Distributed photovoltaic distribution network access method and system

Abstract

The invention relates to the technical field of photovoltaic power distribution, and specifically discloses a distributed photovoltaic distribution network access method and system, the method comprising: based on weather forecast data of each distributed photovoltaic component in the distributed photovoltaic distribution network, predicting the power generation data of each photovoltaic component in the future short period; based on the historical power consumption data of all distributed power grid loads under each division fineness, predicting the power consumption data of each minimum unit distributed power grid load in the distributed photovoltaic distribution network in the future short period; based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period and the ring network structure of the photovoltaic distribution network, updating the current access strategy of the distributed photovoltaic distribution network, obtaining the latest access control result of the distributed photovoltaic distribution network, so as to ensure the stability and reliability of power supply.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic power distribution technology, and in particular to a distributed photovoltaic power distribution network access method and system. Background Art

[0002] Distributed photovoltaic power grid is a power system that uses solar energy to generate electricity and distributes and consumes electricity nearby. At present, with the large-scale access of distributed photovoltaic power grids, new requirements have been put forward for the planning, operation and management of power grids. Distributed photovoltaic power grids can not only transmit electricity to the power grid (that is, the surplus electricity is connected to the grid when the power generation is greater than the power consumption of the local load), but also absorb electricity from the power grid (such as at night or when there is insufficient light), which forms a two-way power flow. The power grid needs to grasp the power generation power of distributed photovoltaic power sources and the power demand of local loads in real time in order to carry out effective power balance and scheduling. The traditional power grid scheduling mode is mainly designed for unidirectional power flow, which is difficult to adapt to the bidirectional power flow characteristics of distributed photovoltaic power grids. This requires the establishment of a new intelligent grid scheduling system that can collect information on distributed photovoltaic power sources and loads in real time, use advanced prediction algorithms (such as power prediction models based on artificial intelligence) to predict photovoltaic power generation power and load demand, and formulate reasonable scheduling strategies based on the prediction results to ensure the safe and stable operation of the power grid under the condition of bidirectional power flow. For example, during the peak period of photovoltaic power generation in the day, the output of other power sources is reasonably arranged to give priority to the consumption of distributed photovoltaic power generation; at night or when photovoltaic power generation is insufficient, the power supply strategy of the grid is adjusted in a timely manner to meet the electricity needs of users.

[0003] Under the current technical conditions, the access to distributed photovoltaic distribution networks usually considers the power generation of photovoltaic modules and the power demand of grid loads. However, due to the large number of distributed photovoltaic power sources, their wide distribution, and the randomness and intermittency of power generation, it is very difficult to accurately predict their power generation. The accuracy and refinement of the prediction and analysis of the power generation of photovoltaic modules and the power demand of grid loads need to be improved. Furthermore, due to the lack of prediction of power generation and power consumption, the access strategy of the distribution network cannot be effectively updated in time according to the actual situation, and the optimal access control cannot be achieved.

[0004] Therefore, the present invention proposes a distributed photovoltaic distribution network access method and system. Summary of the invention

[0005] The present invention provides a distributed photovoltaic distribution network access method and system, which is used to predict power generation data based on weather forecast data at the location of each distributed photovoltaic component, and can fully consider the impact of weather differences in different geographical locations on photovoltaic power generation, so that the power generation prediction is more accurate and precise. And based on the historical power consumption data of the distributed power grid load under each division fineness, the power consumption data in the future short period is predicted, which improves the accuracy and reliability of the power consumption prediction and provides a reliable basis for the subsequent access strategy update. The access strategy is updated by comprehensively considering the power generation data of the photovoltaic components, the power consumption data of the power grid load, and the ring network structure of the distribution network, so as to achieve comprehensive optimization of the access to the distributed photovoltaic distribution network. This access method helps to improve the energy utilization efficiency of the distributed photovoltaic distribution network and ensure the stability and reliability of the power supply. At the same time, it can better adapt to the changes in the power grid load, reduce the power grid operation cost, and promote the effective integration and utilization of distributed photovoltaic energy.

[0006] The present invention provides a distributed photovoltaic power distribution network access method, comprising:

[0007] S1: Based on the weather forecast data of each distributed photovoltaic module in the distributed photovoltaic distribution network, the power generation data of each photovoltaic module in the future short period is predicted;

[0008] S2: Based on the historical power consumption data of all distributed power grid loads at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted;

[0009] S3: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control result of the distributed photovoltaic distribution network.

[0010] Preferably, the distributed photovoltaic distribution network access method, S1: based on the weather forecast data of the location of each distributed photovoltaic component in the distributed photovoltaic distribution network, predicting the power generation data of each photovoltaic component in the future short period, including:

[0011] Obtain weather forecast data for the location of each distributed photovoltaic component in the distributed photovoltaic distribution network in the short term in the future;

[0012] Extracting the time series variation information of all information items affecting power generation prediction from the weather forecast data;

[0013] The time series change information of all power generation prediction influencing information items is input into the power generation time series data prediction model to obtain the power generation data of each photovoltaic module in the future short period.

[0014] Preferably, the distributed photovoltaic distribution network access method, S2: based on the historical power consumption data of all distributed power grid loads at each division level, predicting the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period, including:

[0015] S201: predicting the power consumption data of each distributed power grid load at each division level in a short period in the future based on the historical power consumption data of all distributed power grid loads at each division level;

[0016] S202: Determine the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level;

[0017] S203: Evaluate the power prediction reliability of the power consumption data of each distributed power grid load in the future short period at each division level relative to each minimum unit of distributed power grid load included in the corresponding distributed power grid load;

[0018] S204: Based on the power consumption data of each distributed power grid load at each division level in the future short period, the power consumption data of each distributed power grid load at each division level in the future short period relative to the power prediction reliability of each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted.

