Microgrid stability enhancing method and system based on ocean energy
By using load and generation forecasting and multi-energy complementary dispatch, the problems of generation intermittency and volatility when marine energy is integrated into the microgrid have been solved, thereby improving the stability and power supply reliability of the microgrid.
Patent Information
- Application Number
- CN202511777241.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-04-03
AI Technical Summary
The intermittent and fluctuating power generation of ocean energy when integrated into microgrids leads to power imbalance, reduced operational stability, and decreased power supply reliability in microgrids.
By forecasting load and generation, multi-energy complementary optimal scheduling is carried out. Load forecasting is performed using LSTM networks. Combined with ocean energy generation characteristic forecasting and environmental forecasting, ocean energy generation strategies are generated for multi-energy complementary scheduling and stability enhancement.
It effectively mitigates power fluctuations and improves the reliability and operational stability of microgrid power supply.
Smart Images
Figure CN121791309A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of microgrid technology, specifically to a method and system for enhancing the stability of microgrids based on ocean energy. Background Technology
[0002] Microgrids, as a flexible and efficient distributed energy system, have demonstrated significant advantages in improving energy utilization efficiency and enhancing power supply reliability. However, the stable operation of microgrids faces numerous challenges, especially as the proportion of renewable energy continues to increase. Their inherent intermittency and volatility can easily lead to problems such as system frequency deviation and voltage fluctuations, seriously affecting the power quality and operational safety of microgrids. Ocean energy, including wave energy, tidal energy, and ocean thermal energy conversion, is a renewable energy source with abundant resources and strong predictability. Compared with wind and solar energy, ocean energy has higher energy density and good spatiotemporal complementarity, possessing unique development value, especially in coastal and island areas. However, ocean energy power generation systems are also affected by natural conditions, resulting in output fluctuations. Direct connection to microgrids may exacerbate system instability. How to effectively utilize ocean energy to participate in the optimal scheduling of microgrids and improve system stability has become an important aspect of the current energy field. Traditional methods have not paid enough attention to the stability-enhancing role of ocean energy in microgrids, relying on real-time scheduling and energy storage compensation, lacking forward-looking utilization of the characteristics of ocean energy generation, and making it difficult to achieve optimal matching of multiple energy sources under complex operating conditions.
[0003] Therefore, current technologies present technical challenges related to the intermittency and volatility of ocean energy generation when integrated into microgrids, leading to power imbalances, reduced operational stability, and decreased power supply reliability in microgrids. Summary of the Invention
[0004] This application provides a method and system for enhancing the stability of microgrids based on ocean energy. It solves the technical problems in the prior art where the intermittency and volatility of power generation when ocean energy is connected to a microgrid lead to power imbalance, reduced operational stability and power supply reliability of the microgrid. It achieves the technical effect of effectively smoothing power fluctuations and improving the power supply reliability and operational stability of the microgrid through forward-looking load and power generation forecasting and multi-energy complementary optimal scheduling.
[0005] This application provides a method for enhancing the stability of a microgrid based on ocean energy. The method includes: forecasting the load of the microgrid according to a future time zone to obtain the microgrid load demand; forecasting the power generation characteristics of the ocean energy power generation system according to the future time zone to obtain an ocean energy power generation forecast map; performing multi-energy complementary scheduling of the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation forecast map to obtain an ocean energy power generation strategy; enhancing the stability of the microgrid according to the ocean energy power generation strategy to obtain an optimized power generation strategy; and managing the power supply of the microgrid according to the ocean energy power generation system based on the optimized power generation strategy.
[0006] In a possible implementation, the microgrid stability enhancement method based on ocean energy further performs the following processing: acquiring real-time load data and historical load datasets of the microgrid; performing supervised training on an LSTM network based on the historical load dataset to obtain a load prediction model; and using the load prediction model to predict the load of the microgrid based on the real-time load data and the future time zone to obtain the microgrid load demand.
