints; correspondingly, the charging and discharging model of electric vehicles is as follows:

[0050] In the formula, express t Time of the first k Total load of electric vehicle nodes and They represent t The number of electric vehicles charging and discharging at any given time. and They represent t Time of the first k Charging and discharging power of each electric vehicle node; and They represent t Time of the first k The lower and upper limits of charging power for each electric vehicle node. and They represent t Time of the first k The lower and upper limits of discharge power for each electric vehicle node.

[0051] Flexible loads are affected by various types of equipment. In this embodiment, air conditioners are selected as a representative. Accordingly, the constraint model for flexible loads represented by air conditioners is as follows:

[0052] In the formula, express t Time of the first m Total load of each flexible load node Indicates the total number of flexible load nodes. Indicates the energy efficiency ratio. This represents the efficiency coefficient. Indicates cooling capacity. express t Constant indoor temperature express t Set the temperature at all times. This indicates standby power.

[0053] Based on the above model and related constraints, the corresponding power data or load data are obtained.

[0054] In an optional embodiment, the expected value of the current tuning parameter in step 120 is obtained in the following way: A radial basis function neural network is used to solve the multi-element load grid connection parameter model.

[0055] Based on the solution results, the expected values ​​of the current tuning parameters are obtained.

[0056] The hidden layer activation functions of a radial basis function neural network are:

[0057] In the formula, Represents Euclidean distance. This indicates the j-th center position of the hidden layer. This represents the width of the j-th basis function in the hidden layer. This indicates the number of neuron nodes.

[0058] The output obtained by solving the multi-element load grid connection parameter model using a radial basis function neural network is as follows:

[0059] In the formula, and They represent t The values ​​of the multi-load grid connection parameter model and the hidden layer activation function values ​​of the radial basis function neural network at different times.

[0060] This output, or solution result, is used as the expected value of the current tuning parameters.

[0061] In an optional embodiment, if the index value is not less than a critical threshold in step 140, the grid connection parameters of the target distribution network are adjusted based on the power data, load data, and the expected value of the current setting parameters at the next time moment, including: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are tuned based on the expected value of the current tuning parameters, and the hidden layer activation function of the radial basis function neural network is updated based on the power data and load data at the next moment after tuning; wherein, the center position of the hidden layer activation function and the update of the basis function width, as well as the weight of the grid connection parameters, are determined based on the expected value of the current tuning parameters.

[0062] Based on the updated radial basis function neural network, the multi-variable load grid connection parameter model is solved until the obtained index value is less than the critical threshold.

[0063] If the index value is not less than the critical threshold, the power and load data at the next moment after tuning are used as the basis to obtain the expected value of the tuning parameters at the next moment. In the process of obtaining the expected value of the tuning parameters at the next moment, it is necessary to update the parameters in the radial basis function neural network based on the current expected value of the tuning parameters to obtain a new solution. This process is essentially an iterative process, and correspondingly, this process can be represented as:

[0064] In the formula, , and These represent the grid connection parameters of the photovoltaic-integrated energy storage node, photovoltaic-integrated electric vehicle node, and photovoltaic-integrated flexible load node at time t+1, respectively. , and These represent the grid connection parameter weights for photovoltaic-integrated energy storage nodes, photovoltaic-integrated electric vehicle nodes, and photovoltaic-integrated flexible load nodes, respectively. , and Let represent the hidden layer activation functions of the grid connection parameters of the photovoltaic-containing energy storage node, photovoltaic-containing electric vehicle node, and photovoltaic-containing flexible load node at time t, respectively.

[0065] In each iteration, the activation function of the hidden layer needs to be adjusted and updated. During the update, its center position and the width of the basis function are updated. The corresponding formula is expressed as:

[0066]

[0067] in,

[0068]

[0069] In the formula, , and Let represent the j-th center position of the hidden layer at time t+1 for the photovoltaic-containing energy storage node, photovoltaic-containing electric vehicle node, and photovoltaic-containing flexible load node, respectively. , , , , and This represents the momentum factor, with a value range of [0, 1]. , and Let represent the widths of the j-th basis functions in the hidden layer for the photovoltaic-containing energy storage node, photovoltaic-containing electric vehicle node, and photovoltaic-containing flexible load node at time t+1, respectively. , , , , and This represents the learning rate, with a value range of [0, 1].

