Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting

11/05/2018
by   Cong Feng, et al.
0

With the growing prevalence of smart grid technology, short-term load forecasting (STLF) becomes particularly important in power system operations. There is a large collection of methods developed for STLF, but selecting a suitable method under varying conditions is still challenging. This paper develops a novel reinforcement learning based dynamic model selection (DMS) method for STLF. A forecasting model pool is first built, including ten state-of-the-art machine learning based forecasting models. Then a Q-learning agent learns the optimal policy of selecting the best forecasting model for the next time step, based on the model performance. The optimal DMS policy is applied to select the best model at each time step with a moving window. Numerical simulations on two-year load and weather data show that the Q-learning algorithm converges fast, resulting in effective and efficient DMS. The developed STLF model with Q-learning based DMS improves the forecasting accuracy by approximately 50 learning based STLF models.

READ FULL TEXT

page 2

page 4

research
05/10/2018

An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending

Solar forecasting accuracy is affected by weather conditions, and weathe...
research
09/25/2020

A Meta-learning based Distribution System Load Forecasting Model Selection Framework

This paper presents a meta-learning based, automatic distribution system...
research
09/02/2019

Data Selection for Short Term load forecasting

Power load forecast with Machine Learning is a fairly mature application...
research
12/28/2019

Hour-Ahead Load Forecasting Using AMI Data

Accurate short-term load forecasting is essential for efficient operatio...
research
03/02/2022

ES-dRNN with Dynamic Attention for Short-Term Load Forecasting

Short-term load forecasting (STLF) is a challenging problem due to the c...
research
04/10/2022

Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching

The expansion of renewable energy could help realizing the goals of peak...
research
04/26/2021

Performance Testing Using a Smart Reinforcement Learning-Driven Test Agent

Performance testing with the aim of generating an efficient and effectiv...

Please sign up or login with your details

Forgot password? Click here to reset