Intelligent dispatching method and system based on multi-source microgrid fluctuation prediction

Abstract

The present application discloses an intelligent dispatching method and system based on multi-source microgrid fluctuation prediction, which relates to the field of smart grid technology. The multi-source microgrid includes at least three subgrids, each of which corresponds to a type of renewable energy. The method includes: acquiring physical data of various types of renewable energy in real time, and determining the fluctuation mode of each type of energy based on the physical data; constructing a neural network model for each type of energy according to the fluctuation mode, which is used to predict power generation fluctuation data; based on the fluctuation data and the real-time load of each subgrid, dynamically adjusting the energy storage system and power output of each subgrid. In addition, the method also achieves the optimal allocation of surplus power by calculating the power supply status of each subgrid, and adopts a weighted calculation method based on volatility scoring and physical property scoring to determine the power supply priority of the subgrid. The present application improves the stability and energy utilization efficiency of multi-source microgrids, and is suitable for intelligent management and dispatching of large-scale multi-source microgrids.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a smart scheduling method and system based on multi-source microgrid fluctuation prediction. Background Art

[0002] Since multi-source microgrids integrate multiple types of renewable energy (such as solar energy, wind energy, hydropower, etc.), their grid-connected control technology is particularly important. However, due to the different power generation characteristics of different types of renewable energy, how to achieve stable and efficient grid-connected control is still a technical problem that needs to be solved urgently.

[0003] For example, the Chinese patent with the authorization announcement number CN115021318B discloses a multi-support source microgrid grid-connected synchronous control method and system. The method includes obtaining the voltage signals of the grid side and the microgrid side of the isolated island main switch of the microgrid with multiple support sources, and calculating the amplitude deviation, frequency deviation and phase deviation of the voltage information of the grid side and the microgrid side according to the voltage signals on both sides; performing PI adjustment according to the frequency deviation and phase deviation to obtain the frequency adjustment instruction, and at the same time judging whether the frequency deviation and phase deviation meet the first judgment condition, if they meet, the amplitude deviation of the voltage is adjusted, and if they do not meet, the deviations are recalculated; according to the amplitude deviation adjustment, the amplitude adjustment instruction is obtained, and at the same time judging whether the amplitude deviation, frequency deviation and phase deviation meet the second judgment condition, if they meet, the grid-connected closing control instruction is issued, and the frequency adjustment instruction and the amplitude adjustment instruction are set to zero, and if they do not meet, the deviations are recalculated. The method can realize the seamless switching of the multi-support source microgrid from the isolated island state to the grid-connected state, and is suitable for applications in the field of microgrids.

[0004] However, the above method has some shortcomings. This method mainly relies on the deviation of voltage, frequency and phase for control, and lacks real-time prediction and intelligent scheduling mechanism for fluctuations in power generation of various types of renewable energy. This leads to the fact that when there are large fluctuations in the power generation of multi-source renewable energy, the system's response speed and regulation accuracy may be insufficient, making it difficult to achieve optimal power resource allocation. Secondly, the PI regulation strategy in the existing method may not fully consider the mutual influence between various types of energy when facing a complex multi-source microgrid environment, thereby affecting the overall stability and operation efficiency of the microgrid. Therefore, there is an urgent need for a multi-source microgrid grid-connected method based on real-time data acquisition and intelligent prediction to solve the deficiencies in the existing technology and improve the stability and energy utilization efficiency of the microgrid. Summary of the invention

[0005] In view of the shortcomings of the existing technology, this application discloses an intelligent dispatching method and system based on multi-source microgrid fluctuation prediction. It aims to achieve efficient and stable grid-connected control of multi-source microgrids by dynamically adjusting the energy storage system and power output of each sub-grid by acquiring the physical data of various renewable energy sources in real time and combining intelligent prediction models.

[0006] In a first aspect, the present application provides an intelligent scheduling method based on multi-source microgrid fluctuation prediction, wherein the multi-source microgrid includes at least three subgrids; each of the subgrids corresponds to a type of renewable energy, and the method includes:

[0007] Acquire physical data of each type of renewable energy in real time; determine fluctuation patterns of each type of renewable energy based on the physical data of each type of renewable energy;

[0008] Based on the fluctuation patterns of the various types of renewable energy, a neural network model for predicting the fluctuation data of power generation of the various types of renewable energy is constructed for each type of renewable energy;

[0009] For the physical data of each type of renewable energy, a neural network model corresponding to each type of renewable energy is used to perform fluctuation prediction to generate fluctuation data;

[0010] Based on the fluctuation data and the real-time load of each subgrid, the energy storage system and power output of each subgrid are dynamically adjusted.

[0011] As an optional implementation, the dynamically adjusting the energy storage system and power output of each subgrid includes:

[0012] Determine the power supply status of each subgrid based on the fluctuation data and the real-time load of each subgrid;

[0013] The power supply status includes: surplus status, sufficient status, and insufficient status;

[0014] In response to the subgrid being in the insufficient power supply state, the subgrid in the insufficient power supply state is powered by the subgrid in the surplus power supply state.

