Research Article
Short Term Load Forecasting Method Based on Full Convolution Deep Learning
@INPROCEEDINGS{10.1007/978-3-030-94182-6_37, author={Hai-hong Bian and Xing-jian Shi and Qian Wang and Li-kuan Gong}, title={Short Term Load Forecasting Method Based on Full Convolution Deep Learning}, proceedings={IoT and Big Data Technologies for Health Care. Second EAI International Conference, IoTCare 2021, Virtual Event, October 18-19, 2021, Proceedings, Part II}, proceedings_a={IOTCARE PART 2}, year={2022}, month={6}, keywords={Full convolution deep learning Short term electricity Load forecasting Neural network}, doi={10.1007/978-3-030-94182-6_37} }- Hai-hong Bian
Xing-jian Shi
Qian Wang
Li-kuan Gong
Year: 2022
Short Term Load Forecasting Method Based on Full Convolution Deep Learning
IOTCARE PART 2
Springer
DOI: 10.1007/978-3-030-94182-6_37
Abstract
The traditional load forecasting methods can not take into account the time and space characteristics of load data at the same time, which leads to the low application efficiency of load forecasting methods. In order to solve this problem, a short-term load forecasting method based on full convolution deep learning is proposed. Preprocess the power load data, delete the abnormal samples, unify the load data format through normalization processing, design the relevant network parameters, determine the loss function, complete the design of the prediction model, use the sample data to train the prediction model, and predict the short-term power load after the model meets the prediction requirements. The experimental results show that: in the same experimental environment, the short-term power load forecasting method based on full convolution deep learning has high prediction accuracy, wide prediction range, and its application efficiency has been improved.
