Recently, deep learning models are utilized to predict the energy consumption. However, to construct the smart grid systems, the conventional methods have limitation on explanatory power or require manual analysis. To overcome it, in this paper, we present a novel deep learning model that can infer the predicted results by calculating the correlation between the latent variables and output as well as forecast the future consumption in high performance. The proposed model is composed of 1) a main encoder that models the past energy demand, 2) a sub encoder that models electric information except global active power as the latent variable in two dimensions, 3) a predictor that maps the future demand from the concatenation of the latent variables extracted from each encoder, and 4) an explainer that provides the most significant electric information. Several experiments on a household electric energy demand dataset show that the proposed model not only has better performance than the conventional models, but also provides the ability to explain the results by analyzing the correlation of inputs, latent variables, and energy demand predicted in the form of time-series.
|Title of host publication||Proceedings - 20th IEEE International Conference on Data Mining Workshops, ICDMW 2020|
|Editors||Giuseppe Di Fatta, Victor Sheng, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu|
|Publisher||IEEE Computer Society|
|Number of pages||6|
|Publication status||Published - 2020 Nov|
|Event||20th IEEE International Conference on Data Mining Workshops, ICDMW 2020 - Virtual, Sorrento, Italy|
Duration: 2020 Nov 17 → 2020 Nov 20
|Name||IEEE International Conference on Data Mining Workshops, ICDMW|
|Conference||20th IEEE International Conference on Data Mining Workshops, ICDMW 2020|
|Period||20/11/17 → 20/11/20|
Bibliographical noteFunding Information:
ACKNOWLEDGMENT This work was partially supported by an Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (No. 2020-0-01361, Artificial Intelligence Graduate School Program (Yonsei University)) and Korea Electric Power Corporation (Grant number: R18XA05). J. Y. Kim has been supported by NRF (National Research Foundation of Korea) grant funded by the Korean government (NRF-2019-Fostering Core Leaders of the Future Basic Science Program/Global Ph.D. Fellowship Program).
© 2020 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Science Applications