[0015] As an optional implementation manner, determining the power supply status of each subgrid includes:

[0016] Determine the power generation and power generation demand of each subgrid based on the fluctuation data and the real-time load of each subgrid;

[0017] In response to the existence of the power generation of the subgrid exceeding the power generation demand, and the excess value is greater than or equal to a first threshold, marking the subgrid as being in a surplus state;

[0018] In response to the existence of the power generation of the subgrid exceeding the power generation demand, and the excess value is less than a first threshold, marking the subgrid as being in a sufficient state;

[0019] In response to the generation demand of the subgrid exceeding the generation capacity, the subgrid is marked as being in a deficit state.

[0020] As an optional implementation manner, supplying power to the subgrid in an insufficient state includes:

[0021] Determining the power supply priority of each sub-grid in a surplus state based on the fluctuation data corresponding to each sub-grid in a surplus state;

[0022] The subgrid with the highest priority among the available power supply priorities is used for power supply.

[0023] As an optional implementation manner, determining the power supply priority of each sub-grid in the surplus state includes:

[0024] Determining a volatility score of each of the subgrids based on the volatility data of each of the subgrids in a surplus state;

[0025] Determining a physical characteristic score of each of the subgrids based on the physical data of the renewable energy sources corresponding to each of the surplus state subgrids;

[0026] Based on the volatility score and the physical characteristic score of each of the subgrids, the power supply priority of each of the subgrids in the surplus state is weightedly calculated.

[0027] As an optional implementation manner, the volatility score is calculated based on a dynamic time period; and determining the volatility score of each of the subgrids includes:

[0028] Based on the real-time load of each of the subgrids, the calculation time period of the volatility score is adjusted; wherein, the closer the real-time load of the subgrid is to a preset load threshold of the subgrid, the shorter the calculation time period of the volatility score is.

[0029] As an optional implementation manner, determining the physical characteristic score of each subgrid includes:

[0030] The renewable energy includes: solar energy, wind energy, and water energy;

[0031] In response to the renewable energy corresponding to the subgrid being solar energy, the physical property score is based on current light intensity and sunshine duration, and the higher the light intensity, the higher the physical property score;

[0032] In response to the renewable energy corresponding to the subgrid being wind energy, the physical characteristic score is based on the current wind speed; wherein, when the wind speed is within a preset power generation interval, the physical characteristic score is the highest; in response to the wind speed being lower than or higher than the preset power generation interval, the physical characteristic score gradually decreases based on the magnitude of the wind speed deviation from the preset power generation interval;

[0033] In response to the renewable energy corresponding to the subgrid being hydropower, the physical characteristic score is based on current water flow and water storage; wherein, the closer the water flow and water storage are to preset target values, the higher the physical characteristic score is.

[0034] In a second aspect, the present application also provides an intelligent dispatching system based on multi-source microgrid fluctuation prediction, including: a collection unit, a construction unit, a prediction unit, and a dispatching unit; wherein:

[0035] The acquisition unit is used to acquire the physical data of each type of renewable energy in real time; based on the physical data of each type of renewable energy, determine the fluctuation mode of each type of renewable energy;

[0036] The construction unit is used to construct a neural network model for predicting the power generation fluctuation data of each type of renewable energy based on the fluctuation mode of each type of renewable energy.

[0037] The prediction unit is used to perform fluctuation prediction on the physical data of each type of renewable energy by using the neural network model corresponding to each type of renewable energy to generate fluctuation data;

[0038] The dispatching unit is used to dynamically adjust the energy storage system and power output of each sub-grid based on the fluctuation data and the real-time load of each sub-grid.

[0039] Compared with the prior art, the beneficial effects of this application are: by acquiring the physical data of various types of renewable energy in real time and combining it with an intelligent prediction model, it is possible to accurately predict power generation fluctuations and dynamically adjust the energy storage system and power output, thereby significantly improving the response speed and energy utilization efficiency of the microgrid. In addition, a weighted calculation method based on volatility scoring and physical property scoring is introduced to achieve more intelligent power supply distribution, ensuring that subgrids with high power generation stability and superior physical conditions are given priority in providing power support, effectively responding to the complex fluctuation characteristics of various types of renewable energy in multi-source microgrids, and maintaining the overall stability and efficient operation of the system.

[0040] By deeply analyzing the fluctuation patterns of various energy sources and using dedicated neural network models for prediction and scheduling, the problems of insufficient response speed and regulation accuracy of traditional methods when dealing with large-scale multi-source microgrid fluctuations are solved, the reliability and operation efficiency of microgrids are significantly improved, and the optimal allocation and utilization of power resources are ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of an intelligent scheduling method based on multi-source microgrid fluctuation prediction provided in an embodiment of the present application;

[0042] Figure 2 A flow chart of a method for determining the power supply status of each sub-grid provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of an intelligent dispatching system based on multi-source microgrid fluctuation prediction provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0045] In this disclosure, grid-connected refers to the process of connecting a power generation system (such as solar energy, wind energy or other distributed energy) to the public power grid. A grid-connected system can directly transmit the generated electricity to the grid to share with other power sources, or obtain electricity from the grid when the power generation is insufficient.

