uGIM is a microgrid intelligent management platform that can represent individual end-users using a multi-agent approach. This dataset has data regarding two weeks (May 13th to May 18th, 2019, and September 30th to October 6th, 2019) where auction-based peer-to-peer transactions were performed in a real microgrid. The data was collected by uGIM agents and auctions were executed every hour. The hour-ahead auctions are performed by the sellers in a fully distributed approach. To create this dataset two NanoPi M1 Plus (with 1.2 GHz quad-core CPUs and 1 GB of RAM running the Ubuntu 16.04.6 LTS operating system), and three Raspberry Pi Model B+ (with 1.4 GHz 64-bit quad-core CPUs and GB of RAM running the Raspberry Pi OS operating system) were used. uGIM related publications: - Gomes, L., Vale, Z., & Corchado, J. M. (2020). Microgrid management system based on a multi-agent approach: An office building pilot. Measurement: Journal of the International Measurement Confederation, 154. https://doi.org/10.1016/j.measurement.2019.107427 - Gomes, L., Vale, Z. A., & Corchado, J. M. (2020). Multi-Agent Microgrid Management System for Single-Board Computers: A Case Study on Peer-to-Peer Energy Trading. IEEE Access, 8, 64169–64183. https://doi.org/10.1109/ACCESS.2020.2985254 - Gomes, L. (2020). μGIM - Microgrid intelligen management system based on a multi-agent approach and the active participation of end-users [Universidad de Salamanca]. https://doi.org/10.14201/gredos.144238 - Gomes, L., Spínola, J., Vale, Z., & Corchado, J. M. (2019). Agent-based architecture for demand side management using real-time resources’ priorities and a deterministic optimization algorithm. Journal of Cleaner Production, 241, 118154. https://doi.org/10.1016/j.jclepro.2019.118154 (if you used this dataset in your publications, please send us your information so we can add your publication to the list above) We would be grateful if you could acknowledge the use of this dataset in your publications. Please use the Zenodo publication to cite this work.

This work has received funding from the European Union's Horizon 2020 research and innovation programme under project DOMINOES (grant agreement No 771066) and from FEDER Funds through COMPETE program and from National Funds through FCT under the project UIDB/00760/2020.