Electrical Data Recovery with Weather Information via Collective Matrix Factorization

Abstract

It is an important application in power systems to monitor load and calculate the electricity cost using data collected from smart meters. As the development of smart grid and energy internet, this leads to a significant increase in the amount of data transmitted in real time. Due to the mismatch with communication networks that were not designed to carry high-speed and real time data, data losses and data quality degradation may happen constantly. The electrical data is incomplete. Therefore, the electrical data recovery is an important issue. The electrical data is produced by the action and feelings of the human being which has strong season feature and depends on the weather. We take the weather information as aid to recover electrical data via collective matrix factorization. We perform extensive simulations based on the real power system and weather data sets and the simulation results validate the efficiency and efficacy of the proposed scheme compared without weather information.