Power dispatching method, device and equipment of distributed new energy system and medium

Abstract

The invention discloses a power dispatching method and device for a distributed new energy system, equipment and a medium. The method comprises the steps of obtaining new energy data; performing data cleaning on the new energy data; performing data verification on the cleaned new energy data; if the data verification is passed, performing strategy prediction on the cleaned new energy data to obtain a target scheduling strategy; and scheduling the power of the distributed new energy system based on the target scheduling strategy. Therefore, the power of the new energy system is scheduled by adopting the target scheduling strategy obtained by predicting the new energy data after data cleaning and verification, so that the scheduling risk of power scheduling of the new energy system is reduced, and the accuracy and reliability of power scheduling are improved.

Description

Technical Field

[0001] The present invention relates to the field of power dispatching technology, and in particular to a power dispatching method, device, equipment and medium for a distributed new energy system. Background Art

[0002] With the deepening of the global energy structure transformation, distributed new energy such as wind energy, hydropower, and solar energy have been widely used. In the field of distributed new energy, data sharing plays a fundamental and key role in achieving energy optimization and intelligent management.

[0003] However, the instability of existing data sharing, such as low data quality, has caused uncertainty in power dispatch, increased the dispatch risk of power dispatch in new energy systems, reduced the accuracy and reliability of power dispatch, and thus increased the probability of power grid failures or accidents. Summary of the invention

[0004] The present application proposes a power dispatching method, device, equipment and medium for a distributed new energy system, which reduces the dispatching risk of power dispatching of the new energy system, thereby improving the accuracy and reliability of power dispatching.

[0005] In a first aspect, a power dispatching method for a distributed new energy system is provided, comprising:

[0006] Obtain new energy data;

[0007] Performing data cleaning on the new energy data;

[0008] Verify the cleaned new energy data;

[0009] If the data verification is passed, the cleaned new energy data will be used for strategy prediction to obtain the target scheduling strategy;

[0010] The electric power of the distributed new energy system is dispatched based on the target dispatching strategy.

[0011] In a second aspect, a power dispatching device for a distributed new energy system is provided, comprising:

[0012] An acquisition module is used to acquire new energy data;

[0013] A cleaning module, used for cleaning the new energy data;

[0014] A verification module is used to verify the cleaned new energy data;

[0015] The prediction module is used to make a strategy prediction on the cleaned new energy data to obtain the target scheduling strategy if the data verification passes;

[0016] The scheduling module is used to schedule the power of the distributed new energy system based on the target scheduling strategy.

[0017] Optionally, in some embodiments of the present application, the acquisition module includes:

[0018] A receiving submodule, used for receiving distribution transformer data;

[0019] A first identification submodule is used to identify the data source of the distribution transformer data;

[0020] The acquisition submodule is used to acquire the new energy data from the distribution transformer data according to the source identification result.

[0021] Optionally, in some embodiments of the present application, the clear module includes:

[0022] A second identification submodule, used to identify and record all target data sources in the new energy data;

[0023] An extraction submodule, used to extract original data from each of the target data sources;

[0024] A first cleaning submodule, used for performing a first data cleaning on the original data to obtain normalized data;

[0025] A conversion submodule, used for performing format conversion on the normalized data to obtain target analysis data;

[0026] A first detection submodule, configured to perform anomaly detection on the target analysis data to obtain anomaly detection results;

[0027] The second cleaning submodule is used to perform a second data cleaning on the target analysis data based on the abnormality detection result.

[0028] Optionally, in some embodiments of the present application, the device further includes:

[0029] A division module, used for dividing the new energy data into stages based on the data type of the new energy data to obtain a stage division management cycle;

[0030] An evaluation module, used to evaluate the new energy data based on the divided management cycle to obtain a data evaluation result;

[0031] A management module is used to perform data quality management on the new energy data based on the data evaluation result.

[0032] Optionally, in some embodiments of the present application, the verification module includes:

[0033] The verification submodule is used to verify the cleaned new energy data and obtain the data verification result;

[0034] The detection submodule is used to perform data detection on the cleaned new energy data to obtain data detection results;

[0035] A determination submodule is used to determine whether the data verification of the cleaned new energy data has passed based on the data verification result and the data detection result.

[0036] Optionally, in some embodiments of the present application, the prediction module includes:

[0037] The first prediction submodule is used to perform output prediction based on the cleaned new energy data to obtain new energy output prediction data;

[0038] The second prediction submodule is used to perform strategy prediction on the new energy output prediction data based on the improved particle swarm algorithm to obtain a target scheduling strategy.

[0039] Optionally, in some embodiments of the present application, the scheduling module includes:

[0040] A conversion submodule, used to convert the target scheduling strategy into a scheduling instruction set;

[0041] The scheduling submodule is used to schedule the power of the distributed new energy system based on the scheduling instruction set.

[0042] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned power dispatching method for the distributed new energy system when executing the computer program.

[0043] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power dispatching method of the above-mentioned distributed new energy system are implemented.