[0046] See also Figure 1 As shown, it is a flow chart of an intelligent scheduling method based on multi-source microgrid fluctuation prediction provided by an embodiment of the present application, wherein the multi-source microgrid includes at least three subgrids; each of the subgrids corresponds to a type of renewable energy; the method includes steps S101 to S104, wherein:

[0047] S101: acquiring physical data of each type of renewable energy in real time; and determining fluctuation patterns of each type of renewable energy based on the physical data of each type of renewable energy;

[0048] S102: Based on the fluctuation patterns of the various types of renewable energy, respectively construct a neural network model for predicting the fluctuation data of power generation of the various types of renewable energy;

[0049] S103: For physical data of each type of renewable energy, using a neural network model corresponding to each type of renewable energy to perform fluctuation prediction to generate fluctuation data;

[0050] S104: Dynamically adjust the energy storage system and power output of each subgrid based on the fluctuation data and the real-time load demand of each subgrid.

[0051] The multi-source microgrid involved in this application includes at least three subgrids, each of which is associated with different types of renewable energy. The type of renewable energy can be solar energy, wind energy, hydropower or other types of clean energy. The subgrids can achieve coordinated power supply through intelligent scheduling to ensure the stability of the entire microgrid system.

[0052] Regarding S101 above:

[0053] In a specific implementation, corresponding physical parameter sensors and data acquisition devices can be deployed in each subgrid to achieve comprehensive monitoring of different types of renewable energy.

[0054] For solar subgrids, light intensity sensors, ambient temperature sensors and solar radiometers are installed at key locations such as photovoltaic arrays and solar thermal collectors. These sensors can collect physical data such as light intensity, ambient temperature, solar radiation intensity and sunshine duration in real time. The collected data is transmitted to the local controller or central control system via wired (such as Ethernet, optical fiber) or wireless (such as Wi-Fi, ZigBee, LoRa) communication.

[0055] In the wind energy subgrid, ultrasonic anemometers, mechanical cup anemometers, and wind vanes are installed at wind turbines and wind towers. These sensors monitor key parameters such as wind speed, wind direction, air pressure, temperature, and humidity in real time.

[0056] For the hydropower subgrid, water level meters, flow meters, pressure sensors and temperature sensors are arranged at key locations such as the water inlet, outlet and dam of the hydropower station. These sensors can obtain physical data such as water level, water flow, pressure and water temperature in real time, and transmit them to the control room or remote monitoring center through high-speed communication methods such as industrial Ethernet and optical fiber.

[0057] During the data collection process, it is necessary to set a reasonable sampling frequency to meet the real-time requirements of different energy types. For example, the data sampling frequency of the solar subgrid can be set to once per minute, the wind subgrid can be set to multiple times per second, and the hydropower subgrid dynamically adjusts the sampling frequency according to the changes in water flow. In addition, the sensor node can also be configured with a data cache module to prevent data loss when communication is interrupted, and a real-time communication protocol is used to ensure real-time data transmission.

[0058] After the data is transmitted to the central control system, the received physical data is preprocessed, for example, including data cleaning, calibration and time synchronization. Data cleaning removes outliers and noise through filtering algorithms (such as mean filtering and Kalman filtering) to ensure the smoothness and accuracy of the data. Data calibration corrects the data according to the sensor's calibration curve and environmental factors to eliminate system errors. Time synchronization aligns data from different sources through timestamps or synchronized clocks to ensure data synchronization and consistency.

[0059] After completing data preprocessing, based on the real-time physical data, feature extraction is first performed. For solar energy, by analyzing the trend of light intensity changes, features such as sunshine peak, slope and fluctuation frequency are extracted; for wind energy, the mean, variance and spectrum characteristics of wind speed are calculated to identify the periodicity and randomness of wind speed changes; for hydropower, the rate of change of water flow and water level fluctuations are evaluated to identify seasonal and sudden change characteristics. Subsequently, the system uses machine learning algorithms (such as cluster analysis, support vector machine) or signal processing methods (such as wavelet analysis, Fourier transform) to analyze the extracted features and identify the fluctuation patterns of various types of renewable energy.

[0060] Regarding S102 above:

[0061] In the specific implementation, for the solar power subgrid, a Long Short-Term Memory (LSTM) model can be constructed using the identified fluctuation pattern. Due to its advantages in processing time series data, the LSTM model can effectively capture the daily periodic changes and short-term fluctuation characteristics of solar power generation, thereby achieving accurate prediction of future power generation. For the wind power subgrid, since its power generation is greatly affected by wind speed and wind direction and has high volatility, a hybrid model combining a convolutional neural network (CNN) and LSTM can be used. CNN is used to extract spatial features from wind speed data, while LSTM is used to capture dynamic changes in time, which improves the accuracy of wind power generation fluctuation prediction. For the hydropower subgrid, considering that the changes in water flow and water level are relatively stable but still have seasonal and sudden fluctuations, a recurrent neural network (RNN) can be selected as the prediction model. RNN can effectively handle the medium- and long-term fluctuation trend of hydropower generation and adapt to its seasonal changes and the impact of incidental events.