[0019] Preferably, the distributed photovoltaic distribution network access method, S202: determining the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, comprises:

[0020] Based on the historical power consumption data of all distributed power grid loads at each division level, the historical power consumption data of each minimum unit of distributed power grid load is determined;

[0021] The ratio of the power consumption at each historical moment in the historical power consumption data of each minimum unit of distributed power grid load to the power consumption at the same historical moment in the historical power consumption data of the distributed power grid load to which it belongs at each division level is taken as the power consumption ratio of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level at the corresponding moment;

[0022] The average value of the proportion of power consumption of each minimum unit of distributed power grid load in the distributed power grid load at each division level at all historical moments is taken as the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load at each division level.

[0023] Preferably, the distributed photovoltaic distribution network access method, S203: evaluating the power prediction reliability of the power consumption data of each distributed power grid load in each division level in the future short period relative to each minimum unit of the distributed power grid load contained in the corresponding distributed power grid load, including:

[0024] The reciprocal of the total number of minimum unit distributed grid loads contained in the distributed grid loads to which each minimum unit distributed grid load belongs at each division level is taken as the power prediction reliability of the power consumption data of each distributed grid load at each division level in the future short period relative to each minimum unit distributed grid load contained in the corresponding distributed grid load.

[0025] Preferably, the distributed photovoltaic distribution network access method, S204: based on the power consumption data of each distributed power grid load at each division level in the future short period, the power consumption data of each distributed power grid load at each division level in the future short period relative to the power prediction reliability of each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period, including:

[0026] The average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption at each future moment contained in the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level in the future short period, and the power prediction reliability of the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level relative to the corresponding minimum unit of distributed power grid load are taken as the predicted power consumption at each future moment determined by each minimum unit of distributed power grid load based on the distributed power grid load to which it belongs at each division level;

[0027] The average value of the predicted power consumption at the same future moment determined by the distributed power grid loads of each minimum unit based on all the distributed power grid loads at all the division levels is regarded as the final predicted power consumption of each minimum unit distributed power grid load at the corresponding future moment;

[0028] The final predicted power consumption of each minimum unit of distributed power grid load at all future moments in the future short period is regarded as the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period.

[0029] Preferably, the distributed photovoltaic distribution network access method, S3: based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control result of the distributed photovoltaic distribution network, including:

[0030] Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the current access strategy of the distributed photovoltaic distribution network is reasonable. If so, the current access strategy is retained as the latest access control result of the distributed photovoltaic distribution network;

[0031] Otherwise, all accessible photovoltaic components and all accessible loads of each access point in the photovoltaic distribution network are determined based on the ring network structure of the photovoltaic distribution network;

[0032] Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the short future cycle, the power consumption data of all the smallest units of distributed power grid loads in the short future cycle, and all accessible photovoltaic modules and all accessible loads at each access point in the photovoltaic distribution network, the latest access strategy of the distributed photovoltaic distribution network is generated;

[0033] Based on the latest access strategy of the distributed photovoltaic distribution network, the access adjustment control of the distributed photovoltaic distribution network is carried out to obtain the latest access control result of the distributed photovoltaic distribution network.

[0034] Preferably, the distributed photovoltaic distribution network access method determines whether the current access strategy of the distributed photovoltaic distribution network is reasonable based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period, including:

[0035] Based on the current access strategy of the distributed photovoltaic distribution network, all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network and all the smallest units of distributed grid loads are determined;

[0036] Based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the power generation data of all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network meets the power consumption data of all the smallest units of distributed power grid loads currently connected to the corresponding access point in the future short period. If so, it is determined that the current access strategy of the distributed photovoltaic distribution network is reasonable; otherwise, it is determined that the current access strategy of the distributed photovoltaic distribution network is unreasonable.

[0037] Preferably, the distributed photovoltaic distribution network access method generates the latest access strategy of the distributed photovoltaic distribution network based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, as well as all accessible photovoltaic components and all accessible loads at each access point in the photovoltaic distribution network, including:

[0038] Obtain access strategy generation model;

[0039] The power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and all accessible photovoltaic components and all accessible loads at each access point in the photovoltaic distribution network are input into the access strategy generation model to generate the latest access strategy for the distributed photovoltaic distribution network.

[0040] The present invention provides a distributed photovoltaic distribution network access system, which is used to execute any of the above distributed photovoltaic distribution network access methods, including:

[0041] The power generation data prediction module is used to predict the power generation data of each photovoltaic component in the future short period based on the weather forecast data of the location of each distributed photovoltaic component in the distributed photovoltaic distribution network;

[0042] The power consumption data prediction module is used to predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period based on the historical power consumption data of all distributed power grid loads at each division level;

[0043] The grid structure optimization module is used to update the current access strategy of the distributed photovoltaic distribution network based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, and obtain the latest access control results of the distributed photovoltaic distribution network.