[0044] The present application provides a method, device, equipment and medium for dispatching electric power of a distributed new energy system, which obtains new energy data; performs data cleaning on the new energy data; performs data verification on the cleaned new energy data; if the data verification passes, the cleaned new energy data is subjected to strategy prediction to obtain a target dispatching strategy; and the electric power of the distributed new energy system is dispatched based on the target dispatching strategy. In the electric power dispatching scheme for the distributed new energy system provided in the present application, the quality and consistency of the data are ensured by performing data cleaning on the new energy data and performing data verification on the cleaned new energy data; once the data verification passes, the electric power of the new energy system is dispatched based on the target dispatching strategy obtained by predicting the cleaned new energy data. It can be seen that by using the target dispatching strategy obtained by predicting the new energy data after data cleaning and verification to dispatch the electric power of the new energy system, it is beneficial to reduce the dispatching risk of the electric power dispatching of the new energy system, thereby improving the accuracy and reliability of the electric power dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 An application environment diagram of the power dispatching method for a distributed new energy system provided in an embodiment of the present application;

[0047] Figure 2 A flow chart of a power dispatching method for a distributed new energy system provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of the process of new energy data collection provided in the embodiment of the present application;

[0049] Figure 4 A schematic diagram of the data cleaning process provided in the embodiment of the present application;

[0050] Figure 5 A schematic diagram of the data management process provided in the embodiment of the present application;

[0051] Figure 6 A schematic diagram of a data error prevention process provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of the decision process of the target scheduling strategy provided in the embodiment of the present application;

[0053] Figure 8A flow chart of a power dispatching method for a distributed new energy system provided in another embodiment of the present application;

[0054] Fig. 9 A flow chart of a power dispatching method for a distributed new energy system provided in yet another embodiment of the present application;

[0055] Fig.10 A structural block diagram of a power dispatching device for a distributed new energy system provided in an embodiment of the present application;

[0056] Fig.11 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0059] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0060] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0061] The power dispatching method of the distributed new energy system provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment. Among them, the computer device 110 communicates with the server 120 through the network 130. The computer device 110 can obtain new energy data; perform data cleaning on the new energy data; perform data verification on the cleaned new energy data; if the data verification passes, the cleaned new energy data is predicted to obtain a target scheduling strategy; the power of the distributed new energy system is scheduled based on the target scheduling strategy, and displayed through the computer device 110. In the present invention, the quality and consistency of the data are ensured by performing data cleaning on the new energy data and performing data verification on the cleaned new energy data; once the data verification passes, the power of the new energy system is scheduled based on the target scheduling strategy predicted by the cleaned new energy data. It can be seen that by using the target scheduling strategy predicted by the new energy data after data cleaning and verification to schedule the power of the new energy system, it is beneficial to reduce the scheduling risk of the power scheduling of the new energy system, thereby improving the accuracy and reliability of the power scheduling. . Among them, the computer device 110 can be, but is not limited to, various smart phones 110-1, tablet computers 110-2 and laptop computers 110-3. The present invention is described in detail below through specific embodiments.

[0062] See also Figure 2 As shown, Figure 2 A flow chart of a method for dispatching electric power in a distributed new energy system provided in an embodiment of the present invention is provided. The method can be applied to both a terminal and a server. This embodiment is illustrated by applying it to a server. The method for dispatching electric power in a distributed new energy system includes the following steps:

[0063] 101: Obtain new energy data.

[0064] Among them, new energy data can be data used to reflect the operating status, power generation, environmental factors and other information of the new energy system. New energy data can include power generation, environmental parameters (such as temperature, humidity, sunshine intensity, wind speed, etc.), equipment status, system efficiency (such as capacity loss, performance indicators), etc. The types of new energy data include but are not limited to solar energy, wind energy, geothermal energy, tidal energy, etc.

[0065] Renewable energy data can be collected through metering automation systems. It is also possible to install metering equipment (such as smart meters) on the new energy power generation equipment (such as wind turbines and solar panels) in the new energy system to monitor and record new energy data in real time. Renewable energy data can also be collected through distribution terminals, which mainly collect data related to the operation of the distribution network of the new energy system, such as voltage, current, power, power quality, etc.

[0066] Considering that the distribution and transformation data of the distributed new energy system is complex and numerous, the distribution and transformation data can be obtained from multiple data acquisition channels. That is, in one embodiment, the acquisition of new energy data includes:

[0067] Receive distribution transformer data;

[0068] Identifying the data source of the distribution transformer data;

[0069] According to the source identification result, the new energy data is obtained from the distribution transformer data.

