PSML
收藏资源简介:
PSML数据集是由德克萨斯A&M大学和南加州大学的研究团队开发的首个开放访问的多尺度时间序列数据集,旨在支持未来电力系统可靠运行的数据驱动机器学习方法的发展。该数据集通过联合输电和配电电网合成,捕捉电网动态中日益重要的交互和不确定性,包含多个时空尺度的电力、电压和电流测量。PSML数据集包含分钟级实时负载、天气和可再生能源时间序列数据,覆盖美国66个区域,适用于开发多尺度机器学习算法,同时支持安全关键系统的启发式机器学习研究,并为能源部门的脱碳做出贡献。
The PSML dataset is the first open-access multi-scale time series dataset developed by research teams from Texas A&M University and the University of Southern California, which aims to support the development of data-driven machine learning methods for reliable operation of future power systems. Synthesized by integrating transmission and distribution grids, this dataset captures the increasingly important interactions and uncertainties in power grid dynamics, and includes power, voltage, and current measurements across multiple spatiotemporal scales. The PSML dataset includes minute-level real-time load, weather, and renewable energy time series data, covering 66 regions across the United States. It is suitable for developing multi-scale machine learning algorithms, supports heuristic machine learning research for safety-critical systems, and contributes to decarbonization efforts in the energy sector.

- 1A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Grids德克萨斯A&M大学 · 2022年



