Intelligent micro-grid new energy centralized scheduling system

The intelligent microgrid dispatching system addresses data inaccuracies by using a centralized dispatching system with modules for data collection, processing, and control to enhance scheduling reliability and efficiency.

CN119093361APending Publication Date: 2024-12-06SUIZHOU POWER SUPPLY COMPANY STATE GRID HUBEI ELECTRIC POWER
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411297079.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

Microgrid renewable energy scheduling is unreliable due to inaccurate data, leading to unnecessary energy loss and economic waste.

Method used

An intelligent microgrid new energy centralized dispatching system comprising a data acquisition module, data processing module, decision support module, dispatch control module, and monitoring feedback module, which collects, processes, and analyzes data using algorithms to optimize scheduling and control.

Benefits of technology

Accurately collects and processes data to optimize dispatching strategies, reducing energy loss and economic waste by ensuring reliable and efficient energy management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119093361A_ABST
    Figure CN119093361A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of power systems, and discloses an intelligent micro-grid new energy centralized scheduling system, which is characterized in that micro-grid new energy data is acquired through a data acquisition module; the data processing module carries out data abnormal value detection, data missing value processing, data denoising and data normalization processing on the collected data through an algorithm formula, and the decision support module carries out analysis and prediction based on the processed data and provides a decision basis. And the scheduling control module carries out scheduling and control on the system according to the suggestion of the decision support module, calculates real-time power scheduling and transmits a scheduling instruction and a control execution result to the monitoring feedback module, and the monitoring feedback module carries out real-time power scheduling on the system according to the suggestion of the decision support module. And the monitoring feedback module continuously monitors the system operation efficiency, the equipment operation state and the accident alarm information, and feeds back the monitoring result to the data acquisition module to form closed-loop control.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a smart microgrid new energy centralized dispatching system. Background Art

[0002] A microgrid refers to a small-scale power system that can independently provide power supply and load management within a local area. Its main function is to support multiple types of energy, including the integration and scheduling of traditional energy and renewable energy. The new energy of a microgrid usually refers to electricity sources based on renewable energy, such as solar energy, wind energy, geothermal energy, biomass energy, etc. These energy sources have the advantages of being renewable, environmentally friendly and low-emission. By using low-emission renewable energy, microgrids can significantly reduce greenhouse gas emissions and help address global climate change. In addition, microgrids combined with energy storage systems can reduce power fluctuations, improve power quality, and further reduce negative impacts on the environment.

[0003] Currently, microgrid renewable energy scheduling relies on massive amounts of data, including load forecasts, meteorological data, and equipment status. If the data is inaccurate, the scheduling strategy may be unreasonable, which will lead to unnecessary energy loss and economic waste. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies of the prior art, the present invention provides an intelligent microgrid new energy centralized dispatching system, which has a data acquisition module that uses sensors to collect solar power generation data, wind power generation data, battery energy storage status, grid voltage, grid current, grid power, ambient temperature and ambient humidity. The data processing module uses an algorithm formula to detect data anomalies, process data missing values, denoise data and normalize data on the collected data. The decision support module analyzes and predicts based on the processed data, provides a basis for decision-making, and performs short-term load forecasting through an algorithm formula. , Medium-term load forecast , Energy Supply Forecast and economic dispatch optimization , and generate decision suggestions. The dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch The dispatching instructions and control execution results are transmitted to the monitoring feedback module. The monitoring feedback module continuously monitors the system operation efficiency, equipment operation status and accident alarm information, and feeds back the monitoring results to the data acquisition module to form a closed-loop control. Through the combination of the above modules, data can be accurately collected for analysis and calculation, and the dispatching strategy can be reasonably arranged, which avoids unnecessary energy loss and economic waste, and solves the above problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent microgrid new energy centralized dispatching system, comprising a data acquisition module, a data processing module, a decision support module, a dispatching control module and a monitoring feedback module;

[0008] The data acquisition module collects solar power generation data, wind power generation data, battery energy storage status, grid voltage, grid current, grid power, ambient temperature and ambient humidity through sensors, and transmits the collected data to the data processing module through the network;

[0009] The data processing module performs data outlier detection, data missing value processing, data denoising and data normalization processing on the collected data through an algorithm formula, and transmits the processed data to the decision support module;

[0010] The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and performs short-term load forecasting through algorithm formulas. , Medium-term load forecast , Energy Supply Forecast and economic dispatch optimization , and generate decision suggestions to be passed to the scheduling control module;

[0011] The dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch and transmit the dispatching instructions and control execution results to the monitoring feedback module;

[0012] The monitoring feedback module continuously monitors the system operating efficiency, equipment operating status and accident alarm information, and feeds back the monitoring results to the data acquisition module to form a closed-loop control.