[0062] For example, in the training process of the model, taking the LSTM model of the solar power subgrid as an example, the preprocessed time series data can be input into the model, and the model parameters can be optimized through multiple rounds of iterative training so that it can accurately capture the periodic changes and short-term fluctuations of solar power generation. The CNN-LSTM hybrid model of the wind power subgrid is trained in stages, first using the CNN layer to extract the spatial features of the wind speed data, and then inputting the extracted features into the LSTM layer for time series prediction. The RNN model of the hydropower subgrid processes the time dependence of water flow and water level through a recursive structure to adapt to changes in its fluctuation pattern. During the training process, the mean square error (MSE) can be used as the loss function, and the Adam optimization algorithm can be used to accelerate convergence and improve training efficiency.

[0063] In addition, after training, the neural network model can be deployed to the central control system or edge computing node to achieve real-time power generation fluctuation prediction. By continuously inputting real-time physical data, the trained model is used to generate power generation fluctuation prediction data for a period of time in the future. These prediction data will be used to guide the charging and discharging strategy of the energy storage system and the dynamic adjustment of power output, ensuring that the microgrid can maintain stable and efficient operation when dealing with renewable energy fluctuations.

[0064] Regarding S103 above:

[0065] In the specific implementation, the constructed neural network model is used to analyze the physical data of various types of renewable energy to generate predicted power generation fluctuation data. This power generation fluctuation data can be used to evaluate the power generation capacity of each sub-grid and provide a basis for subsequent energy storage and output adjustments.

[0066] Regarding S104 above:

[0067] Based on the fluctuation data and the real-time load conditions of each subgrid, the charging and discharging status and power output of the energy storage system are dynamically adjusted. The flexible adjustment of the energy storage system can cope with the volatility of various types of renewable energy and improve energy efficiency. By matching power output with real-time demand, energy waste or shortage can be avoided, thereby maintaining the overall stability and efficient operation of the microgrid.

[0068] As an optional implementation, in the intelligent scheduling method based on multi-source microgrid fluctuation prediction of the present application, the process of dynamically adjusting the energy storage system and power output of each subgrid further includes judging and scheduling the power supply status of each subgrid.

[0069] In a specific implementation, the power supply status of each subgrid is determined based on the fluctuation data and the real-time load of each subgrid. The power supply status can be divided into three types: surplus status, sufficient status and insufficient status, where:

[0070] Surplus state: The power generation of a subgrid exceeds the current load demand, and the excess power generation can be supplied to other subgrids.

[0071] Sufficient state: The power generation of a sub-grid basically matches the current load demand, with neither excess nor shortage, and can balance the power supply demand autonomously.

[0072] Insufficient state: The power generation of a subgrid is insufficient to meet the current load demand and requires additional power support from other subgrids.

[0073] When a subgrid is detected to be in a state of insufficient power, it will automatically search for a subgrid in a state of surplus power. The subgrid in a state of surplus power can supply power to the subgrid in a state of insufficient power through the intelligent dispatching system to maintain the stable operation of the entire microgrid.

[0074] Specifically, when a subgrid is short of power, it will send a power request to other subgrids through the communication network. In response, the subgrid with surplus power will provide power support based on its own power generation capacity and energy storage status, thereby ensuring that the subgrid with insufficient power can restore its power supply capacity and avoid the risk of load power outage or overload.

[0075] See also Figure 2 As shown, it is a flow chart of a method for determining the power supply status of each sub-grid provided in an embodiment of the present application, the method comprising steps S201 to S204, wherein:

[0076] S201: Determine the power generation and power generation demand of each subgrid based on the fluctuation data and the real-time load of each subgrid;

[0077] S202: In response to the power generation of a certain subgrid exceeding the power generation demand, and the excess value is greater than or equal to a first threshold, marking the subgrid as being in a surplus state;

[0078] S203: In response to the power generation of a certain subgrid exceeding the power generation demand, and the excess value is less than a first threshold, marking the subgrid as being in a sufficient state;

[0079] S204: In response to the power generation demand of a certain subgrid exceeding the power generation, marking the subgrid as being in a shortage state.

[0080] In the specific implementation, the power generation and power generation demand of each sub-grid are first collected in real time. For example, the power generation can be measured by the power metering device, which represents the actual power output of renewable energy (such as solar energy, wind energy, and hydropower) in the sub-grid; while the power generation demand is obtained through the load detection device, which represents the power required in the current sub-grid to maintain the normal operation of all loads.

[0081] For example, for a solar subgrid, the current power generation can be collected in real time through a power sensor connected to a photovoltaic inverter, and the power demand of all electrical devices in the subgrid can be detected through a load controller.

[0082] The power supply status is determined based on the difference between the power generation and power generation demand of each sub-grid. This difference reflects the power supply and demand balance of the sub-grid and serves as the basis for judgment.