[0070] Among them, distribution and transformation data refers to data related to renewable energy power generation, distribution and transformation, and transformers. Distribution and transformation data may include power generation data, distribution data, transformer data, power quality data, environmental detection data, user power consumption data, maintenance and repair data, as well as economic and operational data, etc. Power generation data may include the output power of renewable energy power generation equipment (such as the speed of wind turbines, the output current and voltage of solar photovoltaic panels, etc.), the operating status of power generation equipment (such as startup, quality, maintenance and fault status), and power generation statistics; distribution data may include voltage, current and power quality parameters in the new energy system (such as voltage level, current size and power factor), the load conditions of distribution lines (such as load distribution, load distribution and valley period), and the operating status of distribution equipment (such as the status of circuit breakers, fuses and protective devices); transformer data may include transformer operating parameters, load rate, maintenance and repair records, etc.; power quality data may include voltage and current fluctuations (such as voltage sag, instantaneous power outage and frequency deviation), harmonic content and imbalance of new energy systems, and power quality monitoring data (such as waveform records of voltage and current); environmental monitoring data may include environmental factors that affect renewable energy power generation (such as wind speed, wind direction, temperature, humidity, solar radiation intensity, etc.), the impact of environmental conditions on the operation of distribution equipment, such as equipment performance under extreme weather conditions; user electricity consumption data may include users' electricity load, including electricity consumption and electricity consumption patterns in different time periods, and users' electricity quality feedback, such as reports of voltage instability or power outages; maintenance and overhaul data may include equipment maintenance history and overhaul records, including preventive maintenance and emergency repairs, and information on replacement parts, such as transformer oil replacement, calibration of protection devices, etc.; economic and operational data may include the costs and benefits of renewable energy power generation, including operating costs, maintenance costs and electricity sales revenue and the operating efficiency of the distribution network (such as power supply reliability and user satisfaction).

[0071] Among them, multiple data collection channels can be set up in the distribution network of the new energy system, and the new energy data can be obtained from each distribution data according to the priority of the data collection channel.

[0072] For example, a metering automation system and / or a marketing and distribution fusion terminal can be set up in the power distribution center of the energy system to collect distribution and transformation data. The marketing and distribution fusion terminal has a higher priority than the metering automation system. Figure 3 As shown, when receiving each distribution data, the data source of each distribution data can be identified first to obtain the source identification result. The source identification result is used to indicate the data source of each distribution data and mark it. For example, if the distribution transformer data is identified as directly purchased from the marketing and distribution fusion terminal, the distribution transformer data is marked as a high-priority data source; and if the distribution transformer data is identified as non-directly purchased data, the distribution transformer data is marked as a low-priority data source. Then, according to the priority order of each data source, the distribution transformer data collected by the marketing and distribution fusion terminal with the highest priority is used as new energy data. Optionally, data anomaly detection can be performed on the high-priority data source; if it is detected that the high-priority data source fails or the data is unavailable (such as data anomalies, too low quality evaluation), it is automatically switched to the low-priority data source (i.e., the distribution transformer data forwarded by the metering automation system) to ensure the data continuity of the new energy data. It should be noted that when the distribution network is configured with a metering automation system but no marketing and distribution fusion terminal is configured, the distribution transformer data forwarded from the metering automation system can be used as new energy data.

[0073] The marketing and distribution fusion terminal refers to an intelligent terminal device that integrates marketing (operation), power distribution, and power consumption information collection in a new energy system. The marketing and distribution fusion terminal is usually deployed at various nodes in the power grid, such as distribution transformers, ring network cabinets, branch boxes, etc., to collect and process distribution and transformation data in real time. The marketing and distribution fusion terminal can collect distribution and transformation data from the source of the equipment through optical fiber communication, which helps to avoid delays or errors that may occur during the data collection process.

[0074] 102: Clean the new energy data.

[0075] During the data collection stage, the original new energy data may contain noise and outliers, which will have a negative impact on subsequent data analysis, such as reducing the accuracy and reliability of the energy data. Therefore, before the new energy data enters the analysis process, the original data needs to be cleaned and preprocessed to improve the data quality. Therefore, data cleaning and processing techniques (such as outlier detection and processing) can be used to clean the new energy data to remove noise and outliers in the new energy data and improve the data quality of the new energy data.

[0076] In one embodiment, the step of cleaning the new energy data includes:

[0077] Identify and record all target data sources in the new energy data;

[0078] Extracting raw data from each of the target data sources;

[0079] Performing a first data cleaning on the original data to obtain normalized data;

[0080] Performing format conversion on the normalized data to obtain target analysis data;

[0081] Performing anomaly detection on the target analysis data to obtain anomaly detection results;

[0082] A second data cleaning is performed on the target analysis data based on the abnormality detection result.

[0083] Among them, the target data source refers to the data source in the distribution network of the new energy system that can provide information about the operating status, performance and environmental conditions of the new energy system, which can include the type, location, acquisition frequency and data format of each data source. The data source can include sensors (such as temperature sensors, humidity sensors, wind speed sensors, solar radiation sensors, etc.), smart meters, inverters, protection and control equipment (such as circuit breakers, fuses, relay protection devices, etc.), telemetry and telesignaling systems, energy management systems (EMS), fault recorders, and maintenance and repair records, etc.