[0044] The beneficial effects of the present invention compared to the prior art are as follows: by predicting the power generation data based on the weather forecast data at the location of each distributed photovoltaic component, the influence of weather differences in different geographical locations on photovoltaic power generation can be fully considered, making the power generation prediction more accurate and precise. And based on the historical power consumption data of the distributed power grid load at each division level, the power consumption data in the future short period is predicted, which improves the accuracy and reliability of the power consumption prediction and provides a reliable basis for the subsequent access strategy update. The access strategy is updated by comprehensively considering the power generation data of the photovoltaic components, the power consumption data of the power grid load, and the ring network structure of the distribution network, realizing the comprehensive optimization of the access to the distributed photovoltaic distribution network. This access method helps to improve the energy utilization efficiency of the distributed photovoltaic distribution network and ensure the stability and reliability of the power supply. At the same time, it can better adapt to the changes in the power grid load, reduce the operating cost of the power grid, and promote the effective integration and utilization of distributed photovoltaic energy.

[0045] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in this application document.

[0046] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 is a flow chart of a distributed photovoltaic distribution network access method in an embodiment of the present invention;

[0049] Figure 2is a flowchart of a specific execution method of step S2 in an embodiment of the present invention;

[0050] Figure 3 Schematic diagram of a distributed photovoltaic power distribution network access system in an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0052] Example 1

[0053] The present invention provides a distributed photovoltaic power distribution network access method, referring to Figure 1 ,include:

[0054] S1: Based on the weather forecast data of each distributed photovoltaic module in the distributed photovoltaic distribution network, the power generation data of each photovoltaic module in the future short period is predicted;

[0055] S2: Based on the historical power consumption data of all distributed power grid loads at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted;

[0056] S3: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control result of the distributed photovoltaic distribution network.

[0057] In this embodiment, the distributed photovoltaic assembly refers to a combination of photovoltaic cell units that are dispersedly installed at different locations and generate electricity independently. For example, photovoltaic panels installed on different roofs of a community are distributed photovoltaic assemblies.

[0058] In this embodiment, the weather forecast data is information about future weather conditions in a specific area, including temperature, light intensity, cloud conditions, etc. For example, data such as the maximum temperature and sunshine duration of each day in a certain area in the next week.

[0059] In this embodiment, the future short period is a relatively short future time period, such as a future day, a week, or a month.

[0060] In this embodiment, the power generation data refers to the power value of the photovoltaic module generating electric energy per unit time. For example, the power generation power of a distributed photovoltaic module at a certain moment is 5 kilowatts.

[0061] In this embodiment, the division fineness refers to the degree of detail when classifying or dividing the distributed power grid loads. For example, the division can be made in different levels according to standards such as power consumption areas.

[0062] In this embodiment, the distributed power grid load refers to the power demand of power-consuming equipment or users dispersed in various places of the power grid, such as the power load of multiple factories and residential areas dispersed in different locations.

[0063] In this embodiment, the historical power consumption data is the power consumption record of the distributed power grid load in the past period of time, such as the power consumption data of a factory every month in the past year.

[0064] In this embodiment, the power consumption data refers to the power consumption value at a specific time or time period. For example, the power consumption of a distributed power grid load at the current time is 10 kilowatts.

[0065] In this embodiment, the current access strategy refers to the connection and power supply mode of photovoltaic components and loads based on different access points in the current distributed photovoltaic distribution network.

[0066] In this embodiment, the latest access control result is the final result obtained after adjusting the access mode of the distributed photovoltaic distribution network (i.e., the connection mode of photovoltaic components and loads with access points respectively) based on the latest power generation and consumption data and factors such as the grid structure.

[0067] The beneficial effects of the above technology are: by predicting the power generation data based on the weather forecast data at the location of each distributed photovoltaic component, the impact of weather differences in different geographical locations on photovoltaic power generation can be fully considered, making the power generation prediction more accurate and precise. And based on the historical power consumption data of the distributed power grid load at each division level, the power consumption data in the future short period is predicted, which improves the accuracy and reliability of the power consumption prediction and provides a reliable basis for the subsequent access strategy update. The access strategy is updated by comprehensively considering the power generation data of the photovoltaic components, the power consumption data of the power grid load, and the ring network structure of the distribution network, realizing the comprehensive optimization of the access to the distributed photovoltaic distribution network. This access method helps to improve the energy utilization efficiency of the distributed photovoltaic distribution network and ensure the stability and reliability of the power supply. At the same time, it can better adapt to the changes in the power grid load, reduce the operating cost of the power grid, and promote the effective integration and utilization of distributed photovoltaic energy.

[0068] Example 2

[0069] Based on Example 1, a distributed photovoltaic distribution network access method, S1: based on the weather forecast data of the location of each distributed photovoltaic component in the distributed photovoltaic distribution network, predicting the power generation data of each photovoltaic component in the future short period, including:

[0070] Obtain weather forecast data for the location of each distributed photovoltaic component in the distributed photovoltaic distribution network in the short term in the future;

[0071] Extracting the time series variation information of all information items affecting power generation prediction from the weather forecast data;

[0072] The time series change information of all power generation prediction influencing information items is input into the power generation time series data prediction model to obtain the power generation data of each photovoltaic module in the future short period.

[0073] In this embodiment, the power generation prediction influencing information items refer to specific factors or parameters that can affect the prediction of power generation, such as light intensity, temperature, weather conditions, etc.

[0074] In this embodiment, the time series variation information of the information items influencing power prediction is the variation of the above-mentioned information items at different time points, for example, the light intensity variation data at different times of the day, the temperature variation in different seasons, etc.