[0083] When the power generation is greater than the power generation demand, the difference is compared with a preset "first threshold". The threshold is dynamically set based on historical data and system requirements. For example, the threshold may be determined based on the system's power supply safety margin or the charging capacity of the energy storage device.

[0084] In a specific implementation, when the power generation of a subgrid exceeds the power generation demand, and the excess value is greater than or equal to the first threshold, the subgrid is marked as being in a "surplus state". The surplus state means that the subgrid can not only meet its own load demand, but also provide power support for other subgrids with insufficient load.

[0085] For example, when the wind speed is high, the power generation of a wind subgrid may greatly exceed the load demand, and the excess can be stored or transmitted to other subgrids. At this time, the subgrid can be marked as surplus to ensure that its surplus power can be quickly identified and used during subsequent power supply scheduling.

[0086] When the power generation of a subgrid exceeds the power generation demand, but the excess value is less than the first threshold, the subgrid is marked as being in a "sufficient state". The sufficient state indicates that the power generation of the subgrid is basically balanced with its load demand, but its power generation is not enough to provide additional power to other subgrids.

[0087] For example, when the water flow of a hydroelectric subgrid is moderate, its power generation can maintain the normal operation of the subgrid, but there is no excess power to be stored or exported to other subgrids.

[0088] When the power generation demand of a subgrid exceeds the power generation, the subgrid is marked as "insufficient". Insufficient state means that the power generation of the subgrid cannot meet the current load demand, which may cause load power outage or system instability, and it is necessary to obtain power support from other subgrids in surplus state.

[0089] For example, when the intensity of sunlight decreases, the power generation of the solar subgrid may not be sufficient to support the operation of all loads. At this time, the subgrid can be marked as insufficient and automatically seek other subgrids in surplus state to provide power supplement.

[0090] The first threshold is dynamically adjusted based on the historical power generation and load data of the multi-source microgrid to ensure that the surplus power resources are maximized without wasting energy. For example, the threshold can be set based on factors such as the capacity of the energy storage system, the load characteristics of the subgrid, and the fluctuation of power generation.

[0091] For example, if the energy storage system capacity of a subgrid is relatively small, the first threshold value may be set relatively low to ensure that the subgrid does not waste energy due to surplus power exceeding the storage capacity.

[0092] In this way, through detailed analysis of power generation and demand, the power supply status of each subgrid can be quickly and accurately judged to ensure the rational allocation of energy resources. This method can effectively deal with the uncertainty of power generation caused by fluctuations in renewable energy, avoid power shortages or waste, and further improve the reliability and operation efficiency of microgrids.

[0093] As an optional implementation, the powering of the sub-grid in the insufficient state includes: determining the power supply priority of each sub-grid in the surplus state based on the fluctuation data corresponding to each sub-grid in the surplus state; and using the sub-grid with the highest priority among the power supply priorities for powering.

[0094] In the specific implementation, when a subgrid is in a state of shortage, all subgrids in a state of surplus are first identified, and the fluctuation data of these subgrids are obtained. The fluctuation data represents the changing trend of the power generation of each subgrid in a specific period of time. By analyzing these data, the power generation stability and sustainability of each surplus subgrid in the future period of time can be determined.

[0095] For example, a wind power subgrid is currently in a surplus state, but according to its fluctuation data (such as wind speed fluctuation), the power generation of this subgrid may fluctuate greatly in the future, making it difficult to continuously provide stable power. Therefore, when scheduling power supply, the system may give priority to subgrids with less volatility and more stable power generation.

[0096] In the specific implementation, the power supply priority of each redundant subgrid is calculated based on the fluctuation data of each redundant subgrid. The priority can be determined based on the following factors:

[0097] Power generation stability: Subgrids with relatively stable fluctuation data usually have a higher power supply priority because these subgrids can maintain continuous power generation for a longer period of time during the power supply process, reducing the risk of load fluctuations.

[0098] Power generation capacity: Subgrids with larger current power generation and energy storage capacity will also be given higher priority to ensure sufficient power is provided to subgrids with insufficient power.

[0099] Energy storage status: If the energy storage device of a redundant subgrid is fully charged, its priority may also be increased, because continuing to store electricity at this time will lead to waste, and it is better to distribute the electricity to other subgrids.

[0100] For example, two subgrids in a surplus state are detected: the wind subgrid and the hydro subgrid. The wind subgrid has a large power generation capacity but high volatility; the hydro subgrid has a relatively small power generation capacity but stable power generation. Based on this data, the hydro subgrid can be given a higher power supply priority.

[0101] In the specific implementation, the subgrid with the highest priority is selected to supply power to the subgrid in a state of insufficient power. Through this priority sorting, it can ensure that the power dispatch in the microgrid is more reasonable, which can not only meet the needs of the insufficient subgrid, but also avoid the waste of power.

[0102] In this way, accurate and efficient power distribution can be achieved during the power supply dispatching process. The mechanism of determining priority based on fluctuation data ensures that the sub-grids in insufficient state get the most stable power support first, avoiding the problem of secondary power supply shortage caused by excessive fluctuation.