[0070] In an optional embodiment, if the index value is not less than a critical threshold, the method further includes: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network will not be tuned, and the expected value of the current tuning parameters will be output as the optimal tuning parameters.

[0071] The optimal tuning parameter, the corresponding index value, and the error level determined based on the corresponding index value are used as a set of historical tuning data.

[0072] Determine whether the error level of each set of historical setting data meets the preset standard; otherwise, set the grid connection parameters of the target distribution network based on the current power data and the current load data.

[0073] And / or, when the cumulative value of the indicator within a preset time period is greater than the preset cumulative threshold, an error compensation factor is determined based on the historical tuning data within the preset time period, and the critical threshold is adjusted based on the error compensation factor.

[0074] If the index value is not less than the critical threshold, it means that the actual setting parameters required when the target distribution network is connected to the grid match the current actual setting parameters. In this case, it is not necessary to set the current grid connection parameters of the target distribution network. The expected value of the current setting parameters can be output as the optimal setting parameters.

[0075] If the calculated index value is always less than the critical threshold, this will have a drawback. Although the actual required setting parameters match the current actual setting parameters each time, the characteristics of photovoltaic grid connection will lead to sudden changes in the grid connection parameters. Even if the calculated index value is always less than the critical threshold, sudden changes may still occur, causing a mismatch between the actual required setting parameters and the current actual setting parameters when the target distribution network is connected. In this case, adjusting the settings will affect the safe operation of the distribution network.

[0076] To avoid this situation, the expected value of the current setting parameter can be used for setting at preset intervals, even if the actual setting parameters required when the target distribution network is connected to the grid match the current actual setting parameters.

[0077] Alternatively, the optimal tuning parameters, the corresponding index values, and the error level determined based on the corresponding index values ​​can be stored as a set of historical tuning data.

[0078] The error level is determined based on the magnitude of the index value and can be divided into three levels: Level 1, Level 2, and Level 3; Level 1 represents low error, Level 2 represents medium error, and Level 3 represents high error.

[0079] If the number of consecutive occurrences of high-level errors in each set of continuous historical data exceeds the preset number, then the grid connection parameters of the target distribution network are adjusted based on the current power data and the current load data.

[0080] Alternatively, the cumulative values ​​of each set of indicators can be calculated over a preset time period. While a single indicator value reflects only the parameter mismatch at that particular moment, the cumulative value sums the deviations from all moments within the preset time period, indicating whether the deviation is persistent or merely apparent. Furthermore, the cumulative value not only reflects the duration of the deviation but also its magnitude. If an indicator value significantly exceeds a critical threshold at a certain moment, its contribution to the cumulative value will be far greater than at moments with slight deviations, thus quantifying the overall severity of the parameter mismatch within that time period.

[0081] When the cumulative value of the indicator within the preset time period exceeds the preset cumulative threshold, it indicates that the currently used critical threshold is no longer suitable for the current situation. Therefore, the error compensation factor can be determined by fitting the historical tuning data within the preset time period, and the critical threshold can be adjusted based on the error compensation factor.

[0082] When the cumulative value of the indicator within the preset time period is not greater than the preset cumulative threshold, it indicates that the system has returned to normal. The critical threshold can be adjusted back to its original value. This method can avoid the resource consumption caused by over-setting and the operational risks of the distribution network caused by timely setting.

[0083] To verify the effectiveness of the method provided in this embodiment, an example is used for verification below: The following will illustrate this with specific examples. Figure 2 This is a distribution network node topology diagram provided in an embodiment of the present invention. Taking this topology as an example, each node in the diagram is equipped with 20kW photovoltaic power, while nodes 1-5 and nodes 19-25 are configured with energy storage. The upper limit of the energy storage capacity is 100kW, the charging and discharging efficiency is 0.9, the upper limit of SOC is 0.9, and the lower limit is 0.1. Nodes 7-18 are flexible load nodes with photovoltaic power, and nodes 26-33 are electric vehicle nodes with photovoltaic power.

[0084] Figure 3 This is a comparison chart of the per-unit voltage values ​​of distribution network nodes before and after photovoltaic grid connection, provided in an embodiment of the present invention. Figure 3 As shown, the horizontal axis represents the time period, the vertical axis represents the per-unit value, the triangle line represents the per-unit value of the node voltage when there is no photovoltaic connection, and the star line represents the per-unit value of the node voltage after photovoltaic connection.

