Method and device for dynamic evaluation and promotion of power distribution area light storage charging carrying capacity and computer equipment

Abstract

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for dynamically assessing and improving the photovoltaic, energy storage, and charging capacity of a distribution substation. The method includes: acquiring multi-source operational data of the distribution substation during the current decision-making period; constructing a dynamic capacity assessment model for the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operational data of the distribution substation during the current decision-making period; solving the dynamic capacity assessment model to obtain the maximum accessible photovoltaic, energy storage, and charging capacity of the distribution substation during the current decision-making period, and generating a target multi-device coordinated control strategy for the maximum accessible photovoltaic, energy storage, and charging capacity; generating timing control commands for the photovoltaic, energy storage, and charging equipment in the distribution substation according to the target multi-device coordinated control strategy, and adjusting the operating power of the photovoltaic, energy storage, and charging equipment through the timing control commands. Using this method, the utilization rate of power distribution resources in the distribution substation can be improved.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for dynamic evaluation and improvement of the photovoltaic, energy storage, and charging carrying capacity of a distribution substation. Background Technology

[0002] With the rapid popularization of new energy vehicles and the rapid development of distributed photovoltaics, more and more distribution substations are connecting to distributed photovoltaics, energy storage systems and electric vehicle charging piles (referred to as photovoltaic-storage-charging).

[0003] In traditional technologies, the assessment of the photovoltaic, energy storage, and charging capacity of a distribution substation is generally conducted using manual experience. However, manual assessment is prone to errors, resulting in a low accuracy rate in assessing the photovoltaic, energy storage, and charging capacity. Consequently, when controlling the operation of the photovoltaic, energy storage, and charging equipment in the distribution substation based on the manually assessed capacity, it is difficult to fully utilize the operational efficiency of the equipment, ultimately leading to a low utilization rate of power distribution resources in the distribution substation. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for dynamically evaluating and improving the photovoltaic, energy storage, and charging carrying capacity of a distribution substation, which can improve the utilization rate of power distribution resources in the substation.

[0005] Firstly, this application provides a method for dynamically evaluating and improving the optical storage and charging capacity of a distribution network, including:

[0006] Acquire multi-source operational data of the distribution radio area during the current decision-making cycle;

[0007] Based on the multi-source operation data of the distribution substation in the current decision-making cycle, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed.

[0008] Solve the dynamic evaluation model of the carrying capacity to obtain the maximum access capacity of the distribution radio area for optical storage and charging in the current decision period, and generate a target multi-device collaborative control strategy for the maximum access capacity of optical storage and charging.

[0009] According to the target multi-device collaborative control strategy, a timing control command is generated for the optical storage and charging equipment in the distribution area, and the operating power of the optical storage and charging equipment is adjusted through the timing control command;

[0010] The process involves acquiring multi-source operational data of the distribution substation in the next decision cycle of the current decision cycle, using the multi-source operational data of the next decision cycle as the multi-source operational data of the current decision cycle, and then proceeding to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operational data of the distribution substation in the current decision cycle, until a preset assessment termination condition is met.

[0011] In one embodiment, acquiring multi-source operational data of the distribution radio area in the current decision-making cycle includes:

[0012] Acquire historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution area; acquire historical and current user load data of the distribution area; and acquire meteorological element forecast data for future periods.

[0013] The historical operating data, the current operating data, the historical user load data, the current user load data, and the meteorological element forecast data for future periods are fused to obtain the multi-source operating data of the distribution area in the current decision-making cycle.

[0014] In one embodiment, the step of constructing a dynamic carrying capacity assessment model for the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operational data of the distribution substation in the current decision-making period, includes:

[0015] Based on the multi-source operation data of the distribution substation in the current decision-making period, determine the uncertainty characterization parameters of source load prediction, the model optimization objective, and the opportunity constraints.

[0016] Based on the source load prediction uncertainty characterization parameters, the model optimization objective, and the opportunity constraints, an optimization evaluation model is constructed.

[0017] Based on the optimized evaluation model, a dynamic evaluation model for the carrying capacity of the distribution substation considering the uncertainty of source load prediction is obtained.

[0018] In one embodiment, solving the dynamic assessment model of the carrying capacity to obtain the maximum available optical storage and charging capacity of the distribution radio area in the current decision period includes:

[0019] The dynamic evaluation model of carrying capacity is solved using a mixed-integer linear programming algorithm or an intelligent optimization algorithm to obtain the model solution results;

[0020] Based on the solution results of the model, the maximum available access capacity of the distribution radio area for optical storage and charging in the current decision period is obtained.

[0021] In one embodiment, generating a target multi-device collaborative control strategy for the maximum accessible optical storage and charging capacity includes:

[0022] Based on the maximum accessible capacity of optical storage and charging, multiple candidate multi-device collaborative control strategies for the maximum accessible capacity of optical storage and charging are obtained, as well as the predicted probability of each candidate multi-device collaborative control strategy.

[0023] From the multiple candidate multi-device collaborative control strategies, the candidate multi-device collaborative control strategy with the highest predicted probability is selected;

[0024] Based on the candidate multi-device collaborative control strategy with the highest predicted probability, a target multi-device collaborative control strategy for the maximum available optical storage and charging capacity is obtained.

[0025] In one embodiment, adjusting the operating power of the optical storage and charging device via the timing control command includes:

[0026] The timing control command is sent to the distribution area's converged terminal via a preset communication protocol; the converged terminal is used to send the timing control command to the controller of the optical storage and charging equipment, so that the controller adjusts the operating power of the optical storage and charging equipment based on the timing control command.

[0027] Secondly, this application also provides a dynamic evaluation and improvement device for the photovoltaic storage and charging capacity of a distribution station area, comprising:

[0028] The data acquisition module is used to acquire multi-source operational data of the distribution radio area during the current decision-making cycle;

[0029] The model building module is used to build a dynamic assessment model of the carrying capacity of the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operation data of the distribution substation in the current decision-making cycle.

[0030] The strategy generation module is used to solve the dynamic evaluation model of the carrying capacity to obtain the maximum optical storage and charging access capacity of the distribution radio area in the current decision period, and generate a target multi-device collaborative control strategy for the maximum optical storage and charging access capacity.

[0031] The equipment control module is used to generate timing control commands for the optical storage and charging equipment in the distribution area according to the target multi-device collaborative control strategy, and adjust the operating power of the optical storage and charging equipment through the timing control commands;

[0032] The loop processing module is used to acquire the multi-source operation data of the distribution substation in the next decision cycle of the current decision cycle, use the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jump to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operation data of the distribution substation in the current decision cycle, until the preset assessment termination condition is reached.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Acquire multi-source operational data of the distribution radio area during the current decision-making cycle;

[0035] Based on the multi-source operation data of the distribution substation in the current decision-making cycle, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed.

