Data Model Design for Explainable Machine Learning-based Electricity Applications
This work addresses the problem of inefficient data modeling for explainable machine learning in electricity applications, particularly for smart grids and renewable energy integration, but it is incremental as it builds on existing forecasting methods with a new data taxonomy.
The paper tackles the lack of structured study on multivariate data in machine learning for energy applications by proposing a taxonomy to guide data model design, and validates it in household electricity forecasting, showing improved accuracy with domain, contextual, and behavioral features across multiple datasets and models.
The transition from traditional power grids to smart grids, significant increase in the use of renewable energy sources, and soaring electricity prices has triggered a digital transformation of the energy infrastructure that enables new, data driven, applications often supported by machine learning models. However, the majority of the developed machine learning models rely on univariate data. To date, a structured study considering the role meta-data and additional measurements resulting in multivariate data is missing. In this paper we propose a taxonomy that identifies and structures various types of data related to energy applications. The taxonomy can be used to guide application specific data model development for training machine learning models. Focusing on a household electricity forecasting application, we validate the effectiveness of the proposed taxonomy in guiding the selection of the features for various types of models. As such, we study of the effect of domain, contextual and behavioral features on the forecasting accuracy of four interpretable machine learning techniques and three openly available datasets. Finally, using a feature importance techniques, we explain individual feature contributions to the forecasting accuracy.