Gene

Quantum mechanics

Engineering

Ensemble learning

Probabilistic forecasting

Robustness (evolution)

Power demand

Ensemble forecasting

Probabilistic logic

Power (physics)

Biochemistry

Computer science

Boosting (machine learning)

Technology forecasting

Physics

Operations research

Electric power system

Long short term memory

Artificial intelligence

Chemistry

Demand forecasting

Term (time)

Artificial neural network

Power consumption

Recurrent neural network

Machine learning

IEEE Transactions on Power Systems

Power demand forecasting with high accuracy is a guarantee to keep the balance between power supply and demand. Due to strong volatility of industrial power load, ultra-short-term power demand is difficult to forecast accurately and robustly. To solve this problem, this article proposes a Long Short-Term Memory (LSTM) network based hybrid ensemble learning forecasting model. A hybrid ensemble strategy-which consists of Bagging, Random Subspace, and Boosting with ensemble pruning-is designed to extract the deep features from multivariate data, and a new loss function that integrates peak demand forecasting error is proposed according to bias-variance tradeoff. Experimental results on open dataset and practical dataset show that the proposed model outperforms several state-of-the-art time series forecasting models, and obtains higher accuracy and robustness to forecast peak demand.

Ultra-Short-Term Industrial Power Demand Forecasting Using LSTM Based Hybrid Ensemble Learning