[0013] Preferably, the data processing module performs data outlier detection on the collected data through an algorithm formula, and the data outlier detection formula is as follows:

[0014]

[0015] In the formula, represents the outlier detection data, Represents the observed value, which refers to the data point that needs to be judged as an outlier. Represents the sample mean, which represents the average level of the data set. It is calculated by summing up all the data points and averaging them. It represents the sample standard deviation, which reflects the degree of dispersion of the data set. When calculating, take the square of the difference between each data point and the mean, calculate the mean and then take the square root. When the absolute value of is greater than 3, the data point is considered an outlier.

[0016] Preferably, the data processing module performs data missing value processing on the collected data through an algorithm formula, and the data missing value processing formula is as follows:

[0017]

[0018] In the formula, Represents the data value after filling. represents the number of non-missing values, Represents every known data value.

[0019] Preferably, the data processing module performs data denoising on the collected data through an algorithm formula, and the data denoising formula is as follows:

[0020]

[0021] In the formula, Indicates The sliding average of the positions, Indicates the size of the sliding window. The smoothing value at each time point is approximately Time point is used to reduce the impact of random noise.

[0022] Preferably, the data processing module normalizes the collected data through an algorithm formula, and the data normalization formula is as follows:

[0023]

[0024] In the formula, represents the normalized data, Represents the original data value, and Represents the minimum and maximum values ​​in the data set. This formula scales the original data to the range of [0, 1] to eliminate the magnitude differences between different features.

[0025] Preferably, the decision support module performs analysis and prediction based on the processed data, provides decision-making basis, and performs short-term load forecasting through algorithm formulas. , the calculation formula is as follows:

[0026]

[0027] In the formula, represents the target variable for short-term load forecasting, represents a constant term, represents the autoregressive coefficient, represents the sliding mean coefficient, represents the error term.

[0028] Preferably, the decision support module performs analysis and prediction based on the processed data, provides decision-making basis, and performs medium-term load forecasting through algorithm formulas. , the calculation formula is as follows:

[0029]

[0030] In the formula, represents the medium-term load forecast, represents the intercept term, represents the regression coefficient of each feature, represents the independent variable, represents the error term.

[0031] Preferably, the decision support module performs analysis and prediction based on the processed data, provides decision-making basis, and performs energy supply prediction through algorithm formula , the calculation formula is as follows:

[0032]

[0033] In the formula, represents the energy supply forecast, represents the activation function, Represents the weight matrix, which represents the strength of connecting nodes in each layer. represents the input features, Represents the bias term.

[0034] Preferably, the decision support module performs analysis and prediction based on the processed data, provides decision-making basis, and optimizes economic dispatch through algorithm formulas. , the calculation formula is as follows:

[0035]

[0036] In the formula, represents economic dispatch optimization, Indicates The unit cost of the power supply, Indicates The power generated by a power source.

[0037] Preferably, the dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch , the calculation formula is as follows:

[0038]

[0039] In the formula, represents real-time power scheduling, Indicates The unit cost of the power supply, Indicates The power generated by the power source, Indicates The unit emission cost of the power source.

[0040] Compared with the prior art, the present invention provides a smart microgrid new energy centralized dispatching system, which has the following beneficial effects:

[0041] The present invention uses sensors to collect solar power generation data, wind power generation data, battery energy storage status, grid voltage, grid current, grid power, ambient temperature and ambient humidity through a data acquisition module. The data processing module performs data abnormal value detection, data missing value processing, data denoising and data normalization processing on the collected data through an algorithm formula. The decision support module analyzes and predicts based on the processed data, provides a basis for decision-making, and performs short-term load forecasting through an algorithm formula. , Medium-term load forecast , Energy Supply Forecast and economic dispatch optimization , and generate decision suggestions. The dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch The dispatching instructions and control execution results are transmitted to the monitoring feedback module. The monitoring feedback module continuously monitors the system operation efficiency, equipment operation status and accident alarm information, and feeds back the monitoring results to the data acquisition module to form a closed-loop control. Through the combination of the above modules, data can be accurately collected for analysis and calculation, and the dispatching strategy can be reasonably arranged to avoid unnecessary energy loss and economic waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0043] 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 only 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.

