Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast

TL;DR

This paper introduces a novel temporal convolutional network architecture with task embeddings for renewable power time-series forecasting, effectively capturing seasonal patterns and enabling zero-shot learning, leading to significant accuracy improvements.

Contribution

It extends task embedding methods to temporal convolutional networks, incorporating seasonal influences and proposing zero-shot learning for renewable power forecasts.

Findings

Up to 25% improvement in multi-task learning accuracy.

10% improvement in wind power transfer learning.

Over 20% accuracy gain in solar power transfer learning.

Abstract

Task embeddings in multi-layer perceptrons for multi-task learning and inductive transfer learning in renewable power forecasts have recently been introduced. In many cases, this approach improves the forecast error and reduces the required training data. However, it does not take the seasonal influences in power forecasts within a day into account, i.e., the diurnal cycle. Therefore, we extended this idea to temporal convolutional networks to consider those seasonalities. We propose transforming the embedding space, which contains the latent similarities between tasks, through convolution and providing these results to the network's residual block. The proposed architecture significantly improves up to 25 percent for multi-task learning for power forecasts on the EuropeWindFarm and GermanSolarFarm dataset compared to the multi-layer perceptron approach. Based on the same data, we achieve a ten percent improvement for the wind datasets and more than 20 percent in most cases for the solar dataset for inductive transfer learning without catastrophic forgetting. Finally, we are the first proposing zero-shot learning for renewable power forecasts to provide predictions even if no training data is available.