The data for PVs and loads from “Multi-agent reinforcement learning for active voltage control on power distribution networks”

The data for PVs and loads are sourced from “Multi-agent reinforcement learning for active voltage control on power distribution networks”, collected from Jan. 1 st, 2012 to Dec. 31 st, 2014 over a 3-minute interval. In this paper, the data is described as follows: “Data Descriptions. The load profile of each network is modified based on the real-time Portuguese electricity consumption accounting for 232 consumers of 3 years. To highlight the differences between residential and industrial users, we randomly perturb ±5% on the default power factors defined in the case files and accordingly generate real-time reactive power consumption. The solar data is collected from Elia group, i.e. a Belgiums power network operator. The load and PV data are then interpolated with 3-min resolution that is consistent with the real-time control period in the grid. To distinguish among different solar radiation levels in various regions, the 3-year PV generations from 10 cites/regions are collected and PVs in the same control region possess the same generation profiles. We define the PV penetration rate (P R) as the ratio between rated PV generation and rated load consumption. In this paper, we set P R ∈ {2.5, 4, 2.5} as the default P R for different topologies. We oversize each PV inverter by 20% of its maximum active power generation to satisfy the IEEE grid code. Besides, each PV inverter is considered to be able to generate reactive power in the STATCOM mode during night. The median and 25%-75% quantile shadings of PV generations.”