[0036] Solve the dynamic evaluation model of the carrying capacity to obtain the maximum access capacity of the distribution radio area for optical storage and charging in the current decision period, and generate a target multi-device collaborative control strategy for the maximum access capacity of optical storage and charging.

[0037] According to the target multi-device collaborative control strategy, a timing control command is generated for the optical storage and charging equipment in the distribution area, and the operating power of the optical storage and charging equipment is adjusted through the timing control command;

[0038] The process involves acquiring multi-source operational data of the distribution substation in the next decision cycle of the current decision cycle, using the multi-source operational data of the next decision cycle as the multi-source operational data of the current decision cycle, and then proceeding to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operational data of the distribution substation in the current decision cycle, until a preset assessment termination condition is met.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] Acquire multi-source operational data of the distribution radio area during the current decision-making cycle;

[0041] Based on the multi-source operation data of the distribution substation in the current decision-making cycle, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed.

[0042] Solve the dynamic evaluation model of the carrying capacity to obtain the maximum access capacity of the distribution radio area for optical storage and charging in the current decision period, and generate a target multi-device collaborative control strategy for the maximum access capacity of optical storage and charging.

[0043] According to the target multi-device collaborative control strategy, a timing control command is generated for the optical storage and charging equipment in the distribution area, and the operating power of the optical storage and charging equipment is adjusted through the timing control command;

[0044] The process involves acquiring multi-source operational data of the distribution substation in the next decision cycle of the current decision cycle, using the multi-source operational data of the next decision cycle as the multi-source operational data of the current decision cycle, and then proceeding to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operational data of the distribution substation in the current decision cycle, until a preset assessment termination condition is met.

[0045] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0046] Acquire multi-source operational data of the distribution radio area during the current decision-making cycle;

[0047] Based on the multi-source operation data of the distribution substation in the current decision-making cycle, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed.

[0048] Solve the dynamic evaluation model of the carrying capacity to obtain the maximum access capacity of the distribution radio area for optical storage and charging in the current decision period, and generate a target multi-device collaborative control strategy for the maximum access capacity of optical storage and charging.

[0049] According to the target multi-device collaborative control strategy, a timing control command is generated for the optical storage and charging equipment in the distribution area, and the operating power of the optical storage and charging equipment is adjusted through the timing control command;

[0050] The process involves acquiring multi-source operational data of the distribution substation in the next decision cycle of the current decision cycle, using the multi-source operational data of the next decision cycle as the multi-source operational data of the current decision cycle, and then proceeding to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operational data of the distribution substation in the current decision cycle, until a preset assessment termination condition is met.

[0051] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for dynamically assessing and improving the carrying capacity of a distribution substation's optical-storage-charging (OSC) capacity first acquires multi-source operational data of the distribution substation during the current decision-making period. Next, based on this data, a dynamic assessment model of the OSC capacity, taking into account the uncertainty of source load prediction, is constructed. This model is then solved to obtain the maximum accessible OSC capacity during the current decision-making period, generating a target multi-device collaborative control strategy for this maximum capacity. Following this strategy, timing control commands are generated for the OSC equipment in the distribution substation, adjusting their operating power. Finally, multi-source operational data for the next decision-making period is acquired and used as the current data. The process then jumps back to the step of constructing the dynamic assessment model of the OSC capacity, taking into account the uncertainty of source load prediction, based on the current OSC data, until a preset assessment termination condition is met. Thus, when assessing the photovoltaic (PV), energy storage, and charging (ESC) carrying capacity of a distribution network, a dynamic assessment model considering the uncertainty of source load prediction is first constructed based on the multi-source operational data of the distribution network during the current decision-making period. This model is then solved to obtain the maximum PV, ESC, and charging capacity that can be accessed during the current decision-making period. In other words, by comprehensively considering the multi-source operational data of the distribution network during the current decision-making period and utilizing the dynamic assessment model considering the uncertainty of source load prediction, the maximum PV, ESC, and charging capacity that can be accessed during the current decision-making period is assessed. Furthermore, dynamic assessment based on each decision-making period ensures that the assessed maximum PV, ESC, and charging capacity is accurately determined. The accuracy of the available charging capacity is improved, thereby enhancing the assessment accuracy of the maximum available photovoltaic, energy storage, and charging capacity in the distribution substation. Furthermore, based on the target multi-device collaborative control strategy for the maximum available photovoltaic, energy storage, and charging capacity, timing control commands are generated for the photovoltaic, energy storage, and charging equipment in the distribution substation. By adjusting the operating power of the photovoltaic, energy storage, and charging equipment through these timing control commands, the aim of adjusting the operating power of the photovoltaic, energy storage, and charging equipment in the distribution substation based on the target multi-device collaborative control strategy for the maximum available photovoltaic, energy storage, and charging capacity is achieved. This is conducive to fully utilizing the operating efficiency of the photovoltaic, energy storage, and charging equipment in the distribution substation, thereby making full use of the distribution resources in the distribution substation and improving the utilization rate of the distribution resources in the distribution substation. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating a method for dynamically evaluating and improving the photovoltaic, energy storage, and charging carrying capacity of a distribution station area in one embodiment.

[0054] Figure 2 This is a flowchart illustrating the steps involved in constructing a dynamic capacity assessment model for a distribution substation that takes into account the uncertainty of source load prediction, as shown in one embodiment.

[0055] Figure 3 This is a flowchart illustrating a method for dynamically evaluating and improving the photovoltaic-storage-charging carrying capacity of a distribution station area in another embodiment.

[0056] Figure 4 This is a structural block diagram of a device for dynamically evaluating and improving the photovoltaic storage and charging carrying capacity of a distribution station area in one embodiment;

[0057] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0060] In one exemplary embodiment, such as Figure 1As shown, a method for dynamically evaluating and improving the photovoltaic, energy storage, and charging capacity of a distribution network area is provided. This embodiment uses the application of this method to a server as an example for illustration. It is understood that this method can also be applied to terminals, and further to systems including terminals and servers, and is implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, and tablets; the servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing cloud computing services. (Reference) Figure 1 The method includes the following steps S101 to S105. Wherein:

[0061] Step S101: Obtain multi-source operation data of the distribution radio area in the current decision-making cycle.

[0062] In this context, a distribution transformer area refers to the entire area supplied by a distribution transformer, specifically the entire area supplied by a single distribution transformer, including all electricity consumption, generation, and energy storage / charging equipment within that area. In practical scenarios, a distribution transformer area includes photovoltaic (PV) storage / charging equipment; this equipment refers to distributed photovoltaic devices, energy storage systems (such as energy storage batteries and supporting systems), and electric vehicle charging stations.

[0063] The current decision cycle refers to the decision cycle divided according to the preset cycle division method, such as a decision cycle of 15 minutes.