[0103] As an optional implementation manner, determining the power supply priority of each sub-grid in the surplus state includes:

[0104] Determining a volatility score of each of the subgrids based on the volatility data of each of the subgrids in a surplus state;

[0105] Determining a physical characteristic score of each of the subgrids based on the physical data of the renewable energy sources corresponding to each of the surplus state subgrids;

[0106] Based on the volatility score and the physical characteristic score of each of the subgrids, the power supply priority of each of the subgrids in the surplus state is weightedly calculated.

[0107] As an optional implementation manner, determining the physical characteristic score of each subgrid includes:

[0108] The renewable energy includes: solar energy, wind energy, and water energy;

[0109] In response to the renewable energy corresponding to the subgrid being solar energy, the physical property score is based on current light intensity and sunshine duration, and the higher the light intensity, the higher the physical property score;

[0110] In response to the renewable energy corresponding to the subgrid being wind energy, the physical characteristic score is based on the current wind speed; wherein, when the wind speed is within a preset power generation interval, the physical characteristic score is the highest; in response to the wind speed being lower than or higher than the preset power generation interval, the physical characteristic score gradually decreases based on the magnitude of the wind speed deviation from the preset power generation interval;

[0111] In response to the renewable energy corresponding to the subgrid being hydropower, the physical characteristic score is based on current water flow and water storage; wherein, the closer the water flow and water storage are to preset target values, the higher the physical characteristic score is.

[0112] In practice, the volatility score is used to assess the power generation stability of each surplus state subgrid. The system calculates the score based on the volatility data of each subgrid, which reflects the changes in power generation of various renewable energy sources (such as wind, solar, and hydro) over a specific period of time.

[0113] The volatility score can be calculated by analyzing the historical power generation data of a subgrid. If the power generation of the subgrid fluctuates greatly in a short period of time, its volatility score will be low; if the power generation is relatively stable, the volatility score will be high.

[0114] For example, a wind subgrid may have a low volatility score because its power generation fluctuates dramatically when wind speeds are more unstable, whereas a hydropower subgrid may have a higher volatility score because its water flow is relatively stable.

[0115] In a specific implementation, the physical characteristic score is used to evaluate the current physical conditions of the renewable energy of each surplus state subgrid. The physical characteristic score is determined by analyzing the physical data of the renewable energy corresponding to the subgrid, including the light intensity of solar energy, the wind speed of wind energy, the water flow of water energy, etc., where:

[0116] Solar subgrid: The higher the light intensity, the higher the physical property score. Light intensity can be assessed in real time based on factors such as sunshine duration and cloud cover.

[0117] Wind energy subgrid: When the wind speed is in the ideal power generation range, the physical characteristics score is the highest; if the wind speed deviates from this range, the score will decrease.

[0118] Hydropower subgrid: The closer the water flow and storage are to the preset ideal state, the higher the physical property score.

[0119] For example, when the wind speed is in the optimal power generation range (such as 7-15 m / s), the physical characteristics score of the wind energy subgrid is high; if the wind speed is too high or too low, the score will be reduced.

[0120] It can be understood that the above-mentioned optimal power generation interval is the preset power generation interval.

[0121] In the specific implementation, the power supply priority of each surplus state subgrid is obtained by weighted calculation of the volatility score and the physical characteristic score. The weighted calculation formula can be adjusted according to actual needs. For example, if a subgrid has low volatility and good power generation stability, its volatility score weight can be increased; in certain cases, if the physical characteristic score shows that the subgrid has abundant energy resources, the weight of the physical characteristic score can be increased.

[0122] According to the results of weighted calculation, the subgrid with higher priority will first provide power to the subgrid with insufficient power. This multi-dimensional priority evaluation method enables the system to select the most suitable subgrid for power supply when the power generation capacity and stability of different subgrids are different.

[0123] In this way, the power generation volatility and physical characteristics are comprehensively considered when prioritizing the power supply of the subgrids in the surplus state. This method effectively improves the utilization efficiency of power resources and minimizes the impact of renewable energy fluctuations on power supply while maintaining the stability of the microgrid.

[0124] As an optional implementation manner, the volatility score is calculated based on a dynamic time period; and determining the volatility score of each of the subgrids includes:

[0125] Based on the real-time load of each of the subgrids, the calculation time period of the volatility score is adjusted; wherein, the closer the real-time load of the subgrid is to a preset load threshold of the subgrid, the shorter the calculation time period of the volatility score is.

[0126] In the specific implementation, the real-time load data of each sub-grid is first obtained, and the calculation time period of the volatility score is dynamically adjusted according to the data.

[0127] In the specific implementation, when the real-time load of the subgrid is closer to the preset load threshold, it means that the load pressure of the subgrid is greater, and the power generation fluctuation needs to be monitored more frequently. Therefore, the calculation period of the volatility score is shortened to capture more subtle fluctuation changes and facilitate timely adjustment of the power supply strategy.

