Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series

TL;DR

This paper presents a neural architecture search framework to automate the design of efficient, accurate, and generalizable models for multi-step energy production forecasting, outperforming existing methods.

Contribution

It introduces a NAS-based approach with a specialized search space and a novel objective function tailored for energy time series forecasting.

Findings

Ensemble of NAS-discovered architectures outperforms Transformers.

The proposed models achieve better efficiency and accuracy.

The framework enhances generalization to unseen energy data.

Abstract

The dynamic energy sector requires both predictive accuracy and runtime efficiency for short-term forecasting of energy generation under operational constraints, where timely and precise predictions are crucial. The manual configuration of complex methods, which can generate accurate global multi-step predictions without suffering from a computational bottleneck, represents a procedure with significant time requirements and high risk for human-made errors. A further intricacy arises from the temporal dynamics present in energy-related data. Additionally, the generalization to unseen data is imperative for continuously deploying forecasting techniques over time. To overcome these challenges, in this research, we design a neural architecture search (NAS)-based framework for the automated discovery of time series models that strike a balance between computational efficiency, predictive performance, and generalization power for the global, multi-step short-term forecasting of energy production time series. In particular, we introduce a search space consisting only of efficient components, which can capture distinctive patterns of energy time series. Furthermore, we formulate a novel objective function that accounts for performance generalization in temporal context and the maximal exploration of different regions of our high-dimensional search space. The results obtained on energy production time series show that an ensemble of lightweight architectures discovered with NAS outperforms state-of-the-art techniques, such as Transformers, as well as pre-trained forecasting models, in terms of both efficiency and accuracy.