[0075] In this embodiment, the power generation time series data prediction model is a mathematical model used to predict future power generation based on historical data and time series change information of related influencing factors. It may be based on statistics, machine learning or other related technologies, and obtain the predicted value of future power generation by analyzing and calculating various input information. The power generation time series data prediction model is usually obtained based on training samples including the following types:

[0076] A large amount of historical power generation data, covering different weather conditions (such as sunny, cloudy, rainy, etc.), seasons (spring, summer, autumn, and winter), and time periods (day and night). These data form a time series, reflecting the change pattern of power generation over time;

[0077] At the same time, it also includes historical data of various weather factors related to power generation, such as light intensity data, temperature data, humidity data, wind speed data, etc. at different times.

[0078] The beneficial effects of the above technology are: accurately obtain the weather forecast data for each distributed photovoltaic component location in the short future period, ensuring the accuracy and pertinence of the data source. Extract the time series change information of the information items affecting the power generation prediction from the weather forecast data, and effectively screen and extract the key influencing factors. Input these time series change information into the power generation time series data prediction model, and use the powerful analysis ability of the model to obtain the power generation data of each photovoltaic component in the short future period, which improves the scientificity and accuracy of the prediction. This method can fully take into account various factors that affect the power generation, making the prediction results more reliable. It helps to make power allocation and planning in advance and improve the operating efficiency and stability of the distributed photovoltaic distribution network. At the same time, it provides accurate data support for optimizing access strategies and promotes the rational allocation and effective use of energy.

[0079] Example 3

[0080] Based on Example 1, a distributed photovoltaic distribution network access method, S2: based on the historical power consumption data of all distributed power grid loads at each division level, predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period, refer to Figure 2 ,include:

[0081] S201: predicting the power consumption data of each distributed power grid load at each division level in a short period in the future based on the historical power consumption data of all distributed power grid loads at each division level;

[0082] S202: Determine the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level;

[0083] S203: Evaluate the power prediction reliability of the power consumption data of each distributed power grid load in the future short period at each division level relative to each minimum unit of distributed power grid load included in the corresponding distributed power grid load;

[0084] S204: Based on the power consumption data of each distributed power grid load at each division level in the future short period, the power consumption data of each distributed power grid load at each division level in the future short period relative to the power prediction reliability of each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted.

[0085] In this embodiment, based on the historical power consumption data of all distributed power grid loads at each division level, predicting the power consumption data of each distributed power grid load at each division level in the short term in the future means using past power consumption data to infer the power consumption of each distributed power grid load in the short term in the future at the same division level according to different division levels. For example, the power grid load is divided into different levels according to the power consumption area, and the power consumption of each area in the short term in the future is predicted based on the power consumption of each area in the past. The prediction process can be achieved in the following ways:

[0086] 1. Establish a mathematical model: For example, use linear regression, time series analysis, neural network and other methods, take historical power consumption data as input, and construct a mathematical expression or model structure that can reflect its changing rules.

[0087] 2. Consider multiple influencing factors: In addition to the historical power consumption data itself, other factors that may affect power consumption need to be included. For example, for industrial power consumption, new orders and production equipment upgrades need to be considered; for residential power consumption, seasonal changes and holiday factors need to be considered.

[0088] 3. Update data in real time: Continuously collect new electricity consumption data and incorporate it into the model for retraining and optimization so that the model can adapt to the latest electricity consumption trends and regular changes.

[0089] 4. Cross-validation and model evaluation: Use a variety of evaluation indicators (such as mean square error, mean absolute error, etc.) to evaluate the prediction model, and select the optimal model parameters and structure through cross-validation and other techniques.

[0090] 5. Combining expert experience: Combine the experience and knowledge of experts in the power field to revise and adjust the forecast results to improve accuracy. For example, for the power consumption forecast of an industrial park, it is known that the power consumption in each month of the past summer has been gradually increasing, and has a significant relationship with the number of newly started enterprises and temperature in the park. By establishing a multivariate linear regression model that includes these factors and continuously updating the model parameters with new data. When predicting the power consumption in the future short period (such as the next month), the current number of newly started enterprises and temperature forecast values ​​are first substituted into the model, and then experts make appropriate adjustments based on recent special circumstances (such as partial shutdown of large-scale enterprise equipment maintenance) to obtain more accurate forecast results.

[0091] In this embodiment, the minimum unit of distributed power grid load refers to the most basic power consumption unit that cannot be further subdivided when the distributed power grid load is subdivided, for example, the power consumption load constituted by a single household user or a specific power consumption device.

[0092] In this embodiment, the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level refers to the historical average proportion of the power consumption of each most basic power consumption unit in the total distributed power grid load corresponding to different division levels. For example, at a certain level of division according to region, the average proportion of the historical power consumption of a household user to the total power consumption of the region.

[0093] In this embodiment, the power prediction reliability indicates the reliability of the prediction result obtained when predicting the power consumption data of a single minimum unit of distributed power grid load contained therein based on the power consumption data of the distributed power grid load in a short future period.

[0094] The beneficial effects of the above technology are as follows: Step S201 predicts the future short-term power consumption data of each distributed power grid load at each division level based on the historical power consumption data, providing basic data for subsequent detailed analysis. Step S202 determines the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs, which helps to understand its relative position in the whole. Step S203 evaluates the power prediction reliability of the power consumption data at each division level relative to each minimum unit, thereby improving the accuracy and credibility of the prediction. Step S204 comprehensively considers the above-mentioned multiple factors to predict the power consumption data of each minimum unit of distributed power grid load, making the prediction results more comprehensive, accurate and reliable. This comprehensive and detailed prediction method can better adapt to the complex changes in the load in the distributed photovoltaic distribution network, and provide accurate data support for the access strategy of the distribution network. It helps to optimize the allocation of power resources, improve the stability and economy of power grid operation, ensure the quality and reliability of power supply, and promote the efficient integration and utilization of distributed photovoltaic energy in the distribution network.