[0084] For example, see Figure 4First, we can determine the data source, that is, identify and record all available data sources in the new energy data to obtain all target data sources; then, we can collect data, that is, collect the original data from each target data source, for example, assuming that the new energy data includes solar energy data, then the original data includes the temperature and power generation in the solar energy data; secondly, we can perform the first data cleaning on the original data, that is, perform preliminary cleaning on the collected original data to remove obvious errors and inconsistencies, such as checking and correcting wrong timestamps, removing duplicate records and correcting unreasonable values ​​to obtain normalized data; then, we can perform data conversion, that is, perform normalized data conversion on the normalized data. Format conversion to obtain target analysis data is conducive to improving data analysis efficiency and accuracy, such as data type conversion (such as converting strings to numeric types), unit conversion (such as converting kilowatt-hours to megawatt-hours), etc.; Next, anomaly detection is performed on the target analysis data, that is, anomaly detection algorithms are applied to identify abnormal values ​​or patterns in the target analysis data, such as abnormal power generation, abnormal temperature, abnormal light intensity, etc., and the abnormal results are sent to relevant operation and maintenance personnel; Subsequently, the target analysis data can be cleaned for the second time based on the abnormal detection results, that is, the abnormal values ​​in the target analysis data are cleaned to obtain cleaned new energy data. Finally, continuous monitoring and optimization can also be carried out, that is, a continuous data monitoring mechanism is established to regularly clean (i.e., second data cleaning), convert, normalize (i.e., first data cleaning) and detect anomalies of the collected new energy data.

[0085] In this embodiment, by extracting the original data from all target data sources in the new energy data, and then performing the first data cleaning, format conversion, anomaly detection, and second data cleaning on the original data in sequence, it helps to improve the real-time nature of the new energy data, ensure the reliability and accuracy of the new energy data, and help reduce the scheduling risk of power scheduling in the new energy system, thereby improving the accuracy and reliability of power scheduling.

[0086] Data Lifecycle Management (DLM) refers to the process of managing the entire life cycle of new energy data from creation, storage, use, sharing, archiving to final destruction. The goal of DLM is to ensure the quality, security, compliance and availability of data throughout its life cycle. The process of managing new energy data needs to be implemented on related services, storage devices, network devices and other hardware. In this process, according to the different uses and needs of new energy data, it is divided into multiple stages, and gradually transferred to the next stage after meeting specific conditions or completing established tasks, so as to ensure the security and availability of new energy data at each stage. That is, in one embodiment, before the new energy data is cleaned, the method also includes:

[0087] Dividing the new energy data into stages based on the data type of the new energy data to obtain a stage division management cycle;

[0088] Evaluate the new energy data based on the divided management cycle to obtain a data evaluation result;

[0089] Data quality management is performed on the new energy data based on the data evaluation result.

[0090] For example, see Figure 5 , taking solar energy data as an example of new energy data, first, the solar energy data is divided into stages, and the obtained stage division management cycle includes collection, storage, use, transmission, sharing and destruction. In the storage stage, rely on automated tools to identify new solar energy data and data types, divide solar energy data into public level, internal level and confidential level, mark the attributes, sources and uses of solar energy data, and finally collect solar energy data including temperature, illumination time, output power, etc.; in the data storage stage, rely on automated tools to identify new solar energy data and data types, divide solar energy data into public level, internal level and confidential level for storage, such as meteorological data (affecting the efficiency of power conversion), geographical location (determining the distribution of solar energy resources); in the data use stage, monitor the operation behavior and manage the permissions; in the data transmission stage, perform protocol monitoring and application monitoring; in the data sharing stage, perform protocol monitoring, application monitoring, copy and print monitoring; in the data destruction stage, perform automatic data discovery and tag-based data removal. Then, a data quality assessment indicator system is established to conduct a comprehensive and objective evaluation of the data quality to ensure that solar energy data maintains high quality and consistency throughout the entire life cycle management process; taking the evaluation of solar energy data as an example, the following data quality assessment indicator system can be set to obtain data evaluation results:

[0091] Accuracy: measured by comparing the difference between actual measurements of solar power generation and expected model predictions. If the difference is within an acceptable range (e.g. ±5%), the solar data is considered accurate;

[0092] Completeness: Check that the solar data contains all necessary timestamps and power generation readings. If the solar radiation observation data has any missing data points, they need to be completed.

[0093] Consistency: Ensure that data recorded by different sensors or devices over the same time period is consistent. If there are significant differences, investigate the cause and resolve potential issues.

[0094] Timeliness: Evaluate whether the frequency of solar data updates meets the requirements. For example, if the solar data is updated every minute, but there is a delay, detect the cause of the delay and speed up data processing;

[0095] Finally, based on the data evaluation results, we can ensure the continuous improvement of data collection and processing processes during the data management cycle, improve the quality and reliability of data, provide a solid foundation for data analysis, scheduling strategy support and other applications, and provide quantitative standards for subsequent data anomaly detection and processing.

[0096] 103: Perform data verification on the cleaned new energy data.

[0097] Data error prevention technology can be used to verify the cleaned new energy data. Data error prevention technology includes data verification, data detection and response technology, etc. Specifically, firstly, a plurality of preset verification methods are used to verify the cleaned new energy data to ensure the integrity and accuracy of the data. The preset verification methods include format verification, range verification, logical verification, etc., which are used to prevent the insertion and update of errors, inconsistencies and invalid data; then, data detection and response technology is used to collect and model the data content and data operation behavior of the cleaned new energy data through the network and terminal levels, and automatically perceive abnormal user behavior; when abnormal behavior is detected, the protection action corresponding to the abnormal behavior is executed according to the preset control strategy to prevent the occurrence of data leakage in advance. At the same time, different control strategies are implemented according to different personnel risk levels, and automatic response actions are executed at the terminal.

