高级检索

数字孪生驱动的县域水光储能源AI聚合管理

Digital Twin-driven AI Aggregation Management of County-level Hydro-photovoltaic-storage Energy

  • 摘要: 在“双碳”目标、全国电力统一市场和区域电力供需矛盾日益突出的背景下,供电企业结合自身实际和多方协同,依托数字孪生、AI、“大云物移智”等前沿技术,开展数据智能感知、离散电源点孪生建模、虚实数据精准联动交互建设,构建县域水光储清洁能源聚合孪生AI大模型,并在此平台上开展基于灰狼算法的水光储微电网运行、基于滤波算法的联络线路功率平滑控制、基于神经网络算法的区域清洁能源发电功率预测、基于决策树算法的库容水电站聚合响应应用,实现对地区清洁能源的全方位监测与精细化管理,缓解电力供需压力。

     

    Abstract: Against the background of dual carbon goals, the unified national electricity market, and increasingly prominent regional power supply and demand contradictions, power supply enterprises carry out intelligent data perception, twin modeling of discrete power points, and accurate interaction between virtual and real data based on their own conditions and multi-party collaboration. These tasks rely on digital twins, artificial intelligence, big data, cloud computing, the Internet of Things, mobile communication, and intelligent technologies. A county-level hydro-photovoltaic-storage clean energy aggregation twin AI model is constructed. Based on this platform, this paper carries out hydro-photovoltaic-storage microgrid operation based on the Grey Wolf Optimizer, tie-line power smoothing control based on filtering algorithms, regional clean energy generation forecasting based on neural network algorithms, and aggregated response of reservoir hydropower stations based on decision tree algorithms. The platform realizes comprehensive monitoring and refined management of regional clean energy, alleviates power supply and demand pressure.

     

/

返回文章
返回