Data Analytics in Power Markets

This book aims to solve some key problems in the decision and optimization procedure for power market organizers and participants in data-driven approaches. These methods are especially useful for market organizers to understand the bidding behaviors of market participants and make essential policies.

Introduction to power market data and their characteristics.- Modeling load forecasting uncertainty using deep learning models.- Data-driven load data cleaning and its impacts on forecasting performance.- Generalized cost-oriented load forecasting in economic dispatch.- A monthly electricity consumption forecasting method.- Data-driven pattern extraction for analyzing market bidding behaviors.- Stochastic optimal offering based on probabilistic forecast on aggregated supply curves.- Power market simulation framework based on learning from individual offering strategy.- Deep inverse reinforcement learning for reward function identification in bidding models.- The subspace characteristics and congestion identification of LMP data.- Online transmission topology identification in LMP-based markets.- Day-ahead componential electricity price forecasting.- Quantifying the impact of price forecasting error on market bidding.- Virtual bidding and FTR speculation based on probabilistic LMP forecasting.- Abnormal detection of LMP scenario and data with deep neural networks.