Local Short Term Electricity Load Forecasting: Automatic Approaches

TL;DR

This paper evaluates various models for local short-term electricity load forecasting, highlighting the effectiveness of a modified Holt-Winter method with limited training data, especially at local levels.

Contribution

The paper identifies limitations of existing STLF models for local forecasting and proposes a modified Holt-Winter approach suitable for small datasets with minimal intervention.

Findings

Modified Holt-Winter performs well with 3 months of data

Yearly pattern and temperature are less useful at local levels

Complex models are less applicable due to training instability

Abstract

Short-Term Load Forecasting (STLF) is a fundamental component in the efficient management of power systems, which has been studied intensively over the past 50 years. The emerging development of smart grid technologies is posing new challenges as well as opportunities to STLF. Load data, collected at higher geographical granularity and frequency through thousands of smart meters, allows us to build a more accurate local load forecasting model, which is essential for local optimization of power load through demand side management. With this paper, we show how several existing approaches for STLF are not applicable on local load forecasting, either because of long training time, unstable optimization process, or sensitivity to hyper-parameters. Accordingly, we select five models suitable for local STFL, which can be trained on different time-series with limited intervention from the user. The experiment, which consists of 40 time-series collected at different locations and aggregation levels, revealed that yearly pattern and temperature information are only useful for high aggregation level STLF. On local STLF task, the modified version of double seasonal Holt-Winter proposed in this paper performs relatively well with only 3 months of training data, compared to more complex methods.