[0064] Multi-source operational data refers to data from multiple dimensions related to the assessment of the grid-connected capacity of the distribution substation within the current decision-making cycle. This includes data such as the real-time and historical output sequences of distributed photovoltaic equipment, the real-time and historical power sequences of user loads, the state of charge and charge / discharge power boundaries of the energy storage system, the real-time operational status and set parameters of electric vehicle charging piles, and meteorological forecast data for the corresponding time period. Furthermore, multi-source operational data also includes: real-time active power, reactive power, and current data at the grid connection points of the substation, as well as the charging end time and expected charge amount set by users of each charging pile.

[0065] For example, the server uses multi-source operational data acquisition instructions to obtain initial multi-source operational data of the distribution transformer area in the current decision-making period, and preprocesses the initial multi-source operational data, such as converting the data format, to obtain the multi-source operational data of the distribution transformer area in the current decision-making period. Alternatively, the server can directly obtain the multi-source operational data of the distribution transformer area in the current decision-making period from the database.

[0066] Step S102: Based on the multi-source operation data of the distribution substation in the current decision-making cycle, construct a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction.

[0067] The dynamic capacity assessment model refers to an optimized assessment model used to evaluate the maximum available optical, energy storage, and charging capacity of a distribution and transmission area during the current decision-making period. Alternatively, the dynamic capacity assessment model can also refer to a network model used to evaluate the maximum available optical, energy storage, and charging capacity of a distribution and transmission area during the current decision-making period, such as a convolutional neural network model or a deep learning model.

[0068] For example, the server determines the source-load prediction uncertainty characterization parameters, model optimization objectives, and opportunity constraints based on the multi-source operation data of the distribution substation in the current decision-making cycle. Then, based on the source-load prediction uncertainty characterization parameters, model optimization objectives, and opportunity constraints, it constructs a dynamic assessment model of the carrying capacity of the distribution substation that takes into account the source-load prediction uncertainty.

[0069] Step S103: Solve the dynamic assessment model of carrying capacity to obtain the maximum available access capacity of the distribution radio station area in the current decision cycle, and generate a target multi-device collaborative control strategy for the maximum available access capacity of the distribution radio station area.

[0070] The maximum PV-storage-charging capacity that a distribution substation can connect to during the current decision-making cycle refers to the maximum power threshold that allows the three types of equipment—PV, energy storage, and charging—to operate simultaneously under current operating conditions. Specifically, it refers to the upper limit of the total power that the distribution substation can currently accommodate, including PV power generation, energy storage charging / discharging, and charging pile power consumption, without overloading. For example, the maximum PV-storage-charging capacity = remaining available power capacity of the substation transformer; remaining capacity = rated active power capacity of the transformer - fixed electrical load of the substation foundation. Furthermore, the maximum PV-storage-charging capacity can also include the power limit that can be added beyond existing equipment, such as the maximum power of additional distributed PV equipment that can be installed, or the maximum power of the energy storage system that can be configured.

[0071] It should be noted that the maximum grid-connected capacity of photovoltaic, energy storage and charging can specifically include the maximum operating power of distributed photovoltaic equipment, the maximum operating power of energy storage system and the maximum operating power of electric vehicle charging pile; for example, the maximum grid-connected capacity of photovoltaic, energy storage and charging is 800kW, the maximum operating power of distributed photovoltaic equipment is 450kW, the maximum operating power of energy storage system is 200kW and the maximum operating power of electric vehicle charging pile is 150kW.

[0072] Among them, the target multi-device coordinated control strategy refers to the multi-device coordinated control strategy for the maximum accessible capacity of photovoltaic, energy storage and charging. Specifically, it includes a sequence of timing control commands for the operating power of photovoltaic, energy storage and charging equipment in the distribution area, which is used for peak shaving and valley filling of photovoltaic, flexible management and control of charging load, and adaptation to uncertain fluctuations.

[0073] For example, the server uses an intelligent optimization algorithm (such as particle swarm optimization) to solve the dynamic evaluation model of carrying capacity and obtain the optimal solution of the model, which is taken as the maximum optical storage and charging access capacity of the distribution area in the current decision cycle. Then, it queries the correspondence between the maximum optical storage and charging access capacity and the multi-device collaborative control strategy to obtain the multi-device collaborative control strategy for the maximum optical storage and charging access capacity, which is taken as the target multi-device collaborative control strategy.

[0074] For example, the server can also perform feature extraction processing on the multi-source operation data of the distribution substation in the current decision-making period to obtain multi-source operation data features. Then, the multi-source operation data features are input into a pre-constructed dynamic capacity assessment model for the distribution substation that takes into account the uncertainty of source load prediction. The dynamic capacity assessment model is used to evaluate the available optical-storage-charging capacity of the multi-source operation data features to obtain multiple available optical-storage-charging capacities and the prediction probability corresponding to each available optical-storage-charging capacity. Finally, the available optical-storage-charging capacity with the highest prediction probability is selected from the multiple available optical-storage-charging capacities as the maximum available optical-storage-charging capacity of the distribution substation in the current decision-making period.

[0075] Step S104: According to the target multi-device collaborative control strategy, generate timing control commands for the optical storage and charging equipment in the distribution area, and adjust the operating power of the optical storage and charging equipment through the timing control commands.

[0076] The timing control commands for photovoltaic, energy storage, and charging equipment in distribution substations refer to the timing control commands for the operating power of these equipment. Specifically, this includes timing control commands for the operating power of distributed photovoltaic equipment, the operating power of energy storage systems, and the operating power of electric vehicle charging piles in distribution substations. For example, if the total power of photovoltaic and energy storage systems when fully charged is less than the maximum connectable capacity, then it operates at full power normally; if the total power of photovoltaic and energy storage systems when fully charged is greater than or equal to the maximum connectable capacity, then the power of electric vehicle charging piles is reduced, the charging and discharging power of the energy storage system is adjusted, and the grid-connected photovoltaic output is limited.

[0077] The timing control command is used to indicate that the operating power of the optical storage and charging equipment is adjusted during a specific time period. For example, during time period T1, the operating power of the optical storage and charging equipment is reduced to W1; during time period T2, the operating power of the optical storage and charging equipment is increased to W2.

[0078] For example, based on a target multi-device collaborative control strategy, the server determines the timing control information for the operating power of the photovoltaic, energy storage, and charging equipment in the distribution area. Then, according to the timing control information for the operating power of the photovoltaic, energy storage, and charging equipment in the distribution area, it generates timing control instructions for the photovoltaic, energy storage, and charging equipment in the distribution area. Finally, the server adjusts the operating power of the photovoltaic, energy storage, and charging equipment using the timing control instructions. For example, the server adjusts the operating power of the distributed photovoltaic equipment according to the timing control instructions for the operating power of the distributed photovoltaic equipment; the server adjusts the operating power of the energy storage system according to the timing control instructions for the operating power of the energy storage system; and the server adjusts the operating power of the electric vehicle charging pile according to the timing control instructions for the operating power of the electric vehicle charging pile.