[0098] In this step, data error prevention technology is used to improve the accuracy and reliability of new energy data, thereby improving the safety and accuracy of power dispatching.

[0099] In one embodiment, the data verification of the cleaned new energy data includes:

[0100] Perform data verification on the cleaned new energy data to obtain data verification results;

[0101] Perform data detection on the cleaned new energy data to obtain data detection results;

[0102] Based on the data verification result and the data detection result, it is determined whether the data verification of the cleaned new energy data passes.

[0103] For example, see Figure 6Taking solar energy data as an example, data verification of distributed new energy systems includes data verification and data detection; among them, data verification includes format and range verification, logical integrity verification, real-time and repeatability verification, historical data comparison, manual review and feedback mechanism, etc., and obtains corresponding data detection results. For example, if the solar radiation intensity exceeds the preset range, that is, the data verification fails, the solar radiation intensity is marked as abnormal or invalid; data detection includes network level detection, terminal level detection, information collection and modeling, abnormal behavior perception, strategy execution, and continuous learning and optimization, and obtains corresponding data detection results. For example, when the model established by machine learning perceives and analyzes the current solar data operation behavior in real time, when the current solar data operation behavior is perceived and analyzed to have abnormal behavior that does not conform to the normal behavior pattern, that is, the data verification fails, the corresponding protection actions can be performed on the detected abnormal behavior based on the preset management and control strategy, such as stopping access and sending an alarm to the administrator.

[0104] In this embodiment, by performing data verification and data detection on the cleaned new energy data, standardized management is performed on data collection, storage, processing and other links to ensure the quality and accuracy of the new energy data. The importance of security and compliance is also emphasized, thereby avoiding load forecast deviations caused by data errors. The distributed new energy system can effectively prevent data errors and security threats, improve the accuracy and reliability of power dispatch, and ensure the stable operation and sustainable development of the distributed new energy system.

[0105] 104: If the data verification is passed, a strategy prediction is performed on the cleaned new energy data to obtain a target scheduling strategy.

[0106] The cleaned new energy data can be strategically predicted based on the preset prediction model to obtain the target scheduling strategy. The prediction model can be a statistical model (ARIMA, exponential smoothing, etc.), a machine learning model (random forest, support vector machine, etc.) or a deep learning model (recursive neural network, long short-term memory network, etc.)

[0107] In one embodiment, the step of performing strategy prediction on the cleaned new energy data to obtain a target scheduling strategy includes:

[0108] Perform output prediction based on the cleaned new energy data to obtain new energy output prediction data;

[0109] Based on the improved particle swarm algorithm, the new energy output forecast data is subjected to strategic forecasting to obtain a target scheduling strategy.

[0110] Among them, the new energy output forecast data refers to the predicted data on the expected power generation of new energy power generation systems (such as wind power generation, solar photovoltaic power generation, etc.) in a specific time period in the future.

[0111] For example, see Figure 7 First, the cleaned new energy data is processed and predicted using a deep learning algorithm to obtain new energy output prediction data; then, the improved particle swarm algorithm is used to optimally allocate and dispatch power sources based on the new energy output prediction data; finally, the target scheduling strategy is output. For example, the wind speed and wind direction are predicted every hour in the next 24 hours; then the target scheduling strategy can be a power generation plan: according to the predicted wind speed, more wind power generation resources are scheduled during periods when wind power generation is expected to be higher, and the output of thermal power generation or other traditional power generation resources is reduced. Energy storage scheduling: During periods when wind power generation is predicted to be lower, energy storage equipment is charged in advance to prepare for emergencies. Demand response: Notify industrial users to increase electricity consumption during periods of high wind power generation to make full use of clean energy. Grid operation: During periods when wind power generation is predicted to be high, grid operation parameters such as voltage and reactive power are adjusted to accommodate a high proportion of renewable energy connected to the grid. For another example, by combining the forecast data of multiple new energy sources such as wind energy, solar energy, and hydropower, a comprehensive output forecast is obtained; then the target scheduling strategy can include multi-energy coordination: according to the comprehensive forecast data, coordinate the output of different new energy resources to achieve multi-energy complementarity. Cross-regional scheduling: In areas with high output of new energy, excess electricity is transmitted to other areas through cross-regional power grids. Market transactions: Use forecast data to trade in the electricity market to optimize the economic benefits of electricity resources. Emergency preparedness: During periods when the output of new energy is predicted to be low, prepare emergency power generation resources, such as mobile power generation vehicles or backup generators, to cope with possible power shortages.

[0112] Using deep learning algorithms to predict renewable energy output data is to build a complex neural network model to analyze historical data and real-time meteorological information, so as to accurately predict the power generation of renewable energy such as wind power and solar power in the future. Based on this, it is possible to capture the nonlinear relationship between renewable energy output and various factors, improve the accuracy and reliability of predictions, and provide strong support for power grid dispatching and energy management.