[0007] In a possible implementation, the microgrid stability enhancement method based on ocean energy also performs the following processing: real-time monitoring of multiple ocean energy power generation units within the ocean energy power generation system to obtain monitoring data for each power generation unit; based on the future time zone, predicting the power generation characteristics of the multiple ocean energy power generation units according to the monitoring data of each power generation unit to obtain the power generation characteristic prediction results for each unit; and organizing the power generation characteristic prediction results of each unit to generate the ocean energy power generation prediction map.
[0008] In a possible implementation, the microgrid stability enhancement method based on ocean energy further performs the following processing: data cleaning of the monitoring data of each power generation unit to obtain a monitoring feature set for each unit; predicting the power generation environment of the multiple ocean energy power generation units based on the future time zone to obtain an environmental feature set for each unit; and fitting the power generation characteristic trend of the multiple ocean energy power generation units based on the environmental feature set of each unit and the monitoring feature set of each unit to generate the power generation characteristic prediction result of each unit.
[0009] In a possible implementation, the microgrid stability enhancement method based on ocean energy further performs the following processing: performing multi-energy complementary scheduling on the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation prediction map to obtain a set of ocean energy power generation schemes; fitting the power generation resource utilization rate of the ocean energy power generation scheme set to obtain the resource utilization rate of each scheme; and performing optimization analysis on the ocean energy power generation scheme set based on the resource utilization rate of each scheme to generate the ocean energy power generation strategy.
[0010] In a possible implementation, the microgrid stability enhancement method based on ocean energy further performs the following processes: digitally modeling the microgrid and the ocean energy power generation system to obtain a microgrid ocean power generation model; performing simulation control on the microgrid ocean power generation model according to the ocean energy power generation strategy to obtain microgrid simulation data; and optimizing the ocean energy power generation strategy based on the microgrid simulation data to generate the optimized power generation strategy.
[0011] In a possible implementation, the ocean energy-based microgrid stability enhancement method also performs the following processing: the data cleaning includes removing duplicate data, handling missing values, outlier detection, and data standardization.
[0012] This application also provides a microgrid stability enhancement system based on ocean energy, the system comprising: a load forecasting module for forecasting the microgrid load based on a future time zone to obtain the microgrid load demand; a power generation characteristic forecasting module for forecasting the power generation characteristics of the ocean energy power generation system based on the future time zone to obtain an ocean energy power generation forecast map; a complementary scheduling module for performing multi-energy complementary scheduling of the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation forecast map to obtain an ocean energy power generation strategy; a stability enhancement module for enhancing microgrid stability based on the ocean energy power generation strategy to obtain an optimized power generation strategy; and a power supply management module for managing the power supply of the microgrid based on the optimized power generation strategy and the ocean energy power generation system.
[0013] This application proposes a method and system for enhancing microgrid stability based on ocean energy. The method involves: forecasting microgrid load demand based on future time zones; predicting the generation characteristics of the ocean energy power generation system to obtain a forecast map; implementing multi-energy complementary scheduling of the ocean energy power generation system to obtain an ocean energy generation strategy; enhancing microgrid stability based on the ocean energy generation strategy to obtain an optimized generation strategy; and managing the microgrid's power supply based on the optimized generation strategy. This addresses the technical problems in existing technologies where the intermittency and volatility of ocean energy generation when integrated into the microgrid lead to power imbalance, reduced operational stability, and decreased power supply reliability. The method achieves the technical effect of effectively mitigating power fluctuations and improving the power supply reliability and operational stability of the microgrid through forward-looking load and generation forecasting and multi-energy complementary optimized scheduling. Attached Figure Description
[0014] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.
[0015] Figure 1 This is a schematic diagram of the process for enhancing the stability of a microgrid based on ocean energy, provided in an embodiment of this application.
[0016] Figure 2 A schematic diagram of the structure of a microgrid stability enhancement system based on ocean energy provided in this application embodiment.