[0095] Example 4

[0096] Based on Example 3, the distributed photovoltaic distribution network access method, S202: determining the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, includes:

[0097] Based on the historical power consumption data of all distributed power grid loads at each division level, the historical power consumption data of each minimum unit of distributed power grid load is determined;

[0098] The ratio of the power consumption at each historical moment in the historical power consumption data of each minimum unit of distributed power grid load to the power consumption at the same historical moment in the historical power consumption data of the distributed power grid load to which it belongs at each division level is taken as the power consumption ratio of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level at the corresponding moment;

[0099] The average value of the proportion of power consumption of each minimum unit of distributed power grid load in the distributed power grid load at each division level at all historical moments is taken as the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load at each division level.

[0100] In this embodiment, since the division detail must include the degree of division that can divide the distributed power grid load into the most detailed (i.e., smallest unit) division, the historical power consumption data of each smallest unit of the distributed power grid load can be determined based on the historical power consumption data of all distributed power grid loads at each division detail.

[0101] The beneficial effects of the above technology are: based on the historical power consumption data, the historical power consumption data of each minimum unit of distributed power grid load is determined, providing an accurate data basis for the subsequent calculation of the proportion. By calculating the power consumption ratio at each historical moment, the power consumption ratio of each minimum unit of distributed power grid load at the corresponding moment is obtained, and a detailed analysis of the proportion at different moments is achieved. The power consumption ratios of all historical moments are averaged to obtain the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, making the proportion results more representative and stable. This calculation method can accurately and comprehensively determine the average power proportion, providing an important reference for the subsequent prediction of the power consumption data of the distributed power grid load. It helps to more accurately evaluate the power consumption of each minimum unit of distributed power grid load, optimize the allocation of power resources, improve the rationality and effectiveness of the access to the distributed photovoltaic distribution network, and ensure the stable operation and efficient utilization of the power grid.

[0102] Example 5

[0103] Based on Example 3, the distributed photovoltaic distribution network access method, S203: evaluating the power prediction reliability of each distributed power grid load in a future short period under each division level relative to each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, including:

[0104] The reciprocal of the total number of minimum unit distributed grid loads contained in the distributed grid loads to which each minimum unit distributed grid load belongs at each division level is taken as the power prediction reliability of the power consumption data of each distributed grid load at each division level in the future short period relative to each minimum unit distributed grid load contained in the corresponding distributed grid load.

[0105] The beneficial effect of the above technology is: by taking the reciprocal of the total number of minimum units contained in the distributed power grid load of each minimum unit as the power prediction reliability, this simple and direct calculation method can quickly and effectively evaluate the reliability of power prediction at each division level. It makes it possible to more accurately measure the credibility of prediction results at different division levels when predicting the power consumption data of distributed power grid loads. It helps to make more targeted analysis and decisions when comprehensively considering factors such as power consumption data and average power share. It can optimize the access strategy of distributed photovoltaic distribution networks and improve the rationality and accuracy of power resource allocation. It ensures the stability and reliability of power grid operation and promotes the efficient use of distributed photovoltaic energy.

[0106] Example 6

[0107] On the basis of Example 3, a distributed photovoltaic distribution network access method, S204: based on the power consumption data of each distributed power grid load at each division level in the future short period, the power consumption data of each distributed power grid load at each division level in the future short period relative to the power prediction reliability of each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period, including:

[0108] The average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption at each future moment contained in the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level in the future short period, and the power prediction reliability of the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level relative to the corresponding minimum unit of distributed power grid load are taken as the predicted power consumption at each future moment determined by each minimum unit of distributed power grid load based on the distributed power grid load to which it belongs at each division level;

[0109] The average value of the predicted power consumption at the same future moment determined by the distributed power grid loads of each minimum unit based on all the distributed power grid loads at all the division levels is regarded as the final predicted power consumption of each minimum unit distributed power grid load at the corresponding future moment;

[0110] The final predicted power consumption of each minimum unit of distributed power grid load at all future moments in the future short period is regarded as the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period.

[0111] In this embodiment, the predicted power consumption at each future moment determined by each minimum unit of distributed power grid load based on the distributed power grid load belonging to each division fineness refers to the most basic power consumption unit that cannot be further subdivided (i.e., each minimum unit of distributed power grid load), and the predicted power consumption of this minimum unit at each specific moment in the future is inferred according to the distributed power grid load conditions belonging to different division finenesses.

[0112] The beneficial effects of the above technology are: by calculating the predicted power consumption of each minimum unit of distributed power grid load at each division level, the average power share, power consumption and power prediction reliability are comprehensively considered to make the prediction more comprehensive and accurate. Taking the average of the predicted power consumption at the same future moment based on different division levels as the final predicted power consumption further improves the reliability and stability of the prediction results. This sophisticated and scientific prediction method can more accurately grasp the power consumption of each minimum unit of distributed power grid load, and provide strong data support for the access strategy of distributed photovoltaic distribution network. It helps to optimize the allocation and scheduling of power resources and improve the operating efficiency and economy of the power grid. It can better adapt to the complex operating environment of distributed photovoltaic distribution network, ensure the quality and stability of power supply, and promote the effective integration and full utilization of distributed photovoltaic energy.