[0128] When the real-time load of the subgrid is low and far from the load threshold, it means that the subgrid is operating relatively loosely. The calculation time period can be appropriately extended to focus on long-term fluctuation trends and reduce unnecessary frequent adjustments.

[0129] In a specific implementation, each subgrid has a preset load threshold, which can be set according to the design capacity or safe operation standard of the subgrid.

[0130] Calculate the ratio of the real-time load to the load threshold to get the load proximity. For example, if the real-time load is 90% of the threshold, it means the load proximity is 90%. According to the load proximity, set the corresponding calculation time period. The higher the load proximity, the shorter the calculation time period. You can preset a mapping relationship or use a linear function to adjust it.

[0131] During the adjusted calculation period, the power generation data of the subgrid is collected and the volatility score is calculated using statistical methods. For example, the standard deviation, variance or other volatility indicators of the power generation during the period can be calculated.

[0132] For example, the load threshold of a wind power subgrid is 1000kW, the current real-time load is 950kW, and the load proximity is 95%. According to the preset rules, when the load proximity exceeds 90%, the calculation time period is set to 10 minutes. The system collects power generation data in the last 10 minutes and calculates the volatility score to reflect the power generation stability under the current high load.

[0133] For example, the load threshold of a hydropower subgrid is 800kW, the current real-time load is 400kW, and the load proximity is 50%. At this time, the calculation period can be set to 60 minutes to focus on the power generation fluctuations over a longer period of time.

[0134] The volatility score obtained after dynamically adjusting the calculation time period can better reflect the power generation stability of the subgrid under different load conditions. Under high load conditions, the score is more sensitive and can detect potential power supply risks in a timely manner; under low load conditions, the score is smoother to avoid unnecessary adjustments due to short-term fluctuations.

[0135] Exemplarily, the relationship between the calculation time period T and the load proximity D can be set as:

[0136]

[0137] in, is the maximum calculation time period, and are the minimum and maximum load proximity, respectively.

[0138] Collect power generation data within a certain calculation period , calculate the volatility score S:

[0139]

[0140] Where N is the total number of sampling points, indicating the number of power generation data points collected during the calculation period, i is the index of the sampling point, and the value range is i = 1, 2, 3, ..., N, To calculate the average power generation during the time period, yes The power generation at the moment.

[0141] In this way, the calculation time period of the volatility score can be dynamically adjusted according to the real-time load of the subgrid, so that the score results more accurately reflect the power generation volatility of the subgrid under different load levels. Under high load conditions, shortening the calculation time period can capture power generation fluctuations in a timely manner and respond quickly to potential power supply problems; under low load conditions, extending the calculation time period can reduce frequent adjustments and improve system operation efficiency.

[0142] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0143] Based on the same inventive concept, an intelligent dispatching system based on multi-source microgrid fluctuation prediction is also provided in the embodiments of the present application. Since the principle of solving the problem by the system in the embodiments of the present application is similar to the above-mentioned intelligent dispatching method based on multi-source microgrid fluctuation prediction in the embodiments of the present application, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be repeated.

[0144] Reference Figure 3 As shown, it is a schematic diagram of an intelligent dispatching system based on multi-source microgrid fluctuation prediction provided by an embodiment of the present application, wherein the multi-source microgrid includes at least three subgrids; each of the subgrids corresponds to a type of renewable energy, and the system includes: a collection unit 10, a construction unit 20, a prediction unit 30, and a dispatching unit 40; wherein:

[0145] The acquisition unit 10 is used to acquire the physical data of each type of renewable energy in real time; based on the physical data of each type of renewable energy, determine the fluctuation mode of each type of renewable energy;

[0146] The construction unit 20 is used to construct a neural network model for predicting the power generation fluctuation data of each type of renewable energy based on the fluctuation mode of each type of renewable energy.

[0147] The prediction unit 30 is used to perform fluctuation prediction on the physical data of each type of renewable energy by using the neural network model corresponding to each type of renewable energy to generate fluctuation data;

[0148] The dispatching unit 40 is used to dynamically adjust the energy storage system and power output of each sub-grid based on the fluctuation data and the real-time load of each sub-grid.

[0149] For descriptions of the processing flow of each unit in the system and the interaction flow between each unit, reference may be made to the relevant descriptions in the above method embodiments, which will not be described in detail here.