[0017] Explanation of reference numerals in the attached diagram: Load forecasting module 10, power generation characteristic forecasting module 20, complementary dispatching module 30, stability enhancement module 40, power supply management module 50. Detailed Implementation
[0018] To further illustrate the technical means and effects adopted by the present invention in order to achieve the intended purpose, the following detailed description is provided in conjunction with the accompanying drawings and preferred embodiments, based on the specific implementation methods, structures, features and effects of the present invention.
[0019] This application provides a method for enhancing the stability of microgrids based on ocean energy, such as... Figure 1 As shown, the method includes:
[0020] Step S100: Perform load forecasting on the microgrid based on the future time zone to obtain the microgrid load demand.
[0021] Step S100 further includes step S110, acquiring real-time load data and historical load dataset of the microgrid; step S120, performing supervised training on the LSTM network based on the historical load dataset to obtain a load prediction model; and step S130, using the load prediction model to predict the load of the microgrid based on the real-time load data and the future time zone to obtain the microgrid load demand.
[0022] Preferably, the historical load dataset of the microgrid is obtained from the energy management system, smart meters, or data acquisition and monitoring control system of the microgrid. This dataset contains time-series data recorded by the microgrid over a period of time, including timestamps and corresponding total load power values. Real-time load data refers to load data at the current moment or within the most recent short period, serving as the initial state or starting point for prediction. Electricity load data is a typical time series, and its changes are not only related to the current moment but also closely related to the state over a long period of time. By using an LSTM network for supervised training on the historical load dataset, the patterns, periodicity, and correlations of load changes over time with various factors can be learned, effectively capturing the current trend and instantaneous changes in load. Specifically, a large number of input-label pairs are constructed from the historical load dataset. The input is historical load data for a continuous time window, and the label is load data for a future period within that time window. The LSTM network predicts the output based on the input data, and then compares the prediction result with the actual output label. The error is calculated, and the internal parameters of the LSTM network are automatically adjusted through backpropagation to minimize the prediction error. The LSTM network can predict future load sequences based on historical load sequences, ultimately obtaining a load prediction model.
[0023] Preferably, the future time zone is obtained, i.e. the time range that needs to be predicted, such as the next 24 hours or the next 15 minutes to 4 hours. Then, based on the real-time load data and the future time zone, the load prediction model is called to predict the load of the microgrid. After the load model runs, the predicted load sequence is output, which corresponds to the microgrid load demand in the future time zone and includes the predicted load sequence values at each time point in the future time zone.
[0024] Step S200: Based on the future time zone, predict the power generation characteristics of the ocean energy power generation system to obtain an ocean energy power generation prediction map.
[0025] Step S200 further includes step S210, which involves real-time monitoring of multiple ocean energy power generation units within the ocean energy power generation system to obtain monitoring data for each power generation unit; step S220, which involves predicting the power generation characteristics of the multiple ocean energy power generation units based on the future time zone and the monitoring data of each power generation unit to obtain prediction results for the power generation characteristics of each unit; and step S230, which involves organizing the prediction results for the power generation characteristics of each unit to generate the ocean energy power generation prediction map.
[0026] Preferably, the ocean energy power generation system includes multiple ocean energy power generation units, such as a single turbine generator in a tidal power station, a single wave energy converter in a wave energy device array, or a single wind turbine in offshore wind power. A sensor network installed on multiple ocean energy power generation units monitors them in real time to obtain monitoring data for each unit, including but not limited to power generation unit operating status data, power generation unit environmental response data, and raw environmental data. The power generation unit operating status data includes real-time output power, generator speed, voltage, current, equipment temperature, and switch status. The power generation unit environmental response data includes the displacement and acceleration of the wave energy unit's floating body, and the torque and speed of the tidal turbine blades. The raw environmental data includes real-time wave height, wave period, tidal current velocity, wind direction, and wind speed at the location of the power generation unit.