[0044] In view of the current situation that the dispatch of microgrid renewable energy relies on massive data, including load forecast, meteorological data and equipment status, the dispatch strategy may be unreasonable when the data is inaccurate, which will lead to unnecessary energy loss and economic waste. Therefore, a smart microgrid renewable energy centralized dispatch system is proposed. Figure 1 ,The system includes a data acquisition module, a data processing module, a decision support module, a scheduling control module and a monitoring feedback module;

[0045] The data acquisition module is an important component of the microgrid system. Its main function is to obtain important parameters related to renewable energy generation and energy storage in real time. Through a series of high-precision sensors, the data acquisition module can comprehensively and accurately collect various data to support subsequent energy management and decision-making, including:

[0046] Solar power generation data uses intelligent monitoring sensors on photovoltaic panels to periodically collect the power generation of each photovoltaic module. This not only includes the total power generation, but also allows for detailed analysis of power generation efficiency in different time periods and weather conditions. These data help optimize the operating efficiency of the photovoltaic system and perform preventive maintenance.

[0047] Wind power generation data monitors the output power of wind turbines in real time through anemometers and wind vanes. At the same time, sensors also collect data such as wind speed, wind direction and turbine speed in the surrounding environment to cope with the impact of wind changes on power generation capacity. This information can help optimize wind energy utilization and equipment maintenance scheduling;

[0048] Battery energy storage status monitors the battery's charge and discharge status, remaining power, number of cycles, temperature and other parameters. Through temperature sensors and current sensors, it can analyze the battery's health status and performance in real time, which is crucial to extending the battery's service life and improving storage efficiency.

[0049] Grid voltage and current: Voltage and current sensors are used to monitor the voltage and current levels of the grid in real time to assess the grid’s operating status. These data are important for supporting load management, ensuring power quality, and preventing grid failures.

[0050] The grid power uses power sensors to calculate the grid power demand and power output in real time, ensuring that the microgrid can efficiently manage power distribution and respond to load changes and power generation fluctuations in a timely manner;

[0051] Environmental temperature and humidity use environmental monitoring sensors to obtain temperature and humidity information of the surrounding environment. These data not only affect the power generation efficiency of renewable energy, but also provide a basis for system operation optimization;

[0052] The collected data information is transmitted to the data processing module through the high-speed and reliable communication network LoRa. This real-time transmission ensures that the system can quickly receive updated data, thereby supporting timely scheduling and management decisions;

[0053] The data processing module performs data outlier detection, data missing value processing, data denoising and data normalization processing on the collected data through algorithm formulas, including:

[0054] The data outlier detection formula is as follows:

[0055]

[0056] Data outlier detection can timely identify and process outliers in sensor data, such as faults, noise, or erroneous readings caused by extreme weather conditions, thereby improving system reliability and stability, avoiding reliance on erroneous or inaccurate data for scheduling decisions, and reducing the risk of system failures. In the formula, represents the outlier detection data, Represents the observed value, which refers to the data point that needs to be judged as an outlier. Represents the sample mean, which represents the average level of the data set. It is calculated by summing up all the data points and averaging them. It represents the sample standard deviation, which reflects the degree of dispersion of the data set. When calculating, take the square of the difference between each data point and the mean, calculate the mean and then take the square root. When the absolute value of is greater than 3, the data point is considered an outlier. By performing outlier detection on the data, we can ensure that the collected data meets the standards in terms of accuracy and effectiveness, which will help improve the accuracy of subsequent data analysis and provide a more reliable basis for decision support and strategy optimization.

[0057] The formula for processing missing data values ​​is as follows:

[0058]

[0059] Processing missing values ​​can enhance data integrity, enabling the system to more comprehensively obtain and analyze key parameters and ensure that operational decisions are based on reliable and complete data sets, which is essential for accurate scheduling and resource management. In the formula, Represents the data value after filling. represents the number of non-missing values, Represents each known data value. By processing missing values, the continuity of data can be maintained, providing strong support for subsequent data analysis and modeling. This helps the intelligent dispatching system to make more accurate load forecasts, power generation dispatching and energy management decisions, and improve overall operational efficiency.

[0060] The data denoising formula is as follows:

[0061]

[0062] Denoising can significantly improve the accuracy and reliability of data, ensuring that the data set used for decision-making reduces human interference and random fluctuations, which is crucial for energy management and scheduling that rely on accurate data. In the formula, Indicates The sliding average of the positions, Indicates the size of the sliding window. The smoothing value at each time point is approximately Time point The average is used to reduce the impact of random noise. By filtering out the noise data, the system can more effectively learn the real pattern in the data, thereby improving the accuracy of load forecasting, power generation forecasting and other key indicators, which helps to optimize resource allocation and scheduling strategies;

[0063] The data normalization formula is as follows:

[0064]

[0065] Data normalization can convert data of different dimensions and units into a unified standard range, making the variables comparable. This is very important for analysis and decision-making using multiple parameters at the same time, such as power generation, demand load, temperature, etc. In the formula, represents the normalized data, Represents the original data value, and Represents the minimum and maximum values ​​in the data set. This formula scales the original data to the range of [0, 1], eliminating the magnitude differences between different features. Normalization reduces the numerical deviation in the processing flow, making the calculation process of the optimization algorithm simpler and more efficient. In particular, when processing large-scale data, normalization can significantly save computing resources and time.

