Combining embeddings and fuzzy time series for high-dimensional time series forecasting in internet of energy applications

High-dimensional time series increasingly arise in the Internet of Energy (IoE), given use multi-sensor environments and two way communication between energy consumers smart grid. Therefore, methods that are capable computing high-dimensional great value building IoE applications. Fuzzy Time Series (FTS) models stand out as data-driven non-parametric easy implementation high accuracy. Unfortunately, existing FTS can be unfeasible if all variables were used to train model. We present a new methodology named Embedding (EFTS), by applying combination data embedding transformation methods. The EFTS is an explainable approach, which flexible adaptable for many experimental results with three public datasets show our outperforms several machine learning based forecasting (LSTM, GRU, TCN, RNN, MLP GBM), demonstrates accuracy parsimony comparison baseline previously published literature, showing enhancement greater than 80%. has