[0079] Step S105: Obtain multi-source operation data of the distribution substation in the next decision cycle of the current decision cycle, use the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jump to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operation data of the distribution substation in the current decision cycle, until the preset assessment termination condition is reached.

[0080] Each decision cycle has the same duration, such as 15 minutes.

[0081] Among them, the preset evaluation termination condition refers to the criteria for determining when the rolling evaluation cycle stops, such as reaching the preset evaluation duration, the area capacity being saturated, the operating condition becoming stable, or triggering a shutdown / maintenance command.

[0082] For example, the server retrieves the multi-source operation data of the distribution area in the next decision cycle from the database, uses the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jumps to step S102 to continue repeating the above steps until the preset evaluation termination condition is met, then stops the evaluation.

[0083] For example, this application also provides a method for dynamically assessing and improving the photovoltaic-storage-charging carrying capacity of a distribution substation, specifically including the following steps: S1, acquiring multi-source operating data of the distribution substation, wherein the multi-source operating data includes at least: real-time and historical output sequences of distributed photovoltaic power, real-time and historical power sequences of user loads, state of charge and charge / discharge power boundaries of the energy storage system, real-time operating status and set parameters of charging piles, and meteorological element forecast data for the corresponding time period; S2, based on the multi-source operating data, constructing a dynamic assessment model of carrying capacity that takes into account the uncertainty of source-load prediction, wherein the model quantifies the prediction uncertainty of photovoltaic output and load demand into a probability distribution. The safety operation constraints of the distribution substation are transformed into opportunity constraints; S3, the dynamic evaluation model of carrying capacity is solved to obtain the maximum photovoltaic, energy storage and charging access capacity of the distribution substation in the current decision period, and a multi-device collaborative control strategy for improving the carrying capacity is generated simultaneously. The collaborative control strategy includes a sequence of time-series control instructions for the charging and discharging power of the energy storage system, the active power output of the photovoltaic inverter and the charging power of the charging pile; S4, according to the preset rolling time domain optimization cycle, the above steps are repeated in each decision period, and the latest solved collaborative control strategy is sent to each controllable device through the substation fusion terminal for execution, so as to dynamically update the carrying capacity evaluation results of the substation and form a closed-loop control.

[0084] Specifically, the uncertainty in source-load prediction is quantified into a probability distribution, which is achieved by using a deep neural network based on quantile regression or a Bayesian neural network to directly output the quantile intervals of photovoltaic output and load demand at each prediction time in the future.

[0085] Specifically, the rolling time-domain optimization cycle is as follows: with a decision cycle of 15 minutes, at the beginning of each cycle, based on the latest real-time collected data and the rolling prediction data for the next 24 hours, the construction and solution steps are re-executed; the first control command in the control command sequence obtained from the previous round of optimization or the command for the next 1 to 4 time periods is sent to the substation convergence terminal via the MQTT (Message Queuing Telemetry Transport) protocol, and the terminal forwards it to the corresponding energy storage converter, photovoltaic inverter and charging pile controller according to the object model interface.

[0086] The closed-loop control includes a quantitative verification step for improving load capacity: comparing the peak-to-valley difference of the net load of the transformer area, the cumulative duration of reverse overload, and the number of voltage overruns within a preset time window before and after implementing the coordinated control strategy; and adaptively adjusting the confidence threshold of the opportunity constraint in the dynamic evaluation model of load capacity or the weight coefficient in the optimization objective based on the comparison results.

[0087] In the aforementioned dynamic assessment and improvement method for the photovoltaic-storage-charging (PV-SCDMA) carrying capacity of a distribution network, when assessing the PV-SCDMA carrying capacity, a dynamic assessment model considering the uncertainty of source load prediction is first constructed based on the multi-source operational data of the distribution network in the current decision-making period. This model is then solved to obtain the maximum PV-SCDMA-charging capacity that can be accessed in the current decision-making period. In other words, by comprehensively considering the multi-source operational data of the distribution network in the current decision-making period and using the dynamic assessment model considering the uncertainty of source load prediction, the maximum PV-SCDMA-charging capacity that can be accessed in the current decision-making period is assessed. Furthermore, dynamic assessments are performed for each decision-making period. This allows for a more accurate assessment of the maximum accessible photovoltaic (PV) storage and charging capacity, thereby improving the accuracy of the assessment. Furthermore, by generating timing control commands for the PV storage and charging equipment in the distribution substation according to the target multi-device collaborative control strategy for the maximum accessible PV storage and charging capacity, and adjusting the operating power of the PV storage and charging equipment through these commands, the aim of adjusting the operating power of the PV storage and charging equipment in the distribution substation based on the target multi-device collaborative control strategy for the maximum accessible PV storage and charging capacity is achieved. This helps to fully utilize the operating efficiency of the PV storage and charging equipment in the distribution substation, thereby making full use of the distribution resources in the distribution substation and improving the utilization rate of the distribution resources.

[0088] In an exemplary embodiment, step S101 above, obtaining multi-source operational data of the distribution transformer area in the current decision-making period, specifically includes the following: obtaining historical and current operational data of the photovoltaic storage and charging equipment in the distribution transformer area, obtaining historical and current user load data of the distribution transformer area, and obtaining meteorological element forecast data for future periods; and performing fusion processing on the historical operational data, current operational data, historical user load data, current user load data, and meteorological element forecast data for future periods to obtain multi-source operational data of the distribution transformer area in the current decision-making period.

[0089] Among them, the historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution area include the historical and current operating data of distributed photovoltaic equipment, the historical and current operating data of energy storage systems, and the historical and current operating data of electric vehicle charging piles. For example, the real-time output and historical output sequence of distributed photovoltaic equipment, the state of charge and charging and discharging power boundaries of energy storage systems, and the real-time operating status and set parameters of electric vehicle charging piles.

[0090] Among them, the historical user load data and current user load data of the distribution radio area include the real-time power and historical power sequence of the user load.

[0091] Among them, the meteorological element forecast data for the future period refers to the weather-related parameters for the future period (such as the next few hours or the next day), which is the core basis for predicting photovoltaic power output. Specifically, it includes solar irradiance, sunshine and rain, temperature, wind speed, etc.

[0092] For example, the server acquires historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution transformer area, historical and current user load data of the distribution transformer area, and meteorological element forecast data for future periods through data acquisition instructions; then, it preprocesses and summarizes the historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution transformer area, the historical and current user load data of the distribution transformer area, and the meteorological element forecast data for future periods to obtain multi-source operating data of the distribution transformer area in the current decision-making period.