[0113] Optimal allocation and dispatch of renewable energy power. Based on accurate renewable energy output forecast data, an improved particle swarm algorithm is used to optimally allocate and dispatch the power of distributed renewable energy systems, and to find the best dispatch strategy, namely the target dispatch strategy, to achieve efficient utilization of renewable energy resources and stable operation of the power grid. Based on this, it is possible to comprehensively consider a variety of constraints and objective functions, such as cost, environmental impact, and supply and demand balance, so as to reduce energy consumption and environmental pollution and improve energy efficiency while ensuring energy supply.

[0114] 105: Dispatching the power of the distributed new energy system based on the target dispatching strategy.

[0115] The target dispatch strategy can be automatically executed through automated control systems such as smart inverters, energy management systems (EMS) and demand response systems to dispatch the power of distributed renewable energy systems. The target dispatch strategy can be controlled and executed by the distribution network operation and control system (OCS).

[0116] In one embodiment, scheduling the power of the distributed new energy system based on the target scheduling strategy includes:

[0117] Converting the target scheduling strategy into a scheduling instruction set;

[0118] The power of the distributed new energy system is dispatched based on the dispatch instruction set.

[0119] For example, assuming that the target scheduling strategy includes preset scheduling rules, such as the start and stop sequence, output level, and operating time of the power generation equipment, the scheduling rules are converted into specific scheduling instructions, such as power generation setting, switch operation, etc. The scheduling instructions need to include the specific operations of each control node within a specific time period; please refer to Figure 7 After receiving the dispatching instruction, the distribution network OCS system realizes high-speed and reliable data transmission, and transmits real-time data (i.e. new energy data) and control instructions (i.e. dispatching instructions) to each programmable logic controller (PLC). PLC accurately controls and dispatches new energy equipment according to the received new energy data and dispatching instructions, and realizes automatic energy distribution and management. Based on this, the intelligence and response speed of the system are improved, the efficient and stable operation of new energy equipment is ensured, and a strong guarantee is provided for the safe and reliable power supply of the power grid.

[0120] In one embodiment, see Figures 8 to 9 , based on data governance and data error prevention technology, a power dispatching process for a distributed new energy system is provided, as follows:

[0121] First, the integration and collaborative relationship among data governance, data error prevention and scheduling auxiliary decision-making of distributed new energy systems is analyzed. The target scheduling strategy of distributed new energy is based on data governance and data error prevention, so the technical achievements of coordinated data governance and data error prevention are needed; secondly, distributed new energy data collection is carried out. This method gives priority to the direct acquisition of data from the distribution terminal, and the data that is not collected is forwarded by metering, and has an automatic switching function to ensure the timeliness and correctness of the data; then, distributed new energy data governance is carried out first according to the collaborative relationship among the three. New energy data governance includes data life cycle management and data quality management, among which data anomaly detection and processing are carried out through data cleaning and preprocessing technology to provide data support for the scheduling auxiliary decision-making of distributed new energy; then, distributed new energy data error prevention is carried out according to the collaborative relationship among the three. By ensuring the integrity and accuracy of data through data verification, data detection and response technology is used to automatically perceive abnormal user behavior and execute protective actions according to the strategy, which can prevent data leakage in advance; finally, the new energy output forecast data is predicted by using a deep learning algorithm, and then based on the improved particle swarm algorithm, the optimal allocation and scheduling are achieved through the distribution network OCS system to realize the power scheduling method of the distributed new energy system. Among them, the automatic control unit is used to automatically control the scheduling execution to achieve timely response and rapid scheduling.

[0122] The analysis of the integration and collaborative relationship among data governance, data error prevention, and target scheduling strategy decision-making specifically includes:

[0123] (1) Data governance: Data governance is a comprehensive management process that covers data collection, storage, processing, analysis, and sharing. Effective data governance can ensure the accuracy and reliability of data and provide strong support for the decision-making and development of target scheduling strategies for distributed new energy systems.

[0124] (2) Data error prevention: Data error prevention effectively prevents the insertion and update of erroneous, inconsistent and invalid data through the comprehensive use of multiple means such as data verification, data detection and response technology, thereby ensuring the security and accuracy of scheduling.

[0125] (3) Data governance and data error prevention are interdependent: a sound data governance system can ensure that the data source is reliable and of high quality, thereby reducing the risk of data errors. At the same time, data error prevention is an important part of data governance, used to detect and prevent data errors, and provide a strong guarantee for data governance; the multi-machine collaborative reuse of data governance and data error prevention can achieve all-round management and protection of new energy data, and provide a solid data foundation for power dispatching decisions.