[0113] Example 7

[0114] Based on Example 1, the distributed photovoltaic distribution network access method, S3: based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control result of the distributed photovoltaic distribution network, including:

[0115] Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the current access strategy of the distributed photovoltaic distribution network is reasonable. If so, the current access strategy is retained as the latest access control result of the distributed photovoltaic distribution network;

[0116] Otherwise, all accessible photovoltaic components and all accessible loads of each access point in the photovoltaic distribution network are determined based on the ring network structure of the photovoltaic distribution network;

[0117] Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the short future cycle, the power consumption data of all the smallest units of distributed power grid loads in the short future cycle, and all accessible photovoltaic modules and all accessible loads at each access point in the photovoltaic distribution network, the latest access strategy of the distributed photovoltaic distribution network is generated;

[0118] Based on the latest access strategy of the distributed photovoltaic distribution network, the access adjustment control of the distributed photovoltaic distribution network is carried out to obtain the latest access control result of the distributed photovoltaic distribution network.

[0119] In this embodiment, the ring network structure of the photovoltaic distribution network refers to a network structure in which various nodes (such as substations, distribution boxes, etc.) in the photovoltaic distribution network are interconnected through multiple lines to form a ring. For example, multiple distributed photovoltaic power stations are connected to form a closed ring through lines, and electric energy can flow through multiple paths within the ring.

[0120] In this embodiment, the access point refers to a location where a distributed photovoltaic component or load can be connected to a photovoltaic distribution network. For example, a distribution box is an access point where a photovoltaic component or load can be connected to the grid.

[0121] In this embodiment, all accessible photovoltaic components and all accessible loads of an access point refer to all possible photovoltaic components (such as photovoltaic panels of different models and locations) that can be connected to the power grid at a specific access point and all possible connected power loads (such as various electrical equipment, factory production lines, etc.). For example, the photovoltaic components accessible to a certain access point include 5 groups of solar panels of different specifications, and the accessible loads include 3 large machines and some lighting equipment.

[0122] The beneficial effects of the above technology are: by judging whether the current access strategy is reasonable, it can be quickly determined whether it needs to be adjusted, thereby improving decision-making efficiency. If it is reasonable, it will be retained to ensure the stability and consistency of the system. When the current access strategy is unreasonable, the accessible photovoltaic components and accessible loads of each access point are determined based on the ring network structure, providing comprehensive basic information for generating new strategies. The latest access strategy is generated by comprehensively considering the power generation data, power consumption data and accessible resources, making the strategy more scientific and adaptable. Access adjustment control is performed based on the latest access strategy to obtain the latest access control results, thereby realizing the optimized management of distributed photovoltaic distribution networks. This method can effectively improve the access efficiency and quality of distributed photovoltaic distribution networks, and ensure the stable supply and efficient use of electricity. It helps to reduce the operating costs of the power grid, improve the reliability and flexibility of the power grid, and promote the large-scale application and development of distributed photovoltaic energy.

[0123] Example 8

[0124] On the basis of Example 7, the distributed photovoltaic distribution network access method determines whether the current access strategy of the distributed photovoltaic distribution network is reasonable based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period, including:

[0125] Based on the current access strategy of the distributed photovoltaic distribution network, all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network and all the smallest units of distributed grid loads are determined;

[0126] Based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the power generation data of all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network meets the power consumption data of all the smallest units of distributed power grid loads currently connected to the corresponding access point in the future short period. If so, it is determined that the current access strategy of the distributed photovoltaic distribution network is reasonable; otherwise, it is determined that the current access strategy of the distributed photovoltaic distribution network is unreasonable.

[0127] In this embodiment, whether the power generation data of all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network meets the power consumption data of all the smallest units of distributed power grid loads currently connected to the corresponding access point in the future short period means to determine whether the power values ​​that can be generated by all photovoltaic components that are currently connected at each specific access point of the distributed photovoltaic distribution network when generating electricity are sufficient to supply the power demand values ​​of all the most basic power consumption units (the smallest unit of distributed power grid load) connected to the access point in a short period of time in the future.

[0128] For example, a certain access point is currently connected to 3 groups of photovoltaic panels, and their total power generation is 800 kilowatts. For all the smallest units of distributed grid loads (such as 5 households and 1 small factory) currently connected to this access point, it is predicted that the total power consumption of these loads in the next week will be 1000 kilowatts. At this time, the power generation of the photovoltaic panels currently connected to the access point cannot meet the power demand of the corresponding access point in the future short period.

[0129] The beneficial effects of the above technology are: by determining the photovoltaic components and grid load currently connected to each access point based on the current access strategy, a clear object and scope are provided for subsequent judgment. Based on the power generation data and power consumption data, it is accurately judged whether the power generation power of each access point meets the power consumption. This direct and effective judgment method can accurately evaluate the rationality of the access strategy. If it is satisfied, it is judged to be reasonable, which ensures the effectiveness of the strategy in meeting electricity demand and maintains the stable operation of the system. If it is not satisfied, it is judged to be unreasonable, and problems are discovered in time, providing a clear basis for subsequent adjustment of the strategy. This judgment method helps to improve the accuracy and reliability of the evaluation of distributed photovoltaic distribution network access strategies, ensure the balance of power supply and demand, optimize resource allocation, improve the efficiency and economy of power grid operation, and promote the efficient integration and utilization of distributed photovoltaic energy.