[0085] based on Figure 3 It can be seen that when photovoltaics are not connected, the per-unit voltage values ​​of each node in the distribution network vary greatly, and some nodes may experience voltage over-limit phenomena. However, after photovoltaics and energy storage are connected, the node voltages are all improved, and there are no voltage over-limit phenomena. This indicates that the connection of photovoltaics and energy storage can effectively improve the power quality of the distribution network, thereby promoting the photovoltaic absorption capacity.

[0086] Next, we will analyze the impact of photovoltaic, energy storage, charging, and utilization integration on the reactive power of the distribution network. Figure 4 This is a comparison diagram of reactive power in the distribution network considering only photovoltaic (PV) grid connection and considering simultaneous PV charging and utilization, provided by an embodiment of the present invention; as shown. Figure 4 As shown, the circular lines represent the reactive power curve of the distribution network when only photovoltaic (PV) access is considered, while the star-shaped lines represent the reactive power curve of the distribution network when PV charging and consumption are both considered.

[0087] A comparison of the two shows that flexible loads and electric vehicle charging significantly increase reactive power demand, while energy storage absorbs reactive power during discharge, indicating that the system's reactive power increases when photovoltaic, energy storage, and charging are considered simultaneously.

[0088] In this case, the reference values ​​for grid connection tuning parameters are determined using the method provided in this embodiment, and corresponding parameters are initialized accordingly: , , , , and All values ​​are 1*10-3. , , , , and All values ​​are 1*10-3. , , .

[0089] After parameter tuning using the parameter tuning method provided in this embodiment of the invention, the obtained expected value and actual value are as follows: Figure 5 As shown. Figure 5 As shown, after approximately 0.15 seconds, the actual system value equals the expected value, indicating that the method provided in this embodiment has a good tracking effect.

[0090] Figure 6 This is a graph showing the tuning process of multi-load grid connection parameters in a simulation example provided in this invention; refer to... Figure 5 It can be seen that once the actual value equals the expected value, the three parameters—power data, electric vehicle load data, and flexible load data—no longer change. In this embodiment, the final values ​​for the three data points during the tuning process are as follows: , , .

[0091] In summary, by using radial basis function neural networks to tune grid-connected parameters, the grid-connected parameters can be iteratively updated to ultimately determine grid-connected parameters that meet preset standards, thereby improving the tuning accuracy of grid-connected parameters. Furthermore, the simple structure and few parameters of radial basis function neural networks make the tuning process of grid-connected parameters simpler, thus improving tuning efficiency.

[0092] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0093] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0094] Figure 7 A schematic diagram of the multi-load grid connection parameter setting device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below: like Figure 7 As shown, the multi-load grid connection parameter setting device 7 includes: The acquisition module 71 is used to acquire the current power data and current load data in the target distribution network, which are determined based on the photovoltaic output power; wherein, the current load data includes the load data of electric vehicles and the load data of flexible loads; Module 72 is used to construct a multi-variable load grid connection parameter model based on the current power data and the current load data, so as to obtain the expected value of the current setting parameters; Calculation module 73 is used to calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; The tuning module 74 is used to tune the grid connection parameters of the target distribution network based on the power data, load data and the expected value of the current tuning parameters at the next moment if the index value is not less than the critical threshold.

[0095] In one possible implementation, module 72 is specifically used for: Based on the current power data and current load data, construct a multi-dimensional load grid connection parameter model; A radial basis function neural network is used to solve the multi-element load grid connection parameter model; Based on the solution results, the expected values ​​of the current tuning parameters are obtained.

[0096] In one possible implementation, the tuning module 74 is specifically used for: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are tuned based on the expected value of the current tuning parameters, and the hidden layer activation function of the radial basis function neural network is updated based on the power data and load data at the next moment after tuning; wherein, the center position of the hidden layer activation function and the update of the basis function width, as well as the weight of the grid connection parameters, are determined based on the expected value of the current tuning parameters. Based on the updated radial basis function neural network, the multi-variable load grid connection parameter model is solved until the obtained index value is less than the critical threshold.