[0093] In this embodiment, comprehensively considering the multi-source operating data of the distribution radio station area in the current decision-making cycle is beneficial to improving the accuracy of the maximum available optical storage and charging capacity obtained subsequently, thereby improving the evaluation accuracy of the maximum available optical storage and charging capacity of the distribution radio station area.

[0094] In one exemplary embodiment, such as Figure 2 As shown, step S102 above, based on the multi-source operational data of the distribution substation in the current decision-making cycle, constructs a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction. This specifically includes the following steps S201 to S203. Wherein:

[0095] Step S201: Based on the multi-source operation data of the distribution area in the current decision-making cycle, determine the uncertainty characterization parameters of source-load prediction, the model optimization objective, and the opportunity constraints.

[0096] Step S202: Based on the uncertainty characterization parameters of source load prediction, model optimization objectives, and chance constraints, construct an optimization evaluation model.

[0097] Step S203: Based on the optimized evaluation model, a dynamic evaluation model for the carrying capacity of the distribution substation, taking into account the uncertainty of source load prediction, is obtained.

[0098] Among them, the source-load forecast uncertainty characterization parameters refer to a set of numerical parameters that describe how photovoltaic output and user load will fluctuate randomly, the range of fluctuation, and the probability of occurrence. Specifically, they refer to the forecast intervals or probability quantiles of photovoltaic output and load demand, used to characterize their uncertainty. For example, by quantifying the forecast uncertainty of photovoltaic output and load demand into a probability distribution, the source-load forecast uncertainty characterization parameters can be obtained.

[0099] The model optimization objectives include maximizing the sum of the new distributed photovoltaic capacity and the new charging pile capacity that the distribution area can accommodate, and minimizing the overall operating costs of the distribution area (such as the cost of energy storage cycle aging, photovoltaic curtailment loss cost, and charging pile load adjustment compensation cost). It should be noted that the multi-objective optimization can be transformed into a single-objective optimization through weighted summation.

[0100] Among them, the opportunity constraint condition refers to the probabilistic inequality form that is valid at a given confidence level (such as 95%), which is transformed from the transformer capacity constraint, voltage over-limit constraint and energy storage system operation constraint respectively; for example, there is a 95% probability that the transformer power will not be overloaded, there is a 95% probability that the transformer voltage will not exceed the high and low voltage limits, and there is a 95% probability that the energy storage power will be within the operating range.

[0101] For example, based on the multi-source operation data of the distribution substation in the current decision-making period, the server determines a first optimization objective (i.e., maximizing the sum of the new distributed photovoltaic capacity and the new charging pile capacity that the substation can accommodate) and a second optimization objective (i.e., minimizing the comprehensive operating cost of the substation). The server then merges the first and second optimization objectives according to the first weight corresponding to the first optimization objective and the second weight corresponding to the second optimization objective, obtaining a merged optimization objective, which serves as the model optimization objective. Next, based on the multi-source operation data of the distribution substation in the current decision-making period, the transformer capacity constraint, voltage over-limit constraint, and energy storage system operation constraint are transformed into probabilistic inequalities that hold at a given confidence level, and these are used as chance constraints. Then, based on the multi-source operation data of the distribution substation in the current decision-making period, the prediction uncertainty of photovoltaic output and load demand is quantified into a probability distribution, obtaining source-load prediction uncertainty characterization parameters. Next, based on the source-load prediction uncertainty characterization parameters, the model optimization objective, and the chance constraints, a corresponding optimization evaluation model is constructed, such as a stochastic optimization model or a chance-constrained programming model. Finally, this optimization evaluation model is used as a dynamic evaluation model of the carrying capacity of the distribution substation considering source-load prediction uncertainty.

[0102] For example, the construction of a dynamic capacity assessment model that takes into account the uncertainty of source-load prediction specifically includes: inputting irradiance, temperature elements and historical power data from numerical weather prediction into a pre-trained deep neural network prediction model, and outputting the prediction interval or probability quantile of photovoltaic output and load demand to characterize their uncertainty; converting transformer capacity constraints, voltage over-limit constraints and energy storage system operation constraints into probabilistic inequalities that hold at a given confidence level; and constructing a stochastic optimization or chance-constrained programming model with the optimization objective of maximizing the sum of the new distributed photovoltaic capacity and the new charging pile capacity that the transformer area can accept.

[0103] The specific implementation of transforming transformer capacity constraints into opportunity constraints is as follows: the probability that the absolute value of the transformer's exchange power at any time does not exceed its rated capacity must be greater than or equal to a preset confidence threshold. This confidence threshold is set to 0.85 during light-load periods and 0.95 during heavy-load periods. Through the opportunity constraints, the prediction uncertainty is transformed into a probabilistic relaxation or tightening of the transformer's safety boundary in the load-bearing capacity assessment model.

[0104] The dynamic evaluation model for carrying capacity also includes an economic objective: on the basis of maximizing the access capacity of photovoltaic, energy storage and charging, an additional objective of minimizing the comprehensive operating cost of the distribution area is added. The comprehensive operating cost includes the cost of energy storage cycle aging, the cost of photovoltaic curtailment loss and the cost of charging pile load adjustment compensation. The multi-objective problem is transformed into a single-objective optimization problem by weighted summation and solved by mixed integer linear programming or intelligent optimization algorithm.

[0105] In this embodiment, based on the multi-source operation data of the distribution substation in the current decision-making period, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed. This facilitates the subsequent solution of the dynamic assessment model of carrying capacity, and obtains the maximum optical-storage-charging access capacity of the distribution substation in the current decision-making period. This makes the assessed maximum optical-storage-charging access capacity more accurate, and further improves the assessment accuracy of the maximum optical-storage-charging access capacity of the distribution substation.

[0106] In an exemplary embodiment, step S103 above, which involves solving the dynamic evaluation model of carrying capacity to obtain the maximum available optical storage and charging capacity of the distribution substation in the current decision-making period, specifically includes the following: using a mixed integer linear programming algorithm or an intelligent optimization algorithm to solve the dynamic evaluation model of carrying capacity and obtain the model solution result; based on the model solution result, obtaining the maximum available optical storage and charging capacity of the distribution substation in the current decision-making period.

[0107] Among them, mixed integer linear programming algorithms include branch and bound method, cutting plane method, branch and cut method, etc.

[0108] Intelligent optimization algorithms include genetic algorithms, particle swarm optimization algorithms (such as particle swarm optimization algorithm and multi-objective particle swarm optimization algorithm), simulated annealing algorithm, etc.

[0109] The model solution result refers to the maximum available access capacity of the distribution radio area for photovoltaic storage and charging in the current decision-making cycle.