[0027] Preferably, considering the future time zone, the power generation characteristics of each ocean energy power generation unit are predicted based on monitoring data. This involves using ocean hydro-meteorological forecasting models to predict the marine environment at the specific location of each power generation unit within the future time zone. For example, wave models predict wave height, wave direction, and wave period at each unit, while tidal models predict tide level, current velocity, and current direction. Then, the power generation unit's operational data and historical environmental data are correlated and fitted, and a mapping prediction is performed based on the future marine environment, outputting the predicted power generation characteristics of each unit—that is, the predicted power output sequence of each ocean energy power generation unit over a future period. Finally, the predicted power generation characteristics of each unit are integrated, fusing spatial location and time series to generate an ocean energy power generation prediction map. For example, different colors and animations can be used to display the total power output or power density distribution of the entire ocean energy power station at different future time points.
[0028] Furthermore, step S220 also includes step S221, cleaning the monitoring data of each power generation unit to obtain a monitoring feature set for each unit; step S222, predicting the power generation environment of the multiple ocean energy power generation units based on the future time zone to obtain an environmental feature set for each unit; and step S223, fitting the power generation characteristic trend of the multiple ocean energy power generation units based on the environmental feature set of each unit and the monitoring feature set of each unit to generate the power generation characteristic prediction result of each unit.
[0029] Step S221 further includes the data cleaning process including removing duplicate data, handling missing values, outlier detection, and data standardization.
[0030] Preferably, the monitoring data of each power generation unit is cleaned, including removing duplicate data, handling missing values, detecting outliers, and standardizing data. Removing duplicate data involves deleting identical records caused by communication errors or other reasons. Handling missing values involves filling data gaps caused by temporary sensor malfunctions or data transmission packet loss, for example, by filling with the average of previous and subsequent times, interpolation, or using AI algorithms for prediction. Outlier detection identifies and handles data points that clearly do not conform to physical laws; for example, due to sensor noise or instantaneous interference, a tidal turbine may display huge power output when the flow is calm, and outliers are corrected or removed. Data standardization / normalization refers to converting power, speed, temperature, and wave height data from different sensors and with different dimensions to the same scale, significantly improving the efficiency and stability of subsequent AI model training. This results in a high-quality, structured dataset containing the cleaned historical operating status data of each power generation unit, constituting the monitoring feature set for each unit.
[0031] Preferably, the external physical conditions driving the operation of each power generation unit within the future time zone are predicted based on the marine hydrological and meteorological forecasting model. Specifically, the SWAN model, ROMS model, etc. are called and run, and global meteorological and marine data are used as input to simulate the changes in the future marine environment, provide the future environmental data of the precise geographical location of each power generation unit, and output the environmental feature set of each unit, which includes the driving factor data of each power generation unit at each time point in the future. For example, for wave energy units, the wave height, wave direction, and wave period in the future every hour; for tidal energy units, the current speed and current direction in the future every 15 minutes; and for thermal energy units, the surface water temperature and deep water temperature in the future every hour.
[0032] Preferably, the power generation characteristic trend of multiple ocean energy power generation units is fitted based on the environmental feature set and monitoring feature set of each unit. That is, the monitoring feature set of each unit is used as the output label, and the corresponding environmental feature set of each unit is used as the input feature. Random forest, gradient boosting tree or neural network is used for learning and training. A corresponding mapping model is trained for each power generation unit. The parameters are adjusted by training and learning with a large amount of data so that the predicted value is as close as possible to the true historical power value. Then, the environmental feature set of each unit in the future is input into the corresponding mapping model, and the predicted power value of the power generation unit in the future time zone is directly output as the power generation characteristic prediction result of each unit. For example, the power output prediction curve of each power generation unit based on the future environmental forecast.
[0033] Step S300: Based on the microgrid load demand and the ocean energy power generation prediction map, perform multi-energy complementary scheduling on the ocean energy power generation system to obtain an ocean energy power generation strategy.
