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

Automated summary

Given the use of multi-sensor environments and the two way communication between energy consumers and the smart grid, high-dimensional time series are increasingly arising in the Internet of Energy (IoE). Fuzzy Time Series (FTS) models, as data-driven non-parametric models of easy implementation and high accuracy, are of great value in smart building and IoE applications. However, existing FTS models can become unfeasible if all variables were used to train the model. Therefore, we propose a data-driven approach named Embedding Fuzzy Time Series (EFTS), which combines data embedding transformation and FTS methods, and shows superior accuracy and parsimony compared to baseline methods and previous literature results.