[0110] For example, the server uses a mixed-integer linear programming (MILP) algorithm to solve the dynamic evaluation model of carrying capacity and obtain the optimal solution of the model, which is used as the maximum optical storage and charging access capacity of the distribution area in the current decision cycle.

[0111] For example, the server uses the particle swarm optimization algorithm to solve the dynamic evaluation model of carrying capacity, obtains the optimal solution of the model, and uses the optimal solution of the model as the maximum optical storage and charging access capacity of the distribution radio area in the current decision cycle.

[0112] In this embodiment, a mixed integer linear programming algorithm or an intelligent optimization algorithm is used to solve the dynamic evaluation model of carrying capacity, which makes the obtained maximum optical storage and charging access capacity more accurate and further improves the evaluation accuracy of the maximum optical storage and charging access capacity of the distribution radio station area.

[0113] In an exemplary embodiment, step S103 above, which generates a target multi-device collaborative control strategy for the maximum available optical storage and charging capacity, specifically includes the following: based on the maximum available optical storage and charging capacity, obtaining multiple candidate multi-device collaborative control strategies for the maximum available optical storage and charging capacity, and the predicted probability of each candidate multi-device collaborative control strategy; selecting the candidate multi-device collaborative control strategy with the highest predicted probability from the multiple candidate multi-device collaborative control strategies; and obtaining the target multi-device collaborative control strategy for the maximum available optical storage and charging capacity based on the candidate multi-device collaborative control strategy with the highest predicted probability.

[0114] Among them, the target multi-device collaborative control strategy can refer to the candidate multi-device collaborative control strategy with the highest prediction probability.

[0115] For example, the server performs multi-device collaborative control strategy prediction processing based on the maximum accessible optical storage and charging capacity, obtaining multiple candidate multi-device collaborative control strategies for the maximum accessible optical storage and charging capacity, as well as the predicted probability of each candidate multi-device collaborative control strategy; for example, the maximum accessible optical storage and charging capacity is input into a pre-trained multi-device collaborative control strategy prediction model to obtain multiple candidate multi-device collaborative control strategies for the maximum accessible optical storage and charging capacity, as well as the predicted probability of each candidate multi-device collaborative control strategy; then, from the multiple candidate multi-device collaborative control strategies, the candidate multi-device collaborative control strategy with the highest predicted probability is selected; finally, the candidate multi-device collaborative control strategy with the highest predicted probability is taken as the target multi-device collaborative control strategy for the maximum accessible optical storage and charging capacity.

[0116] For example, the steps for generating a multi-device coordinated control strategy include: dividing the resources within the distribution area into four levels—rigid load, adjustable photovoltaic, adjustable charging pile, and energy storage system—based on device control priorities and physical response characteristics; prioritizing the use of the energy storage system for charging and discharging to smooth net load fluctuations, provided that power balance constraints and transformer non-reverse overload constraints are met; when the energy storage regulation capacity is insufficient, generating power reduction commands for adjustable charging piles or power reduction or shutdown commands for adjustable photovoltaic according to protocol priorities; the time resolution of the coordinated control strategy is 15 minutes or less, and includes time-by-time control commands for the next 24 hours.

[0117] In this embodiment, a target multi-device collaborative control strategy is generated for the maximum accessible capacity of photovoltaic, energy storage, and charging equipment. This facilitates the subsequent adjustment of the operating power of the photovoltaic, energy storage, and charging equipment in the distribution substation based on the target multi-device collaborative control strategy. This helps to fully utilize the operating efficiency of the photovoltaic, energy storage, and charging equipment in the distribution substation, thereby making full use of the power distribution resources in the distribution substation and improving the utilization rate of the power distribution resources in the distribution substation.

[0118] In an exemplary embodiment, step S104 above, adjusting the operating power of the optical storage and charging device through timing control commands, specifically includes the following: sending timing control commands to the distribution area's converged terminal through a preset communication protocol; the distribution area converged terminal is used to send the timing control commands to the controller of the optical storage and charging device, so that the controller adjusts the operating power of the optical storage and charging device based on the timing control commands.

[0119] The preset communication protocol can refer to the MQTT protocol.

[0120] Among them, the controller of photovoltaic, energy storage and charging equipment can refer to photovoltaic inverter, energy storage converter and charging pile controller.

[0121] Among them, the integrated terminal of the transformer area can refer to the centralized control terminal of the transformer area.

[0122] For example, the server sends timing control commands to the distribution area's converged terminal via a preset communication protocol. The converged terminal then forwards the received timing control commands to the controller of the photovoltaic-storage-charging device; the controller adjusts the operating power of the photovoltaic-storage-charging device based on the timing control commands. For instance, the converged terminal sends timing control commands for the distributed photovoltaic device to the controller of the distributed photovoltaic device, causing the controller to adjust the operating power of the distributed photovoltaic device based on the timing control commands.

[0123] In this embodiment, the operating power of the photovoltaic energy storage and charging equipment is adjusted by timing control commands, thereby achieving the purpose of coordinating the adjustment of the operating power of the photovoltaic energy storage and charging equipment in the distribution area. This is conducive to giving full play to the operating efficiency of the photovoltaic energy storage and charging equipment in the distribution area, making full use of the power distribution resources in the distribution area, and thus improving the power distribution resource utilization rate of the distribution area.

[0124] In one exemplary embodiment, such as Figure 3 As shown, another method for dynamically evaluating and improving the optical storage and charging capacity of a distribution network is provided. Taking the application of this method to a server as an example, the method specifically includes the following steps S301 to S310. Wherein:

[0125] Step S301: Obtain historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution area; obtain historical and current user load data of the distribution area; and obtain meteorological element forecast data for future periods.

[0126] Step S302 involves fusing historical operating data, current operating data, historical user load data, current user load data, and meteorological element forecast data for future periods to obtain multi-source operating data of the distribution station area in the current decision-making cycle.

[0127] Step S303: Based on the multi-source operation data of the distribution substation in the current decision-making cycle, determine the uncertainty characterization parameters of source-load prediction, the model optimization objective, and the opportunity constraints.

[0128] Step S304: Based on the source load prediction uncertainty characterization parameters, model optimization objectives, and chance constraints, construct an optimization evaluation model; based on the optimization evaluation model, obtain a dynamic evaluation model of the carrying capacity of the distribution substation considering the source load prediction uncertainty.

[0129] Step S305: Use a mixed integer linear programming algorithm or an intelligent optimization algorithm to solve the dynamic evaluation model of carrying capacity and obtain the model solution results; based on the model solution results, obtain the maximum optical storage charging access capacity of the distribution radio area in the current decision cycle.

[0130] Step S306: Based on the maximum accessible optical storage and charging capacity, obtain multiple candidate multi-device collaborative control strategies for the maximum accessible optical storage and charging capacity, as well as the predicted probability of each candidate multi-device collaborative control strategy.

