Isolated Areas Consumption Short-Term Forecasting Method

Abstract

Forecasting consumption in isolated areas represents a challenging problem typically resolved using deep learning or large mathematical models with various dimensions. These models require expertise in metering and algorithms, and the equipment needs to be frequently maintained. In the context of the MAESHA H2020 project, most of the consumers and producers are isolated. Forecasting becomes more difficult due to the lack of external data and the significant impact of human behaviors on these small systems. The proposed approach is based on data sequencing, sequential mining, and pattern mining to infer the results into a Hidden Markov Model. It only needs the consumption and production curve as a time series and adapts itself to provide the forecast. Our method gives a better forecast than other prediction machines and deep-learning methods used in the literature review.