[0034] Step S300 further includes step S310, performing multi-energy complementary scheduling of the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation prediction map to obtain a set of ocean energy power generation schemes; step S320, fitting the power generation resource utilization rate of the set of ocean energy power generation schemes to obtain the resource utilization rate of each scheme; step S330, performing optimization analysis on the set of ocean energy power generation schemes based on the resource utilization rate of each scheme to generate the ocean energy power generation strategy.
[0035] Preferably, the ocean energy power generation system is subjected to multi-energy complementary scheduling based on the microgrid load demand and ocean energy power generation forecast map. This involves combining fluctuating ocean energy with other controllable resources to meet load demand. These controllable resources include different power generation units within the ocean energy power generation system, energy storage systems, backup diesel generators, or potential photovoltaic and wind power within the microgrid. Specifically, heuristic rules are used to generate multiple different resource combination methods. For example, aggressive scheme A maximizes the utilization of ocean energy, ensuring all ocean energy units operate at near full capacity, with any shortfall supplemented by batteries, and minimizing the activation of diesel generators. Option B, a conservative approach, appropriately suppresses ocean energy output, relying more on batteries and a small number of diesel generators to cope with potential deviations in ocean energy forecasts. Option C, an economical approach, comprehensively considers diesel prices and battery wear costs to formulate the start-stop combination with the lowest operating costs. Option D, a smooth output approach, instructs certain ocean energy units to proactively reduce power during predicted peak output times to achieve more stable power output across the entire power station and reduce the impact on the power grid. The final output is a set of ocean energy power generation schemes containing multiple candidate ocean energy power generation schemes, specifying the specific actions of each ocean energy power generation unit, energy storage system, backup power source, etc., at each point in time in the future.
[0036] Preferably, the resource utilization rate of the ocean energy power generation scheme set is fitted. This involves defining multiple evaluation indicators and calculating their values based on the specific parameters of each ocean energy power generation scheme. Specifically, resource utilization rate is used as a key indicator to measure how to utilize existing resources more intelligently and efficiently. Examples include: ocean energy penetration rate (the proportion of ocean energy power generation in total electricity supply); energy storage system cycle efficiency (assessing the frequency and depth of battery charging and discharging); standby energy consumption rate (the consumption of fossil fuels such as diesel generators); curtailment rate (the amount of ocean energy wasted due to improper scheduling); and load tracking accuracy (the degree of matching between the actual power provided by the scheme and the load demand). A quantified resource utilization rate is then calculated for each ocean energy power generation scheme. Following this, an optimization analysis is performed on the ocean energy power generation scheme set based on the resource utilization rate of each scheme. This involves using genetic algorithms and particle swarm optimization to select the ocean energy power generation scheme with the highest comprehensive resource utilization rate score from all candidate schemes. This scheme is then used as the final ocean energy power generation strategy to maximize the overall resource utilization efficiency of the ocean energy system and complete the power supply task, ensuring that the microgrid's scheduling is data-driven and optimally efficient.
[0037] Step S400: Enhance the stability of the microgrid according to the ocean energy power generation strategy to obtain an optimized power generation strategy.
[0038] Step S400 further includes step S410, performing digital modeling based on the microgrid and the ocean energy power generation system to obtain a microgrid ocean power generation model; step S420, performing simulation control on the microgrid ocean power generation model according to the ocean energy power generation strategy to obtain microgrid simulation data; step S430, performing microgrid stability enhancement optimization on the ocean energy power generation strategy based on the microgrid simulation data to generate the optimized power generation strategy.