[0131] Step S307: Select the candidate multi-device collaborative control strategy with the highest predicted probability from multiple candidate multi-device collaborative control strategies; based on the candidate multi-device collaborative control strategy with the highest predicted probability, obtain the target multi-device collaborative control strategy for the maximum available optical storage and charging capacity.

[0132] Step S308: Generate timing control commands for the optical storage and charging equipment in the distribution area according to the target multi-device collaborative control strategy.

[0133] Step S309: The timing control command is sent to the distribution area convergence terminal through a preset communication protocol; the distribution area convergence terminal is used to send the timing control command to the controller of the optical storage and charging equipment, so that the controller adjusts the operating power of the optical storage and charging equipment based on the timing control command.

[0134] Step S310: Obtain multi-source operation data of the distribution substation in the next decision cycle of the current decision cycle, use the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jump to the step of determining the source-load prediction uncertainty characterization parameters, model optimization objectives and chance constraints based on the multi-source operation data of the distribution substation in the current decision cycle, until the preset evaluation termination condition is reached.

[0135] In the aforementioned dynamic assessment and improvement method for the photovoltaic-storage-charging (PV-SCDMA) carrying capacity of a distribution network, when assessing the PV-SCDMA carrying capacity, a dynamic assessment model considering the uncertainty of source load prediction is first constructed based on the multi-source operational data of the distribution network in the current decision-making period. This model is then solved to obtain the maximum PV-SCDMA-charging capacity that can be accessed in the current decision-making period. In other words, by comprehensively considering the multi-source operational data of the distribution network in the current decision-making period and using the dynamic assessment model considering the uncertainty of source load prediction, the maximum PV-SCDMA-charging capacity that can be accessed in the current decision-making period is assessed. Furthermore, dynamic assessments are performed for each decision-making period. This allows for a more accurate assessment of the maximum accessible photovoltaic (PV) storage and charging capacity, thereby improving the accuracy of the assessment. Furthermore, by generating timing control commands for the PV storage and charging equipment in the distribution substation according to the target multi-device collaborative control strategy for the maximum accessible PV storage and charging capacity, and adjusting the operating power of the PV storage and charging equipment through these commands, the aim of adjusting the operating power of the PV storage and charging equipment in the distribution substation based on the target multi-device collaborative control strategy for the maximum accessible PV storage and charging capacity is achieved. This helps to fully utilize the operating efficiency of the PV storage and charging equipment in the distribution substation, thereby making full use of the distribution resources in the distribution substation and improving the utilization rate of the distribution resources.

[0136] In one exemplary embodiment, this application also provides a dynamic evaluation and improvement system for the photovoltaic storage and charging carrying capacity of a distribution network, specifically including:

[0137] Data acquisition module: used to acquire multi-source operation data of the distribution area. The multi-source operation data includes at least: real-time and historical output sequences of distributed photovoltaic, real-time and historical power sequences of user loads, state of charge and charge / discharge power boundaries of energy storage systems, real-time operation status and set parameters of charging piles, and meteorological element forecast data for the corresponding time period.

[0138] Model building module: Based on the multi-source operation data, it is used to build a dynamic assessment model of carrying capacity that takes into account the uncertainty of source load prediction. The model quantifies the prediction uncertainty of photovoltaic output and load demand into a probability distribution and transforms the safe operation constraints of the distribution substation into opportunity constraints.

[0139] Model Solving Module: Used to solve the dynamic evaluation model of carrying capacity, obtain the maximum photovoltaic, energy storage and charging access capacity of the distribution radio area within the current decision period, and simultaneously generate a multi-device collaborative control strategy to improve the carrying capacity. The collaborative control strategy includes a sequence of timing control instructions for the charging and discharging power of the energy storage system, the active power output of the photovoltaic inverter and the charging power of the charging pile.

[0140] Dynamic assessment and control module: It is used to repeat the above steps in each decision cycle according to the preset rolling time domain optimization cycle, and distribute the latest solved collaborative control strategy to each controllable device through the substation fusion terminal for execution, so as to dynamically update the carrying capacity assessment results of the substation and form a closed-loop control.

[0141] The aforementioned dynamic assessment and enhancement system for the photovoltaic, energy storage, and charging carrying capacity of distribution substations improves the accuracy of assessing the maximum accessible photovoltaic, energy storage, and charging capacity of distribution substations, and also improves the utilization rate of power distribution resources in distribution substations.

[0142] 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 in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0143] Based on the same inventive concept, this application also provides a device for dynamically evaluating and improving the optical-storage-charging capacity of a distribution network, used to implement the aforementioned method for dynamically evaluating and improving the optical-storage-charging capacity of a distribution network. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for dynamically evaluating and improving the optical-storage-charging capacity of a distribution network provided below can be found in the limitations of the method for dynamically evaluating and improving the optical-storage-charging capacity of a distribution network described above, and will not be repeated here.

[0144] In one exemplary embodiment, such as Figure 4 As shown, a dynamic evaluation and improvement device 400 for the photovoltaic, energy storage, and charging carrying capacity of a distribution network is provided, comprising: a data acquisition module 401, a model building module 402, a strategy generation module 403, an equipment control module 404, and a loop processing module 405, wherein:

[0145] The data acquisition module 401 is used to acquire multi-source operating data of the distribution radio area during the current decision-making cycle.

[0146] The model building module 402 is used to build a dynamic assessment model of the carrying capacity of the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operation data of the distribution substation in the current decision-making cycle.

[0147] The strategy generation module 403 is used to solve the dynamic evaluation model of carrying capacity, obtain the maximum available access capacity of the distribution radio area in the current decision cycle, and generate a target multi-device collaborative control strategy for the maximum available access capacity of the distribution radio area.

[0148] The equipment control module 404 is used to generate timing control commands for the optical storage and charging equipment in the distribution area according to the target multi-device collaborative control strategy, and adjust the operating power of the optical storage and charging equipment through the timing control commands.

[0149] The loop processing module 405 is used to acquire the multi-source operation data of the distribution substation in the next decision cycle of the current decision cycle, use the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jump to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operation data of the distribution substation in the current decision cycle, until the preset assessment termination condition is reached.

[0150] In an exemplary embodiment, the data acquisition module 401 is further configured to acquire historical and current operating data of the photovoltaic storage and charging equipment in the distribution radio station area, historical and current user load data of the distribution radio station area, and meteorological element forecast data for future periods; and to perform fusion processing on the historical operating data, current operating data, historical user load data, current user load data and meteorological element forecast data for future periods to obtain multi-source operating data of the distribution radio station area in the current decision-making cycle.