[0130] Example 9

[0131] On the basis of Example 7, the distributed photovoltaic distribution network access method generates the latest access strategy of the distributed photovoltaic distribution network based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all minimum units of distributed power grid loads in the future short period, and all accessible photovoltaic components and all accessible loads at each access point in the photovoltaic distribution network, including:

[0132] Obtain access strategy generation model;

[0133] The power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and all accessible photovoltaic components and all accessible loads at each access point in the photovoltaic distribution network are input into the access strategy generation model to generate the latest access strategy for the distributed photovoltaic distribution network.

[0134] In this embodiment, the access strategy generation model is a mathematical or computational model used to generate the best access strategy based on various relevant data and conditions in the distributed photovoltaic distribution network, such as power generation data, power consumption data, grid structure, accessible photovoltaic components and loads, etc. For example, the model may comprehensively consider the power generation capacity of distributed photovoltaic components in a certain area, the changes in power load in different time periods, and then calculate how to adjust the access point to achieve optimal energy distribution and grid operation efficiency. The training process of the access strategy generation model usually requires the following types of training samples:

[0135] A large amount of historical data of distributed photovoltaic distribution networks under different operating conditions, including the power generation data of photovoltaic modules at each access point in different time periods and the power consumption data of grid loads; power generation and consumption data in different seasons and weather conditions to reflect the impact of environmental factors on grid operation; various possible access schemes and their corresponding operating effect data, such as the power quality and power balance generated by different combinations of photovoltaic module access points and load access points under a specific grid structure; relevant data under grid failure or abnormal conditions, which are used to train the model to generate reasonable access strategies in complex situations; through these diverse training samples, the model can learn the optimal access strategy mode under different conditions, so that it can generate effective access strategies when facing new situations.

[0136] The beneficial effects of the above technology are: obtaining an access strategy generation model provides an effective tool and method for generating the latest access strategy. Relevant power generation data, power consumption data, and accessible resources are input into the model, and with the help of the model's powerful analysis and calculation capabilities, the latest access strategy can be generated quickly and accurately. This method avoids complex manual calculations and analysis, and improves the efficiency and scientificity of strategy generation. It can fully consider the comprehensive impact of various factors, making the generated access strategy more optimized and reasonable. It helps to improve the access quality and performance of distributed photovoltaic distribution networks, ensure the stable operation and efficient supply of power systems, and promote the effective utilization and sustainable development of distributed photovoltaic energy.

[0137] Embodiment 10:

[0138] The present invention provides a distributed photovoltaic distribution network access system, which is used to execute any one of the distributed photovoltaic distribution network access methods in embodiments 1 to 9, including:

[0139] The power generation data prediction module is used to predict the power generation data of each photovoltaic component in the future short period based on the weather forecast data of the location of each distributed photovoltaic component in the distributed photovoltaic distribution network;

[0140] The power consumption data prediction module is used to predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period based on the historical power consumption data of all distributed power grid loads at each division level;

[0141] The grid structure optimization module is used to update the current access strategy of the distributed photovoltaic distribution network based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, and obtain the latest access control results of the distributed photovoltaic distribution network.

[0142] The beneficial effects of the above technology are: by predicting the power generation data based on the weather forecast data at the location of each distributed photovoltaic component, the impact of weather differences in different geographical locations on photovoltaic power generation can be fully considered, making the power generation prediction more accurate and precise. And based on the historical power consumption data of the distributed power grid load at each division level, the power consumption data in the future short period is predicted, which improves the accuracy and reliability of the power consumption prediction and provides a reliable basis for the subsequent access strategy update. The access strategy is updated by comprehensively considering the power generation data of the photovoltaic components, the power consumption data of the power grid load, and the ring network structure of the distribution network, realizing the comprehensive optimization of the access to the distributed photovoltaic distribution network. This access method helps to improve the energy utilization efficiency of the distributed photovoltaic distribution network and ensure the stability and reliability of the power supply. At the same time, it can better adapt to the changes in the power grid load, reduce the operating cost of the power grid, and promote the effective integration and utilization of distributed photovoltaic energy.

[0143] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A distributed photovoltaic distribution network access method, characterized in that: include: S1: Based on the weather forecast data of each distributed photovoltaic module in the distributed photovoltaic distribution network, the power generation data of each photovoltaic module in the future short period is predicted; S2: Based on the historical power consumption data of all distributed power grid loads at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted; S3: based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control result of the distributed photovoltaic distribution network; Wherein, step S2: based on the historical power consumption data of all distributed power grid loads at each division level, predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period, including: S201: predicting the power consumption data of each distributed power grid load at each division level in a short period in the future based on the historical power consumption data of all distributed power grid loads at each division level; S202: Determine the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level; S203: Evaluate the power prediction reliability of the power consumption data of each distributed power grid load in the future short period at each division level relative to each minimum unit of distributed power grid load included in the corresponding distributed power grid load; S204: Based on the power consumption data of each distributed power grid load at each division level in the future short period, the power consumption data of each distributed power grid load at each division level in the future short period relative to the power prediction reliability of each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted.

2. The distributed photovoltaic distribution network access method according to claim 1, characterized in that: S1: Based on the weather forecast data of each distributed photovoltaic module in the distributed photovoltaic distribution network, the power generation data of each photovoltaic module in the short period in the future is predicted, including: Obtain weather forecast data for the location of each distributed photovoltaic component in the distributed photovoltaic distribution network in the short term in the future; Extracting the time series variation information of all information items affecting power generation prediction from the weather forecast data; The time series change information of all power generation prediction influencing information items is input into the power generation time series data prediction model to obtain the power generation data of each photovoltaic module in the future short period.

