摘要
The big data era in energy systems is coming with the popularity of advanced metering architectures such as smart meters, providing much more data sources for ultra-short-term load forecasting. In this context, data-drive techniques, e.g., long short-term memory (LSTM) networks and convolutional neural networks (CNNs) have gradually become essential methodology to improve load forecasting accuracy. In this paper, we identify an ultra-short-term load forecasting model based on LSTM networks and CNNs. LSTM networks reflect the nonlinear relation between influential features and future loads, and the influential features are extracted implicitly from special CNNs. Case studies have verified the effectiveness of the proposed model in terms of both accuracy and efficiency, comparing with shallow neural networks, separate CNNs, separate LSTM networks, and separate gated recurrent unit (GRU) networks.
学科与关键词
- Hybrid CNN-LSTM Model for Short-Term Individual Household Load ForecastingAlhussein, Musaed; Aurangzeb, Khursheed*; Haider, Syed IrtazaIEEE Access, 2020, 8: 180544-180557.被引 215
- Short Term Electric Load Forecasting Based on Data Transformation and Statistical Machine LearningAndriopoulos, Nikos; Magklaras, Aristeidis; Birbas, Alexios*; Papalexopoulos, Alex; Valouxis, Christos; Daskalaki, Sophia; Birbas, Michael; Housos, Efthymios; Papaioannou, George P.Applied Sciences-Basel, 2021, 11(1): 158.被引 30
- Intelligence based Accurate Medium and Long Term Load Forecasting SystemButt, Faisal Mehmood; Hussain, Lal*; Jafri, Syed Hassan Mujtaba; Alshahrani, Haya Mesfer; Al-Wesabi, Fahd N.; Lone, Kashif Javed; El Din, Elsayed M. Tag; Al Duhayyim, MesferAPPLIED ARTIFICIAL INTELLIGENCE, 2022, 36(1): 2088452.被引 12