[0039] Preferably, digital modeling is performed based on the microgrid and ocean energy power generation system to obtain a microgrid ocean energy power generation model capable of simulating real physical processes. This model includes dynamic electromagnetic transient models of generators, transformers, lines, and loads; control models such as inverter control strategies, energy storage system charging and discharging logic, and grid dispatch command response models; electromechanical dynamic models of ocean energy power generation units such as wave energy converters and tidal turbines; and load dynamic characteristic models. These models are used to realistically simulate the dynamic behavior of a real microgrid under various disturbances. Then, the ocean energy power generation strategy is input into the microgrid ocean energy power generation model for simulation control, outputting a large amount of data reflecting the dynamic response of the ocean energy system. The microgrid simulation data mainly includes frequency data, voltage data, functional stability data, and equipment load data, which are used to check for frequency overruns or severe frequency fluctuations, voltage overruns or voltage flicker, generator power angle loss of synchronization, and line and transformer overloads. Next, based on microgrid simulation data, the ocean energy power generation strategy is optimized to enhance microgrid stability. Specifically, the microgrid simulation data is analyzed to identify all potential stability problems and locate the root cause dispatch instructions that lead to stability problems. Then, the ocean energy power generation strategy is automatically adjusted, such as power ramp-up rate limits, reserved spinning reserves, active peak reduction, and rearrangement of energy storage actions. Finally, an optimized power generation strategy is generated that meets both load demand and the economy / efficiency of multi-energy complementarity, while ensuring the dynamic stability of the microgrid.
[0040] Step S500: Based on the optimized power generation strategy, the microgrid is managed for power supply according to the ocean energy power generation system.
[0041] Preferably, the central controller will send the scheduling instructions in the optimized power generation strategy to the local controllers of various execution units such as the ocean energy power generation system and energy storage system in real time through the communication network. After receiving the instructions, the local controller will drive the physical equipment to accurately execute the set power commands, such as adjusting the turbine pitch angle and controlling the inverter output power. At the same time, it will continuously monitor the actual microgrid operation status, such as frequency, voltage, actual load, and actual ocean energy output. The actual operation data will be compared with the expected values of the optimized power generation strategy. If there is a slight deviation, the controller will make fine adjustments to ensure the overall power balance and stability. If a major disturbance that is not expected by the strategy occurs, such as a sudden failure of the main power generation unit or a sudden surge in load, the safety protection mechanism will be triggered. The reserved backup resources will be urgently called up and the optimized power generation strategy may be temporarily decoupled. The system will switch to an emergency control mode based on real-time data to prioritize the stability of the ocean energy power generation system, thereby achieving precise and reliable power supply management of the microgrid.
[0042] In the above text, refer to Figure 1 A method for enhancing the stability of microgrids based on ocean energy according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A microgrid stability enhancement system based on ocean energy is described according to an embodiment of the present invention.
[0043] The microgrid stability enhancement system based on ocean energy according to embodiments of the present invention addresses the technical problems existing in the prior art where the intermittency and volatility of power generation when ocean energy is integrated into a microgrid lead to power imbalance, decreased operational stability, and reduced power supply reliability. It achieves the technical effect of effectively mitigating power fluctuations and improving the power supply reliability and operational stability of the microgrid through forward-looking load and power generation forecasting and multi-energy complementary optimized scheduling. Figure 2 As shown, the microgrid stability enhancement system based on ocean energy includes: a load forecasting module 10, a power generation characteristic forecasting module 20, a complementary dispatching module 30, a stability enhancement module 40, and a power supply management module 50.
[0044] The load forecasting module 10 is used to forecast the load of the microgrid based on the future time zone to obtain the microgrid load demand; the power generation characteristic forecasting module 20 is used to forecast the power generation characteristics of the ocean energy power generation system based on the future time zone to obtain the ocean energy power generation forecast map; the complementary scheduling module 30 is used to perform multi-energy complementary scheduling of the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation forecast map to obtain the ocean energy power generation strategy; the stability enhancement module 40 is used to enhance the stability of the microgrid based on the ocean energy power generation strategy to obtain the optimized power generation strategy; and the power supply management module 50 is used to manage the power supply of the microgrid based on the optimized power generation strategy and the ocean energy power generation system.
