# Energy Predictive Models with Limited Data using Transfer Learning

## TL;DR

This paper introduces a CNN-based energy prediction model that employs transfer learning to improve forecasting accuracy when limited historical data is available, demonstrated on electricity demand forecasting.

## Contribution

The paper proposes a novel transfer learning approach for CNN models to enhance energy asset predictions with scarce data, addressing a key challenge in the field.

## Key findings

- Transfer learning significantly improves forecasting accuracy.
- CNN effectively captures energy time series patterns.
- Method outperforms existing approaches on electricity demand data.

## Abstract

In this paper, we consider the problem of developing predictive models with limited data for energy assets such as electricity loads, PV power generations, etc. We specifically investigate the cases where the amount of historical data is not sufficient to effectively train the prediction model. We first develop an energy predictive model based on convolutional neural network (CNN) which is well suited to capture the interaday, daily, and weekly cyclostationary patterns, trends and seasonalities in energy assets time series. A transfer learning strategy is then proposed to address the challenge of limited training data. We demonstrate our approach on a usecase of daily electricity demand forecasting. we show practicing the transfer learning strategy on the CNN model results in significant improvement to existing forecasting methods.