[0151] In an exemplary embodiment, the model building module 402 is further configured to determine the source-load prediction uncertainty characterization parameters, model optimization objectives, and opportunity constraints based on the multi-source operation data of the distribution substation in the current decision-making cycle; construct an optimization evaluation model based on the source-load prediction uncertainty characterization parameters, model optimization objectives, and opportunity constraints; and obtain a dynamic evaluation model of the carrying capacity of the distribution substation considering the source-load prediction uncertainty based on the optimization evaluation model.

[0152] In an exemplary embodiment, the strategy generation module 403 is further configured to use a mixed integer linear programming algorithm or an intelligent optimization algorithm to solve the dynamic evaluation model of carrying capacity and obtain the model solution result; based on the model solution result, the maximum optical storage and charging access capacity of the distribution radio area in the current decision cycle is obtained.

[0153] In an exemplary embodiment, the strategy generation module 403 is further configured to obtain multiple candidate multi-device collaborative control strategies for the maximum optical storage and charging access capacity based on the maximum optical storage and charging access capacity, and the predicted probability of each candidate multi-device collaborative control strategy; select the candidate multi-device collaborative control strategy with the highest predicted probability from the multiple candidate multi-device collaborative control strategies; and obtain the target multi-device collaborative control strategy for the maximum optical storage and charging access capacity based on the candidate multi-device collaborative control strategy with the highest predicted probability.

[0154] In an exemplary embodiment, the device control module 404 is further configured to send timing control commands to the distribution area's converged terminal via a preset communication protocol; the distribution area converged terminal is configured to send the timing control commands to the controller of the optical storage and charging device, so that the controller adjusts the operating power of the optical storage and charging device based on the timing control commands.

[0155] Each module in the aforementioned dynamic evaluation and enhancement device for the optical storage and charging carrying capacity of the distribution area can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0156] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores data such as the maximum accessible optical storage and charging capacity and target multi-device collaborative control strategies. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for dynamically evaluating and improving the optical storage and charging carrying capacity of a distribution network.

[0157] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0158] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0159] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0160] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for dynamic evaluation and improvement of the optical storage and charging carrying capacity of a distribution network area, characterized in that, The method includes: Acquire multi-source operational data of the distribution radio area during the current decision-making cycle; Based on the multi-source operation data of the distribution substation in the current decision-making cycle, a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction is constructed. Solve the dynamic evaluation model of the carrying capacity to obtain the maximum access capacity of the distribution radio area for optical storage and charging in the current decision period, and generate a target multi-device collaborative control strategy for the maximum access capacity of optical storage and charging. According to the target multi-device collaborative control strategy, a timing control command is generated for the optical storage and charging equipment in the distribution area, and the operating power of the optical storage and charging equipment is adjusted through the timing control command; The process involves acquiring multi-source operational data of the distribution substation in the next decision cycle of the current decision cycle, using the multi-source operational data of the next decision cycle as the multi-source operational data of the current decision cycle, and then proceeding to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operational data of the distribution substation in the current decision cycle, until a preset assessment termination condition is met.

2. The method according to claim 1, characterized in that, The acquisition of multi-source operational data of the distribution substation in the current decision-making cycle includes: Acquire historical and current operating data of the photovoltaic, energy storage and charging equipment in the distribution area; acquire historical and current user load data of the distribution area; and acquire meteorological element forecast data for future periods. The historical operating data, the current operating data, the historical user load data, the current user load data, and the meteorological element forecast data for future periods are fused to obtain the multi-source operating data of the distribution area in the current decision-making cycle.

3. The method according to claim 1, characterized in that, The method of constructing a dynamic capacity assessment model for the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operational data of the distribution substation in the current decision-making cycle, includes: Based on the multi-source operation data of the distribution substation in the current decision-making period, determine the uncertainty characterization parameters of source load prediction, the model optimization objective, and the opportunity constraints. Based on the source load prediction uncertainty characterization parameters, the model optimization objective, and the opportunity constraints, an optimization evaluation model is constructed. Based on the optimized evaluation model, a dynamic evaluation model for the carrying capacity of the distribution substation considering the uncertainty of source load prediction is obtained.

4. The method according to claim 1, characterized in that, Solving the dynamic assessment model of the carrying capacity to obtain the maximum available optical storage and charging capacity of the distribution radio area in the current decision period includes: The dynamic evaluation model of carrying capacity is solved using a mixed-integer linear programming algorithm or an intelligent optimization algorithm to obtain the model solution results; Based on the solution results of the model, the maximum available access capacity of the distribution radio area for optical storage and charging in the current decision period is obtained.

5. The method according to claim 1, characterized in that, The generation of a target multi-device collaborative control strategy for the maximum accessible optical storage and charging capacity includes: Based on the maximum accessible capacity of optical storage and charging, multiple candidate multi-device collaborative control strategies for the maximum accessible capacity of optical storage and charging are obtained, as well as the predicted probability of each candidate multi-device collaborative control strategy. From the multiple candidate multi-device collaborative control strategies, the candidate multi-device collaborative control strategy with the highest predicted probability is selected; Based on the candidate multi-device collaborative control strategy with the highest predicted probability, a target multi-device collaborative control strategy for the maximum available optical storage and charging capacity is obtained.

6. The method according to any one of claims 1 to 5, characterized in that, Adjusting the operating power of the optical storage and charging device through the timing control command includes: The timing control command is sent to the distribution area's converged terminal via a preset communication protocol; the converged terminal is used to send the timing control command to the controller of the optical storage and charging equipment, so that the controller adjusts the operating power of the optical storage and charging equipment based on the timing control command.

7. A dynamic evaluation and improvement device for the optical storage and charging carrying capacity of a distribution station area, characterized in that, The device includes: The data acquisition module is used to acquire multi-source operational data of the distribution radio area during the current decision-making cycle; The model building module is used to build a dynamic assessment model of the carrying capacity of the distribution substation, taking into account the uncertainty of source load prediction, based on the multi-source operation data of the distribution substation in the current decision-making cycle. The strategy generation module is used to solve the dynamic evaluation model of the carrying capacity to obtain the maximum optical storage and charging access capacity of the distribution radio area in the current decision period, and generate a target multi-device collaborative control strategy for the maximum optical storage and charging access capacity. The equipment control module is used to generate timing control commands for the optical storage and charging equipment in the distribution area according to the target multi-device collaborative control strategy, and adjust the operating power of the optical storage and charging equipment through the timing control commands; The loop processing module is used to acquire the multi-source operation data of the distribution substation in the next decision cycle of the current decision cycle, use the multi-source operation data of the next decision cycle as the multi-source operation data of the current decision cycle, and jump to the step of constructing a dynamic assessment model of the carrying capacity of the distribution substation considering the uncertainty of source load prediction based on the multi-source operation data of the distribution substation in the current decision cycle, until the preset assessment termination condition is reached.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images