[0045] The specific configuration of the load forecasting module 10 will be described in detail below. The load forecasting module 10 further includes: acquiring real-time load data and historical load datasets of the microgrid; performing supervised training on the LSTM network based on the historical load dataset to obtain a load forecasting model; and calling the load forecasting model to perform load forecasting on the microgrid based on the real-time load data and the future time zone to obtain the microgrid load demand.
[0046] The specific configuration of the power generation characteristic prediction module 20 will be described in detail below. The power generation characteristic prediction module 20 further includes: real-time monitoring of multiple ocean energy power generation units within the ocean energy power generation system to obtain monitoring data for each power generation unit; based on the future time zone, performing power generation characteristic prediction on the multiple ocean energy power generation units according to the monitoring data of each power generation unit to obtain the power generation characteristic prediction results for each unit; and organizing the power generation characteristic prediction results of each unit to generate the ocean energy power generation prediction map.
[0047] The specific configuration of the power generation characteristic prediction module 20 will be described in detail below. The power generation characteristic prediction module 20 further includes: cleaning the monitoring data of each power generation unit to obtain a monitoring characteristic set for each unit; predicting the power generation environment of the multiple ocean energy power generation units based on the future time zone to obtain an environmental characteristic set for each unit; and fitting the power generation characteristic trend of the multiple ocean energy power generation units based on the environmental characteristic sets of each unit, thereby generating the power generation characteristic prediction results for each unit.
[0048] The specific configuration of the complementary scheduling module 30 will be described in detail below. The complementary scheduling module 30 further includes: performing multi-energy complementary scheduling on the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation prediction map to obtain a set of ocean energy power generation schemes; fitting the resource utilization rate of the ocean energy power generation scheme set to obtain the resource utilization rate of each scheme; and performing optimization analysis on the ocean energy power generation scheme set based on the resource utilization rate of each scheme to generate the ocean energy power generation strategy.
[0049] The specific configuration of the stability enhancement module 40 will be described in detail below. The stability enhancement module 40 further includes: performing digital modeling based on the microgrid and the ocean energy power generation system to obtain a microgrid ocean energy power generation model; performing simulation control on the microgrid ocean energy power generation model according to the ocean energy power generation strategy to obtain microgrid simulation data; and performing microgrid stability enhancement optimization on the ocean energy power generation strategy based on the microgrid simulation data to generate the optimized power generation strategy.
[0050] The specific configuration of the power generation characteristic prediction module 20 will be described in detail below. The power generation characteristic prediction module 20 further includes: data cleaning, which includes removing duplicate data, handling missing values, outlier detection, and data standardization.
[0051] The ocean energy-based microgrid stability enhancement system provided in this invention can execute the ocean energy-based microgrid stability enhancement method provided in this invention, and has the corresponding functional modules and beneficial effects of the method.
[0052] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.
Claims
1. A method for enhancing the stability of microgrids based on ocean energy, characterized in that, The method includes: Based on future time zones, load forecasting of the microgrid is performed to obtain the microgrid load demand. Based on the future time zone, the power generation characteristics of the ocean energy power generation system are predicted to obtain an ocean energy power generation prediction map; Based on the microgrid load demand and the ocean energy power generation prediction map, the ocean energy power generation system is subjected to multi-energy complementary scheduling to obtain an ocean energy power generation strategy. Based on the aforementioned ocean energy power generation strategy, microgrid stability is enhanced to obtain an optimized power generation strategy; Based on the optimized power generation strategy, the microgrid is managed for power supply according to the ocean energy power generation system.
2. The method for enhancing the stability of microgrids based on ocean energy as described in claim 1, characterized in that, Based on future time zones, load forecasting of the microgrid is performed to obtain the microgrid load demand, including: Obtain the real-time load data and historical load dataset of the microgrid; The LSTM network is trained under supervision based on the historical load dataset to obtain a load prediction model. Based on the real-time load data and the future time zone, the load forecasting model is invoked to forecast the load of the microgrid and obtain the microgrid load demand.
