Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems

TL;DR

This paper explores how transfer learning can enhance digital twins in renewable energy by addressing data scarcity and enabling autonomous, incremental knowledge growth in power forecasting and anomaly detection.

Contribution

It proposes a transfer learning framework tailored for renewable energy digital twins, including a feature embedding method for missing sensor data handling.

Findings

Transfer learning improves model accuracy in renewable energy tasks.

The framework enhances system autonomy and incremental learning capabilities.

Handling missing sensor data with feature embedding proves effective.

Abstract

Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.