Short Term Load Forecasting Based on iForest-LSTM

The noise generated by the measured data of the distribution network has impact on the accuracy of the load forecasting. In this paper, a short-term load forecasting method based on Isolation Forest (iForest) and Long Short-Term Memory (LSTM) neural network is proposed. Firstly, the iForest algorithm is used to mine and clean the abnormal historical load data. Secondly, a forecasting model is established based on the LSTM network in deep learning. Thirdly, the iForest-LSTM is formed, and then applied to the short-term load forecasting. Finally, the forecasting results of the iForest-LSTM method are compared with the standard LSTM and iForest-BP methods, and the proposed method can effectively improve the forecasting accuracy.

[1]  Yu Hao,et al.  Training Data Selection for Short Term Load Forecasting , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.

[2]  Saeid Nahavandi,et al.  Improving the Quality of Load Forecasts Using Smart Meter Data , 2015, ICONIP.

[3]  Yong Zhang,et al.  Data Cleaning Method Based on Time Series Similarity Measurement for Large-Scale Smart Grid Load Data , 2017, 2017 5th International Conference on Enterprise Systems (ES).

[4]  Vladimir Ceperic,et al.  A Strategy for Short-Term Load Forecasting by Support Vector Regression Machines , 2013, IEEE Transactions on Power Systems.

[5]  Daniel L. Marino,et al.  Building energy load forecasting using Deep Neural Networks , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[6]  K. Nose-Filho,et al.  Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network , 2011, IEEE Transactions on Power Delivery.

[7]  Ilkay Oksuz,et al.  Electricity Price Forecasting Using Recurrent Neural Networks , 2018 .

[8]  Yaoyao He,et al.  Short-term power load probability density forecasting based on Yeo-Johnson transformation quantile regression and Gaussian kernel function , 2018, Energy.

[9]  Minrui Fei,et al.  An Anomaly Detection Approach Based on Isolation Forest Algorithm for Streaming Data Using Sliding Window , 2013, ICONS.

[10]  Mohsen Mohammadi,et al.  Small-Scale Building Load Forecast based on Hybrid Forecast Engine , 2017, Neural Processing Letters.

[11]  Zuhairi Baharudin,et al.  Electricity load forecasting using hybrid wavelet neural network based on parallel prediction method , 2016, 2016 6th International Conference on Intelligent and Advanced Systems (ICIAS).

[12]  Victor A. Almeida,et al.  Load data cleaning with data mining techniques , 2018, 2018 Simposio Brasileiro de Sistemas Eletricos (SBSE).

[13]  Yousuf Ibrahim Khan,et al.  Artificial Neural Network based Short Term Load Forecasting of Power System , 2013 .

[14]  Igor Škrjanc,et al.  Short-Term Load Forecasting by Separating Daily Profiles and Using a Single Fuzzy Model Across the Entire Domain , 2018, IEEE Transactions on Industrial Electronics.