← Back to all news
arXiv Statistics ML By Jing Shang, Mohammad Mehrabi, Xinyang Zhou, Mahmoud Saleh, Andrey Bernstein, Stefan Wager

Learning to Price Electricity for Optimal Demand Response

Read the original on arXiv Statistics ML →

The paper proposes a neural‑network algorithm for contextual electricity pricing, framing the problem as a Stackelberg game and using a mean‑field solution to learn constrained mappings from contextual features (e.g., weather, sunrise/sunset, day‑of‑week) to feasible price signals. The method is validated through simulations of the energy grid in several U.S. cities, demonstrating that incorporating rich contextual information can significantly enhance the value of demand‑response programs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv AI
Sep 4

Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs

The paper introduces DR‑Gym, an open‑source, Gymnasium‑compatible environment that simulates electric utility demand‑response programs at the market level. It uses a regime‑switching wholesale price model calibrated to real extreme events and physics‑based building demand profiles, providing a rich observational space and a configurable multi‑objective reward function for reinforcement learning. Baseline strategies and data snapshots demonstrate the simulator’s realism and learnability.

By Jose E. Aguilar Escamilla, Lingdong Zhou, Xiangqi Zhu, Huazheng Wang
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 10

Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning

The paper presents a hybrid neural architecture that blends linear and nonlinear feed‑forward networks for day‑ahead electricity price forecasting. It introduces a partial online learning strategy with warm‑starting and stage‑specific hyperparameters to cut computational time, and employs Bernstein Online Aggregation to combine forecasts. Experiments on six years of major European markets show the method reduces RMSE by 11‑12% and MAE by 14‑17% compared to state‑of‑the‑art benchmarks while lowering computational cost.

By Btissame El Mahtout, Florian Ziel
benchmarks
More like this →