Demand Response through Price-setting Multi-agent Reinforcement Learning

Autor: Pierre Pinson, Cédric Ernewein, Morten Herget Christensen

Publikováno v: Proceedings of the 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities.

Price based demand response is a cost-effective way of obtaining flexibility needed in power systems with high penetration of intermittent renewable energy sources. Model-free deep reinforcement learning is proposed as a way to train autonomous agent

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::137abfaf3c52d9e81b0a0c55336c0a9c
https://doi.org/10.1145/3427773.3427862

Data-driven learning from dynamic pricing data - Classification and forecasting

Autor: Diego Caviedes Nozal, Pierre Pinson, Morten Herget Christensen, Ioannis Kavadakis

Publikováno v: 2019 IEEE Milan PowerTech.

Inspired by recent advances in data driven methods from deep-learning, this paper shows how neural networks can be trained to extract valuable information from smart meter data. We show how these methods can help provide new insight into the effectiv

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e62b9ac2c82f5d90eb2dc156303ede24
https://doi.org/10.1109/ptc.2019.8810769

Model Predictive Control for Smart Buildings to Provide the Demand Side Flexibility in the Multi-Carrier Energy Context: Current Status, Pros and Cons, Feasibility and Barriers

Autor: Shujun Mu, Chuhao Jiang, You Zhou, Wenjing Su, Shi You, Morten Herget Christensen, Jiawei Wang, Jakub Krzysztof Rodek, Yi Zong

Publikováno v: Zong, Y, Su, W, Wang, J, Rodek, J K, Jiang, C, Christensen, M H, You, S, Zhou, Y & Mu, S 2019, ' Model Predictive Control for Smart Buildings to Provide the Demand Side Flexibility in the Multi-Carrier Energy Context: Current Status, Pros and Cons, Feasibility and Barriers ', Energy Procedia, vol. 158, pp. 3026-3031 . https://doi.org/10.1016/j.egypro.2019.01.981

In this paper, a state of the art review of model predictive control (MPC) for smart buildings to provide demand side flexibility with the purpose of enhancing a high penetration of renewables into the integrated energy systems is carried, including

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cfd135f883c8eabdcd13271d6b52c930
https://orbit.dtu.dk/en/publications/d646576a-5f99-44ed-91da-10a09f75b10d

Data-driven study on individual occupant comfort using heating setpoints and window openings in new low-energy apartments – preliminary insights

Autor: Pierre Pinson, Lucile Sarran, Andrea Marin Radoszynski, Morten Herget Christensen, Christian Anker Hviid, Carsten Rode

Publikováno v: E3S Web of Conferences, Vol 111, p 04063 (2019)

This work suggests a method to evaluate residential building occupants’ neutral temperature in winter based on their interaction with their heating system. This study applies the developed method on eight new, low-energy apartments in Copenhagen, D

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa35a14c0dafc2de1d4e862361aebfff
https://www.e3s-conferences.org/articles/e3sconf/pdf/2019/37/e3sconf_clima2019_04063.pdf

Demonstration of heating demand peak shaving in smart homes.

Autor: Lucas Beltram, Morten Herget Christensen, Rongling Li

Publikováno v: Journal of Physics: Conference Series; 2019, Vol. 1343 Issue 1, p1-1, 1p