{"references": ["National Renewable Energy Laboratory, 2020. Solar power data for integration studies. Accessed: 2020-04-30. URL https://www.nrel.gov/grid/solar-power-data.html", "Lai, G., Chang, W., Yang, Y., Liu, H., 2017. Modeling long and short-term temporal patterns with deep neural networks. CoRR abs/1703.07015.URL http://arxiv.org/abs/1703.07015", "Lai, G., 2017. multivariate-time-series-data. https://github.com/laiguokun/multivariate-time-series-data, accessed: 2020-05-04"]}

The solar dataset contains approximately 6000 simulated time series representing 5-minute solar power and hourly day-ahead forecasts of photovoltaic (PV) power plants in United States in 2006. The uploaded dataset contains the aggregated version of a subset of the original dataset used by Lai et al. (2017). It contains 137 time series representing the solar power production recorded per every 10 minutes in Alabama state in 2006.