[0066] The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and performs short-term load forecasting through algorithm formulas. , Medium-term load forecast , Energy Supply Forecast and economic dispatch optimization , and generate decision recommendations, where:

[0067] The short-term load forecasting formula is as follows:

[0068]

[0069] Short-term load forecasting can help system operators understand future electricity demand in advance, so as to effectively allocate resources, ensure the balance of electricity supply and demand, and avoid power outages caused by overload. In the formula, represents the target variable for short-term load forecasting, represents a constant term, represents the autoregressive coefficient, represents the sliding mean coefficient, Represents the error term. Through accurate load forecasting, the microgrid system can optimize the scheduling of power generation resources in different time periods, improve the utilization rate of renewable energy, and reasonably schedule energy storage facilities to manage charging and discharging.

[0070] The medium-term load forecast formula is as follows:

[0071]

[0072] Since the power generation of renewable energy is affected by environmental factors, medium-term load forecasting can help the system better integrate these fluctuating resources, improve its power generation efficiency, and reduce dependence on traditional fossil fuels. In the formula, represents the medium-term load forecast, represents the intercept term, represents the regression coefficient of each feature, represents the independent variable, Represents the error term. With reliable medium-term load forecasting, the system can formulate flexible dispatching strategies to cope with possible demand changes in the future, which enables the system to better adapt to market changes and user needs.

[0073] The energy supply forecast formula is as follows:

[0074]

[0075] Accurate energy supply forecasting can help microgrid systems better dispatch and utilize available energy resources, ensure the effective use of energy, and thus maximize the value of resources. In the formula, represents the energy supply forecast, represents the activation function, Represents the weight matrix, which represents the strength of connecting nodes in each layer. represents the input features, Represents the bias term. By understanding the future energy supply capacity, the dispatching system can optimize the output of each power generation unit, reasonably arrange the matching of power generation and load, and improve the economy and reliability of the overall operation;

[0076] The economic dispatch optimization formula is as follows:

[0077]

[0078] Economic dispatch optimization can identify and utilize the lowest-cost power resources, thereby minimizing the cost of energy production and distribution and improving the economic benefits of the system. In the formula, represents economic dispatch optimization, Indicates The unit cost of the power supply, Indicates The power generation capacity of various power sources can be optimized through scheduling, so that the system can use available power generation resources more efficiently, including renewable energy, traditional energy and energy storage facilities, to ensure that resources are optimally configured, thereby reducing waste;

[0079] The dispatch control module dispatches and controls the system according to the suggestions of the decision support module and calculates the real-time power dispatch. , and transmit the scheduling instructions and control execution results to the monitoring feedback module, where:

[0080] The real-time power scheduling formula is as follows:

[0081]

[0082] Real-time power dispatch can quickly respond to changes in power demand, ensure timely increase in power supply during peak demand periods, reduce power generation during low demand periods, and optimize the overall operation of the system. In the formula, represents real-time power scheduling, Indicates The unit cost of the power supply, Indicates The power generated by the power source, Indicates The unit emission cost of each power source. Through real-time scheduling, the system can effectively avoid instability caused by load fluctuations, reduce the risk of power overload or shortage, and thus improve the stability of the power grid;

[0083] The monitoring feedback module continuously monitors the system operating efficiency, equipment operating status and accident alarm information, sets up alarm systems of different levels, and can automatically trigger corresponding alarms based on the collected data to ensure that accidents are discovered in a timely manner. Once an abnormality is found, the system automatically records and sends an alarm message to the operator, and pushes the information to different communication channels according to the configured priority, and feeds back the monitoring results to the data acquisition module to form a closed-loop control. The monitoring results are fed back to the data acquisition module in real time through the efficient data transmission network LoRa to ensure the efficiency and accuracy of information flow. All feedback data follows the unified format XML to facilitate subsequent analysis and processing, and ensure interoperability across modules. By combining historical data and real-time feedback information, the closed-loop control system is continuously optimized to enhance the system's adaptability under different load conditions.

[0084] Through the combination of the above modules, data can be accurately collected for analysis and calculation, and scheduling strategies can be reasonably arranged to avoid unnecessary energy losses and economic waste.

