Deep sequence to sequence Bi-LSTM neural networks for day-ahead peak load forecasting
作者：
Highlights：
• First attempt on using deep Bi-LSTM S2S regression for “peak” load forecasting.
• First attempt on forecasting peak demand of a residential area supplied by FESCO.
• Challenge of accurately forecasting load on special days is effectively addressed.
• Model is effective for grossly limited training data.
• Useful for developing countries with small total load, especially at feeder level.
摘要
•First attempt on using deep Bi-LSTM S2S regression for “peak” load forecasting.•First attempt on forecasting peak demand of a residential area supplied by FESCO.•Challenge of accurately forecasting load on special days is effectively addressed.•Model is effective for grossly limited training data.•Useful for developing countries with small total load, especially at feeder level.
论文关键词：Peak demand forecasting,Demand response programs,Bidirectional long-short term memory networks,Sequence to sequence regression,Deep neural networks
论文评审过程：Received 25 December 2020, Revised 2 March 2021, Accepted 2 March 2021, Available online 11 March 2021, Version of Record 21 March 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114844