[0150] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0151] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0152] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present disclosure, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. An intelligent dispatching method based on multi-source microgrid fluctuation prediction, characterized in that: The multi-source microgrid includes at least three subgrids; each of the subgrids corresponds to a type of renewable energy, and the method includes: Acquire physical data of each type of renewable energy in real time; determine fluctuation patterns of each type of renewable energy based on the physical data of each type of renewable energy; Based on the fluctuation patterns of the various types of renewable energy, a neural network model for predicting the fluctuation data of power generation of the various types of renewable energy is constructed for each type of renewable energy; For the physical data of each type of renewable energy, a neural network model corresponding to each type of renewable energy is used to perform fluctuation prediction to generate fluctuation data; Based on the fluctuation data and the real-time load of each subgrid, the energy storage system and power output of each subgrid are dynamically adjusted; the dynamic adjustment of the energy storage system and power output of each subgrid also includes: determining the volatility score of each subgrid based on the fluctuation data of each subgrid; determining the physical characteristic score of each subgrid based on the change information of the physical data of the renewable energy corresponding to each subgrid; wherein the change information includes: light change information, wind speed change information, and water flow change information; based on the volatility score and physical characteristic score of each subgrid, weighted calculation of the power supply priority of each subgrid; wherein the volatility score is calculated based on a dynamic time period; the determination of the volatility score of each subgrid includes: adjusting the calculation time period of the volatility score based on the real-time load of each subgrid; wherein, the closer the real-time load of the subgrid is to the preset load threshold of the subgrid, the shorter the calculation time period of the volatility score; The dynamic adjustment of the energy storage system and power output of each sub-grid includes: Determine the power supply status of each subgrid based on the fluctuation data and the real-time load of each subgrid; The power supply status includes: surplus status, sufficient status, and insufficient status; In response to the subgrid being in the insufficient power supply state, supplying power to the subgrid in the insufficient power supply state by using the subgrid in the surplus power supply state; Determining the power supply status of each sub-grid includes: Determine the power generation and power generation demand of each subgrid based on the fluctuation data and the real-time load of each subgrid; In response to the existence of the power generation of the subgrid exceeding the power generation demand, and the excess value is greater than or equal to a first threshold, marking the subgrid as being in a surplus state; In response to the existence of the power generation of the subgrid exceeding the power generation demand, and the excess value is less than a first threshold, marking the subgrid as being in a sufficient state; In response to the generation demand of the subgrid exceeding the generation capacity, the subgrid is marked as being in a deficit state.

2. The method according to claim 1, characterized in that The supplying power to the insufficient subgrid includes: Determining the power supply priority of each sub-grid in a surplus state based on the fluctuation data corresponding to each sub-grid in a surplus state; The subgrid with the highest priority among the available power supply priorities is used for power supply.

3. The method according to claim 2, characterized in that Determining the power supply priority of each sub-grid in the surplus state includes: Determining a volatility score of each of the subgrids based on the volatility data of each of the subgrids in the surplus state; Determining a physical characteristic score of each of the subgrids based on the physical data of the renewable energy sources corresponding to each of the surplus state subgrids; Based on the volatility score and the physical characteristic score of each of the subgrids, the power supply priority of each of the subgrids in the surplus state is weightedly calculated.

4. The method according to claim 3, characterized in that Determining the physical characteristic score of each of the sub-grids includes: The renewable energy includes: solar energy, wind energy, and water energy; In response to the renewable energy corresponding to the subgrid being solar energy, the physical property score is based on current light intensity and sunshine duration, and the higher the light intensity, the higher the physical property score; In response to the renewable energy corresponding to the subgrid being wind energy, the physical characteristic score is based on the current wind speed; wherein, when the wind speed is within a preset power generation interval, the physical characteristic score is the highest; in response to the wind speed being lower than or higher than the preset power generation interval, the physical characteristic score gradually decreases based on the magnitude of the wind speed deviation from the preset power generation interval; In response to the renewable energy corresponding to the subgrid being hydropower, the physical characteristic score is based on current water flow and water storage; wherein, the closer the water flow and water storage are to preset target values, the higher the physical characteristic score is.

5. Intelligent dispatching system based on multi-source microgrid fluctuation prediction, characterized by: Execute the intelligent dispatching method based on multi-source microgrid fluctuation prediction as described in any one of claims 1 to 4; The multi-source microgrid includes at least three subgrids; each of the subgrids corresponds to a type of renewable energy, and the system includes: a collection unit, a construction unit, a prediction unit, and a scheduling unit; wherein, The acquisition unit is used to acquire the physical data of each type of renewable energy in real time; based on the physical data of each type of renewable energy, determine the fluctuation mode of each type of renewable energy; The construction unit is used to construct a neural network model for predicting the power generation fluctuation data of each type of renewable energy based on the fluctuation mode of each type of renewable energy. The prediction unit is used to perform fluctuation prediction on the physical data of each type of renewable energy by using the neural network model corresponding to each type of renewable energy to generate fluctuation data; The dispatching unit is used to dynamically adjust the energy storage system and power output of each subgrid based on the fluctuation data and the real-time load of each subgrid; the dynamic adjustment of the energy storage system and power output of each subgrid also includes: determining the volatility score of each subgrid based on the fluctuation data of each subgrid; determining the physical characteristic score of each subgrid based on the change information of the physical data of the renewable energy corresponding to each subgrid; wherein the change information includes: light change information, wind speed change information, and water flow change information; based on the volatility score and physical characteristic score of each subgrid, weighted calculation of the power supply priority of each subgrid; wherein the volatility score is calculated based on a dynamic time period; the determination of the volatility score of each subgrid includes: adjusting the calculation time period of the volatility score based on the real-time load of each subgrid; wherein, the closer the real-time load of the subgrid is to the preset load threshold of the subgrid, the shorter the calculation time period of the volatility score.

Images