A5066265500- Energy Load and Power Forecasting
- Grey System Theory Applications
- Smart Grid and Power Systems
- Geoscience and Mining Technology
Hunan University
2022-2024
Accurate load forecasting is the key to economic dispatch and efficient operation of Multi-Energy System (MES). This paper proposes a combined method for MES based on Bi-directional Long Short-Term Memory (BiLSTM) multi-task learning. Firstly, this investigates multi-energy interaction mechanism multi-loads characteristics analyzes correlation in different seasons. Then, proposed, which focuses making full use coupling relationship among multiple loads. In model, loads are selected...
Accurate load forecasting is essential for the operational management of distribution network. This paper proposes a hybrid ensemble deep learning (HEDL) framework. Two-stage decomposition based on multiple seasonal-trend using loess (MSTL) and variational mode (VMD), which simplifies observed sequence with complex variation patterns multi-timescales multi-frequencies. Multidimensional feature matrices considering component variability are constructed maximum information coefficient (MIC)...
Accurate medium-term load forecasting plays an imperative role in power distribution systems. Since available models lack validity and applicability due to the irregularity of original series, this paper proposes a decomposition-ensemble approach forecast daily electricity consumption for next thirty days. First, seasonal decomposition is applied decompose data into trend, residual components extracting identifying fluctuation characteristics data. Secondly, long short-term memory neural...