[0085] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart microgrid new energy centralized dispatching system, characterized by: It includes data acquisition module, data processing module, decision support module, dispatch control module and monitoring feedback module; The data acquisition module collects solar power generation data, wind power generation data, battery energy storage status, grid voltage, grid current, grid power, ambient temperature and ambient humidity through sensors, and transmits the collected data to the data processing module through the network; The data processing module performs data outlier detection, data missing value processing, data denoising and data normalization processing on the collected data through an algorithm formula, and transmits the processed data to the decision support module; The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and performs short-term load forecasting through algorithm formulas. , Medium-term load forecast , Energy Supply Forecast and economic dispatch optimization , and generate decision suggestions to be passed to the scheduling control module; The dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch and transmit the scheduling instructions and control execution results to the monitoring feedback module; The monitoring feedback module continuously monitors the system operating efficiency, equipment operating status and accident alarm information, and feeds back the monitoring results to the data acquisition module to form a closed-loop control.

2. According to claim 1, a smart microgrid new energy centralized dispatching system is characterized by: The data processing module performs data outlier detection on the collected data through an algorithm formula. The data outlier detection formula is as follows: , in the formula, represents the outlier detection data, Represents the observed value, which refers to the data point that needs to be judged as an outlier. Represents the sample mean, which represents the average level of the data set. It is calculated by summing up all the data points and averaging them. It represents the sample standard deviation, which reflects the degree of dispersion of the data set. When calculating, take the square of the difference between each data point and the mean, calculate the mean and then take the square root. When the absolute value of is greater than 3, the data point is considered an outlier.

3. The intelligent microgrid new energy centralized dispatching system according to claim 2 is characterized by: The data processing module processes the missing data using an algorithm formula. The missing data processing formula is as follows: , in the formula, Represents the data value after filling. represents the number of non-missing values, Represents every known data value.

4. The intelligent microgrid new energy centralized dispatching system according to claim 3 is characterized by: The data processing module performs data denoising on the collected data through an algorithm formula. The data denoising formula is as follows: , in the formula, Indicates The sliding average of the positions, Indicates the size of the sliding window. The smoothing value at each time point is approximately Time point is used to reduce the impact of random noise.

5. The intelligent microgrid new energy centralized dispatching system according to claim 4 is characterized by: The data processing module normalizes the collected data through an algorithm formula. The data normalization formula is as follows: , in the formula, represents the normalized data, Represents the original data value, and Represents the minimum and maximum values ​​in the data set. This formula scales the original data to the range of [0, 1] to eliminate the magnitude differences between different features.

6. The intelligent microgrid new energy centralized dispatching system according to claim 5 is characterized by: The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and performs short-term load forecasting through algorithm formulas. , the calculation formula is as follows: , in the formula, represents the target variable for short-term load forecasting, represents a constant term, represents the autoregressive coefficient, represents the sliding mean coefficient, represents the error term.

7. The intelligent microgrid new energy centralized dispatching system according to claim 6 is characterized by: The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and performs medium-term load forecasting through algorithm formulas. , the calculation formula is as follows: , in the formula, represents the medium-term load forecast, represents the intercept term, represents the regression coefficient of each feature, represents the independent variable, represents the error term.

8. The intelligent microgrid new energy centralized dispatching system according to claim 7 is characterized by: The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and predicts energy supply through algorithm formulas , the calculation formula is as follows: , in the formula, represents the energy supply forecast, represents the activation function, Represents the weight matrix, which represents the strength of connecting nodes in each layer. represents the input features, Represents the bias term.

9. The intelligent microgrid new energy centralized dispatching system according to claim 8, characterized in that: The decision support module analyzes and predicts based on the processed data, provides decision-making basis, and optimizes economic dispatch through algorithm formulas , the calculation formula is as follows: , in the formula, represents economic dispatch optimization, Indicates The unit cost of the power supply, Indicates The power generated by a power source.

10. The intelligent microgrid new energy centralized dispatching system according to claim 9, characterized in that: The dispatch control module performs system dispatch and control according to the suggestions of the decision support module and calculates the real-time power dispatch , the calculation formula is as follows: , in the formula, represents real-time power scheduling, Indicates The unit cost of the power supply, Indicates The power generated by the power source, Indicates The unit emission cost of the power source.

Citation Information

Cited By

  • Energy storage system state monitoring method based on wireless communication

    CN119738725A

  • New energy scheduling intelligent monitoring analysis regulation and control method

    CN120834642A

  • A new energy scheduling intelligent monitoring analysis and control method

    CN120834642B