3. The distributed photovoltaic distribution network access method according to claim 1, characterized in that: S202: Determine the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, including: Based on the historical power consumption data of all distributed power grid loads at each division level, the historical power consumption data of each minimum unit of distributed power grid load is determined; The ratio of the power consumption at each historical moment in the historical power consumption data of each minimum unit of distributed power grid load to the power consumption at the same historical moment in the historical power consumption data of the distributed power grid load to which it belongs at each division level is taken as the power consumption ratio of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level at the corresponding moment; The average value of the proportion of power consumption of each minimum unit of distributed power grid load in the distributed power grid load at each division level at all historical moments is taken as the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load at each division level.

4. The distributed photovoltaic distribution network access method according to claim 1, characterized in that: S203: Evaluate the power prediction reliability of the power consumption data of each distributed power grid load in the future short period at each division level relative to each minimum unit of distributed power grid load included in the corresponding distributed power grid load, including: The reciprocal of the total number of minimum unit distributed grid loads contained in the distributed grid loads to which each minimum unit distributed grid load belongs at each division level is taken as the power prediction reliability of the power consumption data of each distributed grid load at each division level in the future short period relative to each minimum unit distributed grid load contained in the corresponding distributed grid load.

5. The distributed photovoltaic distribution network access method according to claim 1, characterized in that: S204: Based on the power consumption data of each distributed power grid load at each division level in the future short period, the power prediction reliability of each distributed power grid load at each division level in the future short period relative to each minimum unit of distributed power grid load contained in the corresponding distributed power grid load, and the average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period is predicted, including: The average power proportion of each minimum unit of distributed power grid load in the distributed power grid load to which it belongs at each division level, the power consumption at each future moment contained in the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level in the future short period, and the power prediction reliability of the power consumption data of each distributed power grid load to which the corresponding minimum unit of distributed power grid load belongs at each division level relative to the corresponding minimum unit of distributed power grid load are taken as the predicted power consumption at each future moment determined by each minimum unit of distributed power grid load based on the distributed power grid load to which it belongs at each division level; The average value of the predicted power consumption at the same future moment determined by the distributed power grid loads of each minimum unit based on all the distributed power grid loads at all the division levels is regarded as the final predicted power consumption of each minimum unit distributed power grid load at the corresponding future moment; The final predicted power consumption of each minimum unit of distributed power grid load at all future moments in the future short period is regarded as the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period.

6. The distributed photovoltaic distribution network access method according to claim 1, characterized in that: S3: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, the current access strategy of the distributed photovoltaic distribution network is updated to obtain the latest access control results of the distributed photovoltaic distribution network, including: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the current access strategy of the distributed photovoltaic distribution network is reasonable. If so, the current access strategy is retained as the latest access control result of the distributed photovoltaic distribution network; Otherwise, all accessible photovoltaic components and all accessible loads of each access point in the photovoltaic distribution network are determined based on the ring network structure of the photovoltaic distribution network; Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the short future cycle, the power consumption data of all the smallest units of distributed power grid loads in the short future cycle, and all accessible photovoltaic modules and all accessible loads at each access point in the photovoltaic distribution network, the latest access strategy of the distributed photovoltaic distribution network is generated; Based on the latest access strategy of the distributed photovoltaic distribution network, the access adjustment control of the distributed photovoltaic distribution network is carried out to obtain the latest access control result of the distributed photovoltaic distribution network.

7. The distributed photovoltaic distribution network access method according to claim 6, characterized in that: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the current access strategy of the distributed photovoltaic distribution network is reasonable, including: Based on the current access strategy of the distributed photovoltaic distribution network, all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network and all the smallest units of distributed grid loads are determined; Based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period and the power consumption data of all the smallest units of distributed power grid loads in the future short period, it is judged whether the power generation data of all photovoltaic components currently connected to each access point in the distributed photovoltaic distribution network meets the power consumption data of all the smallest units of distributed power grid loads currently connected to the corresponding access point in the future short period. If so, it is determined that the current access strategy of the distributed photovoltaic distribution network is reasonable; otherwise, it is determined that the current access strategy of the distributed photovoltaic distribution network is unreasonable.

8. The distributed photovoltaic distribution network access method according to claim 6, characterized in that: Based on the power generation data of all photovoltaic modules in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed grid loads in the future short period, and all accessible photovoltaic modules and all accessible loads at each access point in the photovoltaic distribution network, the latest access strategy of the distributed photovoltaic distribution network is generated, including: Obtaining an access policy generation model; The power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed power grid loads in the future short period, and all accessible photovoltaic components and all accessible loads at each access point in the photovoltaic distribution network are input into the access strategy generation model to generate the latest access strategy for the distributed photovoltaic distribution network.

9. Distributed photovoltaic distribution network access system, characterized in that: A distributed photovoltaic distribution network access method for executing any one of claims 1 to 8, comprising: The power generation data prediction module is used to predict the power generation data of each photovoltaic component in the future short period based on the weather forecast data of the location of each distributed photovoltaic component in the distributed photovoltaic distribution network; The power consumption data prediction module is used to predict the power consumption data of each minimum unit of distributed power grid load in the distributed photovoltaic distribution network in the future short period based on the historical power consumption data of all distributed power grid loads at each division level; The grid structure optimization module is used to update the current access strategy of the distributed photovoltaic distribution network based on the power generation data of all photovoltaic components in the distributed photovoltaic distribution network in the future short period, the power consumption data of all the smallest units of distributed grid loads in the future short period, and the ring network structure of the photovoltaic distribution network, and obtain the latest access control results of the distributed photovoltaic distribution network.

Images