3. The method for enhancing the stability of microgrids based on ocean energy as described in claim 1, characterized in that, Based on the future time zone, the power generation characteristics of the ocean energy power generation system are predicted to obtain an ocean energy power generation prediction map, including: Real-time monitoring is performed on multiple ocean energy power generation units within the ocean energy power generation system to obtain monitoring data for each power generation unit; Based on the future time zone, the power generation characteristics of the multiple ocean energy power generation units are predicted according to the monitoring data of each power generation unit, and the power generation characteristic prediction results of each unit are obtained. The prediction results of the power generation characteristics of each unit are compiled to generate the ocean energy power generation prediction map.
4. The method for enhancing the stability of microgrids based on ocean energy as described in claim 3, characterized in that, Based on the future time zone, the power generation characteristics of the multiple ocean energy power generation units are predicted according to the monitoring data of each power generation unit, and the prediction results of the power generation characteristics of each unit are obtained, including: Data cleaning is performed on the monitoring data of each power generation unit to obtain the monitoring feature set of each unit; Based on the future time zone, the power generation environment of the multiple ocean energy power generation units is predicted to obtain the environmental feature set of each unit; Based on the environmental feature sets of each unit, the power generation characteristic trends of the multiple ocean energy power generation units are fitted according to the monitoring feature sets of each unit, and the power generation characteristic prediction results of each unit are generated.
5. The method for enhancing the stability of microgrids based on ocean energy as described in claim 1, characterized in that, Based on the microgrid load demand and the ocean energy generation forecast map, the ocean energy generation system is subjected to multi-energy complementary scheduling to obtain an ocean energy generation strategy, including: Based on the microgrid load demand and the ocean energy power generation prediction map, the ocean energy power generation system is subjected to multi-energy complementary scheduling to obtain a set of ocean energy power generation schemes. The resource utilization rate of each ocean energy power generation scheme is fitted to the set of ocean energy power generation schemes to obtain the resource utilization rate of each scheme. Based on the resource utilization rate of each scheme, the set of ocean energy power generation schemes is optimized to generate the ocean energy power generation strategy.
6. The method for enhancing the stability of microgrids based on ocean energy as described in claim 1, characterized in that, Based on the aforementioned ocean energy power generation strategy, microgrid stability enhancement is performed to obtain an optimized power generation strategy, including: A microgrid ocean power generation model is obtained by digitally modeling the microgrid and the ocean energy power generation system. The microgrid ocean power generation model is simulated and controlled according to the ocean energy power generation strategy to obtain microgrid simulation data; The ocean energy power generation strategy is optimized by enhancing microgrid stability based on the microgrid simulation data, thereby generating the optimized power generation strategy.
7. The method for enhancing the stability of microgrids based on ocean energy as described in claim 4, characterized in that, The data cleaning includes removing duplicate data, handling missing values, outlier detection, and data standardization.
8. A microgrid stability enhancement system based on ocean energy, characterized in that, The system is used to implement the microgrid stability enhancement method based on ocean energy as described in any one of claims 1 to 7, and the system comprises: The load forecasting module is used to forecast the load of the microgrid based on the future time zone and obtain the microgrid load demand. The power generation characteristic prediction module is used to predict the power generation characteristics of the ocean energy power generation system based on the future time zone and obtain an ocean energy power generation prediction map. The complementary scheduling module is used to perform multi-energy complementary scheduling of the ocean energy power generation system based on the microgrid load demand and the ocean energy power generation prediction map to obtain the ocean energy power generation strategy. A stability enhancement module is used to enhance the stability of the microgrid according to the ocean energy power generation strategy to obtain an optimized power generation strategy. The power supply management module is used to manage the power supply of the microgrid based on the optimized power generation strategy and the ocean energy power generation system.