[0097] In one possible implementation, module 72 is specifically used for... With the goal of balancing load power supply and demand, a multi-dimensional load grid connection parameter model is constructed based on current power data and current load data; The multi-load grid connection parameter model is as follows:

[0098] In the formula, This represents a multi-load grid connection parameter model. , and These represent the grid connection parameters for photovoltaic-integrated energy storage nodes, photovoltaic-integrated electric vehicle nodes, and photovoltaic-integrated flexible load nodes, respectively. , and Let represent the power functions of a photovoltaic-integrated energy storage node, a photovoltaic-integrated electric vehicle node, and a photovoltaic-integrated flexible load node, respectively. , and These represent the sets of energy storage nodes containing photovoltaics, the sets of electric vehicle nodes containing photovoltaics, and the sets of flexible load nodes containing photovoltaics, respectively.

[0099] In one possible implementation, module 71 is specifically used for: Construct a photovoltaic-storage-charging-utilization system model that satisfies the first preset constraint condition; wherein, the photovoltaic-storage-charging-utilization system model includes a photovoltaic-integrated energy storage node power model, a photovoltaic-integrated electric vehicle node power model, and a photovoltaic-integrated flexible load node power model; Based on the power model of the energy storage node containing photovoltaics, obtain the current power data of the target distribution network determined based on the photovoltaic output power; Based on the power model of electric vehicle nodes with photovoltaics and the power model of flexible load nodes with photovoltaics, the current load data of the target distribution network determined by photovoltaic output power is obtained.

[0100] In one possible implementation, the computation module 73 is specifically used for: Based on the index function formula, calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; The index function formula is used to characterize the square of the difference between the expected value of the current tuning parameter and the actual value of the current tuning parameter.

[0101] In one possible implementation, the tuning module 74 is also used for: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network will not be tuned, and the expected value of the current tuning parameters will be output as the optimal tuning parameters.

[0102] In one possible implementation, the tuning module 74 is also used for: The optimal tuning parameter, the index value corresponding to the optimal tuning parameter, and the error level determined based on the index value corresponding to the optimal tuning parameter are used as a set of historical tuning data. Determine whether the error level of each set of historical setting data meets the preset standard; otherwise, set the grid connection parameters of the target distribution network based on the current power data and the current load data. And / or, when the cumulative value of the indicator within a preset time period is greater than the preset cumulative threshold, an error compensation factor is determined based on the historical tuning data within the preset time period, and the critical threshold is adjusted based on the error compensation factor.

[0103] Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 8 As shown, the electronic device 8 of this embodiment includes a processor 80 and a memory 81. The memory 81 stores a computer program 82. When the processor 80 executes the computer program 82, it implements the steps in the various method embodiments described above. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the various device embodiments described above.

[0104] For example, computer program 82 may be divided into one or more modules / units, which are stored in memory 81 and executed by processor 80 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 82 in electronic device 8.

[0105] Electronic device 8 may include, but is not limited to, processor 80 and memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of electronic device 8 and does not constitute a limitation on electronic device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 8 may also include input / output devices, network access devices, buses, etc.

[0106] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0107] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0108] The above-described 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, and should all be included within the protection scope of the present invention.

Claims

1. A method for setting parameters for multi-load grid connection, characterized in that, include: Acquire current power data and current load data in the target distribution network based on photovoltaic output power; wherein, the current load data includes load data of electric vehicles and load data of flexible loads; Based on the current power data and the current load data, a multi-dimensional load grid connection parameter model is constructed to obtain the expected values ​​of the current setting parameters; Calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are adjusted based on the power data, load data and the expected value of the current setting parameters at the next time moment.

2. The method for setting parameters for multi-load grid connection according to claim 1, characterized in that, The step of constructing a multi-dimensional load grid connection parameter model based on the current power data and the current load data to obtain the expected value of the current setting parameters includes: Based on the current power data and the current load data, a multi-dimensional load grid connection parameter model is constructed; A radial basis function neural network is used to solve the multi-element load grid connection parameter model; Based on the solution results, the expected values ​​of the current tuning parameters are obtained.

