当前位置: X-MOL 学术IEEE Trans. Smart. Grid. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Reinforced Deterministic and Probabilistic Load Forecasting via $Q$ -Learning Dynamic Model Selection
IEEE Transactions on Smart Grid ( IF 9.6 ) Pub Date : 2019-08-26 , DOI: 10.1109/tsg.2019.2937338
Cong Feng , Mucun Sun , Jie Zhang

Both deterministic and probabilistic load forecasting (DLF and PLF) are of critical importance to reliable and economical power system operations. However, most of the widely used statistical machine learning (ML) models are trained by optimizing the global performance, without considering the local behaviour. This paper develops a two-step short-term load forecasting (STLF) model with Q-learning based dynamic model selection (QMS), which provides reinforced deterministic and probabilistic load forecasts (DLFs and PLFs). First, a deterministic forecasting model pool (DMP) and a probabilistic forecasting model pool (PMP) are built based on 10 state-of-the-art ML DLF models and 4 predictive distribution models. Then, in the first-step of each time stamp, a Q-learning agent selects the locally-best DLF model from the DMP to provide an enhanced DLF. At last, the DLF is input to the best PLF model selected from the PMP by another Q-learning agent to perform PLF in the second-step. Numerical simulations on two-year weather and smart meter data show that the developed STLF-QMS method improves DLF and PLF by 50% and 60%, respectively, compared to the state-of-the-art benchmarks.

中文翻译:

通过以下方式增强确定性和概率负荷预测 $ Q $ -学习动态模型选择

确定性和概率性负载预测(DLF和PLF)对于可靠且经济的电力系统运行至关重要。但是,大多数广泛使用的统计机器学习(ML)模型都是通过优化全局性能来进行训练的,而没有考虑本地行为。本文利用基于Q学习的动态模型选择(QMS)开发了两步短期负荷预测(STLF)模型,该模型提供了增强的确定性和概率负荷预测(DLF和PLF)。首先,基于10个最新的ML DLF模型和4个预测分布模型,建立了确定性预测模型池(DMP)和概率预测模型池(PMP)。然后,在每个时间戳的第一步中,Q学习代理从DMP中选择本地最佳的DLF模型以提供增强的DLF。最后,通过另一个Q学习代理将DLF输入到从PMP中选择的最佳PLF模型,以在第二步中执行PLF。两年天气和智能电表数据的数值模拟表明,与最新基准相比,开发的STLF-QMS方法分别将DLF和PLF改善了50%和60%。
更新日期:2020-04-22
down
wechat
bug