Combining Load Forecasts from Independent Experts: Experience at NPower Forecasting Challenge 2015

Forecast combination is regarded as one of the best practices of forecasting. I think it is a straightforward and practical approach to improving existing forecasts. This paper describes the method my students took in the NPower Forecasting Challenge 2015. We will present the paper at the 47th North America Power Symposium.

Citation
Jingrui Xie, Bidong Liu, Xiaoqian Lyu, Tao Hong, and David Basterfield, "Combining load forecasts from independent experts: experience at NPower forecasting challenge 2015", the 47th North American Power Symposium (NAPS2015), October 4 - 6, 2015

Combining Load Forecasts from Independent Experts

Experience at NPower Forecasting Challenge 2015

Jingrui Xie, Bidong Liu, Xiaoqian Lyu, Tao Hong, and David Basterfield

Abstract

The NPower Forecasting Challenge 2015 invited students and professionals worldwide to predict daily energy usage of a group of customers. The BigDEAL team from the Big Data Energy Analytics Laboratory landed a top 3 place in the final leaderboard. This paper presents a refined methodology based on the implementation during the competition. We first build the individual forecasts using several forecast techniques, such as Multiple Linear Regression (MLR), Autoregressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN) and Random Forests (RF). We then select a subset of the individual forecasts based on their performance on a validation period, a.k.a. post-sample. Finally we obtain the final forecast by averaging the selected individual forecasts. The forecast combination on average yields a better result than the forecast from a single technique.