[0126] In this application, firstly, by constructing an integrated data governance framework (i.e., the integration and collaborative relationship analysis of data governance, data error prevention and decision-making of target scheduling strategy), the quality control and error prevention mechanism of the whole chain from data collection to application are ensured, and the interference and safety hazards of erroneous data are effectively avoided; then, the distributed new energy data collection adopts the "one collection and double release" method, combined with the metering automation system and the direct collection of the marketing and distribution integration terminal, and the direct collection data is used first to provide data support for the next three links; then, by adopting advanced technical means such as data verification to prevent data errors, data errors and potential security threats are effectively prevented; at the same time, the deep learning algorithm is introduced to predict the output prediction data of new energy, and the improved particle swarm algorithm is combined to realize the optimal allocation and dynamic scheduling of power resources, overcoming the limitations of the traditional method of insufficient processing of complex nonlinear relationships and slow real-time scheduling response. In addition, with the efficient collaboration of the distribution network OCS system and the programmable logic controller (PLC), the rapid and accurate execution of the dispatching instructions is realized, the synchronization and coordination problems in the grid-connected operation of new energy are solved, and the overall stability and economy of the power grid are improved.

[0127] The above is the power dispatching process of the distributed new energy system of this application.

[0128] As mentioned above, the present application provides a method, device, computer equipment and storage medium for power dispatching of a distributed new energy system, by acquiring new energy data; performing data cleaning on the new energy data; performing data verification on the cleaned new energy data; if the data verification passes, then performing strategy prediction on the cleaned new energy data to obtain a target scheduling strategy; and dispatching the power of the distributed new energy system based on the target scheduling strategy. In the power dispatching scheme of the distributed new energy system provided in the present application, the quality and consistency of the data are ensured by performing data cleaning on the new energy data and performing data verification on the cleaned new energy data; once the data verification passes, the power of the new energy system is dispatched based on the target scheduling strategy predicted by the cleaned new energy data. It can be seen that by using the target scheduling strategy predicted by the new energy data after data cleaning and verification to dispatch the power of the new energy system, it is beneficial to reduce the dispatching risk of power dispatching of the new energy system, thereby improving the accuracy and reliability of power dispatching.

[0129] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0130] In one embodiment, a power dispatching device for a distributed new energy system is provided, and the power dispatching device for the distributed new energy system corresponds one-to-one to the power dispatching method for the distributed new energy system in the above embodiment. Fig.10As shown, the power dispatching device of the distributed new energy system includes:

[0131] An acquisition module 201 is used to acquire new energy data;

[0132] A cleaning module 202, used for cleaning the new energy data;

[0133] Verification module 203, used for verifying the cleaned new energy data;

[0134] The prediction module 204 is used to perform strategy prediction on the cleaned new energy data to obtain a target scheduling strategy if the data verification passes;

[0135] The scheduling module 205 is used to schedule the power of the distributed new energy system based on the target scheduling strategy.

[0136] In this embodiment, by acquiring new energy data; performing data cleaning on the new energy data; performing data verification on the cleaned new energy data; if the data verification passes, then performing strategy prediction on the cleaned new energy data to obtain a target scheduling strategy; and scheduling the power of the distributed new energy system based on the target scheduling strategy. In the power dispatching scheme for the distributed new energy system provided in the present application, by performing data cleaning on the new energy data and performing data verification on the cleaned new energy data, the quality and consistency of the data are ensured; once the data verification passes, the power of the new energy system is dispatched based on the target scheduling strategy predicted by the cleaned new energy data. It can be seen that by scheduling the power of the new energy system by adopting the target scheduling strategy predicted by the new energy data after data cleaning and verification, it is beneficial to reduce the scheduling risk of power dispatching of the new energy system, thereby improving the accuracy and reliability of power dispatching.

[0137] Optionally, in some embodiments of the present application, the acquisition module includes:

[0138] A receiving submodule, used for receiving distribution transformer data;

[0139] A first identification submodule is used to identify the data source of the distribution transformer data;

[0140] The acquisition submodule is used to acquire the new energy data from the distribution transformer data according to the source identification result.

[0141] Optionally, in some embodiments of the present application, the clear module includes:

[0142] A second identification submodule, used to identify and record all target data sources in the new energy data;

[0143] An extraction submodule, used to extract original data from each of the target data sources;

[0144] A first cleaning submodule, used for performing a first data cleaning on the original data to obtain normalized data;

[0145] A conversion submodule, used for performing format conversion on the normalized data to obtain target analysis data;

[0146] A first detection submodule, configured to perform anomaly detection on the target analysis data to obtain anomaly detection results;

[0147] The second cleaning submodule is used to perform a second data cleaning on the target analysis data based on the abnormality detection result.

[0148] Optionally, in some embodiments of the present application, the device further includes:

[0149] A division module, used for dividing the new energy data into stages based on the data type of the new energy data to obtain a stage division management cycle;

[0150] An evaluation module, used to evaluate the new energy data based on the divided management cycle to obtain a data evaluation result;

[0151] A management module is used to perform data quality management on the new energy data based on the data evaluation result.

[0152] Optionally, in some embodiments of the present application, the verification module includes:

[0153] The verification submodule is used to verify the cleaned new energy data and obtain the data verification result;

[0154] The detection submodule is used to perform data detection on the cleaned new energy data to obtain data detection results;

[0155] A determination submodule is used to determine whether the data verification of the cleaned new energy data has passed based on the data verification result and the data detection result.

[0156] Optionally, in some embodiments of the present application, the prediction module includes:

[0157] The first prediction submodule is used to perform output prediction based on the cleaned new energy data to obtain new energy output prediction data;

[0158] The second prediction submodule is used to perform strategy prediction on the new energy output prediction data based on the improved particle swarm algorithm to obtain a target scheduling strategy.

