A hybrid model of kernel density estimation and quantile regression for GEFCom2014 probabilistic load forecasting

Abstract

We present a model for generating probabilistic forecasts by combining kernel density estimation (KDE) and quantile regression techniques, as part of the probabilistic load forecasting track of the Global Energy Forecasting Competition 2014. The KDE method is initially implemented with a time-decay parameter. We later improve this method by conditioning on the temperature or the period of the week variables to provide more accurate forecasts. Secondly, we develop a simple but effective quantile regression forecast. The novel aspects of our methodology are two-fold. First, we introduce symmetry into the time-decay parameter of the kernel density estimation based forecast. Secondly we combine three probabilistic forecasts with different weights for different periods of the month.

9 pages, 1 figure, minor differences to published version. Method achieved top 5 in GEFCom 2014

References in corpus (1)

• Quantile and Probability Curves Without Crossing

Cited by in corpus (8)

• Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges
• Short Term Load Forecasts of Low Voltage Demand and the Effects of Weather
• Quantile Regression for Qualifying Match of GEFCom2017 Probabilistic Load Forecasting
• M5 Competition Uncertainty: Overdispersion, distributional forecasting, GAMLSS and beyond
• Combining Probabilistic Load Forecasts
• Classification of load forecasting studies by forecasting problem to select load forecasting techniques and methodologies
• Modelling the Demand and Uncertainty of Low Voltage Networks and the Effect of non-Domestic Consumers
• Chance-Constrained Two-Stage Unit Commitment under Uncertain Load and Wind Power Output Using Bilinear Benders Decomposition