3. The method for setting parameters for multi-load grid connection according to claim 2, characterized in that, If the index value is not less than the critical threshold, then the grid connection parameters of the target distribution network are adjusted based on the power data, load data, and the expected value of the current setting parameters at the next time moment, including: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network are tuned based on the expected value of the current tuning parameters, and the hidden layer activation function of the radial basis function neural network is updated based on the power data and load data at the next moment after tuning; wherein, the update of the center position and the width of the basis function of the hidden layer activation function, as well as the weight of the grid connection parameters, are determined based on the expected value of the current tuning parameters. The multi-variable load grid connection parameter model is solved based on the updated radial basis function neural network until the obtained index value is less than the critical threshold.

4. The method for setting parameters for multi-load grid connection according to claim 2, characterized in that, The step of constructing a multi-dimensional load grid connection parameter model based on the current power data and the current load data includes: With the goal of balancing load power supply and demand, a multi-dimensional load grid connection parameter model is constructed based on the current power data and the current load data. The multi-load grid connection parameter model is as follows: In the formula, This represents a multi-load grid connection parameter model. , and These represent the grid connection parameters for photovoltaic-integrated energy storage nodes, photovoltaic-integrated electric vehicle nodes, and photovoltaic-integrated flexible load nodes, respectively. , and Let represent the power functions of a photovoltaic-integrated energy storage node, a photovoltaic-integrated electric vehicle node, and a photovoltaic-integrated flexible load node, respectively. , and These represent the sets of energy storage nodes containing photovoltaics, the sets of electric vehicle nodes containing photovoltaics, and the sets of flexible load nodes containing photovoltaics, respectively.

5. The method for setting parameters for multi-load grid connection according to claim 1, characterized in that, The acquisition of current power data and current load data in the target distribution network, determined based on photovoltaic output power, includes: Construct a photovoltaic-storage-charging-utilization system model that satisfies the first preset constraint condition; wherein, the photovoltaic-storage-charging-utilization system model includes a photovoltaic-integrated energy storage node power model, a photovoltaic-integrated electric vehicle node power model, and a photovoltaic-integrated flexible load node power model; Based on the photovoltaic-integrated energy storage node power model, obtain the current power data in the target distribution network determined based on the photovoltaic output power; Based on the photovoltaic-integrated electric vehicle node power model and the photovoltaic-integrated flexible load node power model, the current load data in the target distribution network, determined based on the photovoltaic output power, is obtained.

6. The method for setting parameters for multi-load grid connection according to claim 1, characterized in that, The calculation of the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter includes: Calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter according to the index function formula; The index function formula is used to characterize the square of the difference between the expected value of the current tuning parameter and the actual value of the current tuning parameter.

7. The method for setting parameters for multi-load grid connection according to claim 1, characterized in that, If the index value is not less than a critical threshold, the method further includes: If the index value is not less than the critical threshold, the grid connection parameters of the target distribution network will not be tuned, and the expected value of the current tuning parameter will be output as the optimal tuning parameter.

8. The method for setting parameters for multi-load grid connection according to claim 7, characterized in that, After stating that if the index value is not less than a critical threshold, the grid connection parameters of the target distribution network will not be tuned, and the expected value of the tuning parameters will be output as the optimal tuning parameters, the method further includes: The optimal tuning parameter, the index value corresponding to the optimal tuning parameter, and the error level determined based on the index value corresponding to the optimal tuning parameter are used as a set of historical tuning data. Determine whether the error level of each set of historical setting data meets the preset standard; otherwise, adjust the grid connection parameters of the target distribution network based on the current power data and the current load data. And / or, when the cumulative value of the indicator within a preset time period is greater than a preset cumulative threshold, an error compensation factor is determined based on the historical tuning data within the preset time period, and the critical threshold is adjusted based on the error compensation factor.

9. A multi-load grid connection parameter setting device, characterized in that, include: The acquisition module is used to acquire current power data and current load data in the target distribution network, determined based on photovoltaic output power; wherein, the current load data includes load data of electric vehicles and load data of flexible loads; The construction module is used to construct a multi-dimensional load grid connection parameter model based on the current power data and the current load data, so as to obtain the expected value of the current setting parameters; The calculation module is used to calculate the index value between the expected value of the current tuning parameter and the actual value of the current tuning parameter; The tuning module is used to tune the grid connection parameters of the target distribution network based on the power data, load data and the expected value of the current tuning parameters at the next moment if the index value is not less than the critical threshold.

10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.

Images