[0159] Optionally, in some embodiments of the present application, the scheduling module includes:

[0160] A conversion submodule, used to convert the target scheduling strategy into a scheduling instruction set;

[0161] A scheduling submodule is used to schedule the power of the distributed new energy system based on the scheduling instruction set. In one embodiment, a computer device is provided, and the internal structure diagram of the computer device can be as follows Fig.11 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of a power dispatching method for a distributed new energy system.

[0162] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0163] Acquire new energy data; clean the new energy data; verify the cleaned new energy data; if the data verification passes, perform strategy prediction on the cleaned new energy data to obtain a target scheduling strategy; and schedule the power of the distributed new energy system based on the target scheduling strategy.

[0164] In this embodiment, the quality and consistency of the data are ensured by cleaning the new energy data and verifying the cleaned new energy data; once the data verification is passed, the power of the new energy system is dispatched based on the target dispatch strategy predicted by the cleaned new energy data. It can be seen that by using the target dispatch strategy predicted by the new energy data after data cleaning and verification to dispatch the power of the new energy system, it is beneficial to reduce the dispatch risk of the power dispatch of the new energy system, thereby improving the accuracy and reliability of power dispatch.

[0165] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0166] Acquire new energy data; clean the new energy data; verify the cleaned new energy data; if the data verification passes, perform strategy prediction on the cleaned new energy data to obtain a target scheduling strategy; and schedule the power of the distributed new energy system based on the target scheduling strategy.

[0167] In this embodiment, the quality and consistency of the data are ensured by cleaning the new energy data and verifying the cleaned new energy data; once the data verification is passed, the power of the new energy system is dispatched based on the target dispatch strategy predicted by the cleaned new energy data. It can be seen that by using the target dispatch strategy predicted by the new energy data after data cleaning and verification to dispatch the power of the new energy system, it is beneficial to reduce the dispatch risk of the power dispatch of the new energy system, thereby improving the accuracy and reliability of power dispatch.

[0168] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0169] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0170] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0171] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A power dispatching method for a distributed new energy system, characterized in that: include: Obtain new energy data; Performing data cleaning on the new energy data; Verify the cleaned new energy data; If the data verification is passed, the cleaned new energy data will be used for strategy prediction to obtain the target scheduling strategy; The electric power of the distributed new energy system is dispatched based on the target dispatching strategy.

2. The power dispatching method of a distributed new energy system according to claim 1, characterized in that: The obtaining of new energy data includes: Receive distribution transformer data; Identifying the data source of the distribution transformer data; According to the source identification result, the new energy data is obtained from the distribution transformer data.

3. The power dispatching method of a distributed new energy system according to claim 1, characterized in that: The data cleaning of the new energy data includes: Identify and record all target data sources in the new energy data; Extracting raw data from each of the target data sources; Performing a first data cleaning on the original data to obtain normalized data; Performing format conversion on the normalized data to obtain target analysis data; Performing anomaly detection on the target analysis data to obtain anomaly detection results; A second data cleaning is performed on the target analysis data based on the abnormality detection result.

4. The power dispatching method of a distributed new energy system according to claim 1 or 3, characterized in that: Before performing data cleaning on the new energy data, the method further includes: Dividing the new energy data into stages based on the data type of the new energy data to obtain a stage division management cycle; Evaluate the new energy data based on the divided management cycle to obtain a data evaluation result; Data quality management is performed on the new energy data based on the data evaluation result.

5. The power dispatching method of a distributed new energy system according to claim 1, characterized in that: The data verification of the cleaned new energy data includes: Perform data verification on the cleaned new energy data to obtain data verification results; Perform data detection on the cleaned new energy data to obtain data detection results; Based on the data verification result and the data detection result, it is determined whether the data verification of the cleaned new energy data passes.

6. The power dispatching method of a distributed new energy system according to claim 1, characterized in that: The strategy prediction of the cleaned new energy data to obtain the target scheduling strategy includes: Perform output prediction based on the cleaned new energy data to obtain new energy output prediction data; Based on the improved particle swarm algorithm, the new energy output forecast data is subjected to strategic forecasting to obtain a target scheduling strategy.

7. The power dispatching method of a distributed new energy system according to claim 1, characterized in that: The method of scheduling the power of the distributed new energy system based on the target scheduling strategy includes: Converting the target scheduling strategy into a scheduling instruction set; The power of the distributed new energy system is dispatched based on the dispatch instruction set.

8. A power dispatching device for a distributed new energy system, characterized in that: include: An acquisition module is used to acquire new energy data; A cleaning module, used for cleaning the new energy data; A verification module is used to verify the cleaned new energy data; The prediction module is used to make a strategy prediction on the cleaned new energy data to obtain the target scheduling strategy if the data verification passes; The scheduling module is used to schedule the power of the distributed new energy system based on the target scheduling strategy.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power dispatching method for a distributed new energy system as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the power dispatching method of the distributed new energy system as claimed in any one of claims 1 to 7 are implemented.

Images