Journal
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
Volume 14, Issue 2, Pages 803-812Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSTE.2022.3226106
Keywords
Uncertainty; Generators; Costs; Wind power generation; Programming; Wind forecasting; Power systems; Unit commitment; deep reinforcement learning; safe exploration; renewable energy sources
Ask authors/readers for more resources
This work proposes a deep reinforcement learning (DRL) based approach to address the uncertainties in renewable energy and fluctuating electricity demand, and provide reliable and cost-effective generation schedules of power systems. The approach relies on historical uncertainty realizations and forecast data, and guarantees a feasible commitment schedule without operational constraint violations through safe exploration. Computational experiments on IEEE 39-bus and 118-bus test cases show that the proposed approach outperforms existing methods in terms of computational efficiency and incurred operational costs.
The intermittent nature of renewable energy sources and fluctuating electricity demand induce significant uncertainty that needs to be tackled with computationally efficient solution techniques to provide reliable and cost-effective generation schedules of power systems. In this work, we present a deep reinforcement learning (DRL) based approach for the day-ahead scheduling of generation resources under demand and wind power uncertainties. The proposed approach yields a causal policy relying only on historical uncertainty realizations and forecast data that is trained with an actor-critic-based reinforcement learning algorithm. Through safe exploration, the DRL-based approach guarantees a feasible commitment schedule without any operational constraint violations. We conduct computational experiments on the IEEE 39-bus and 118-bus test cases to demonstrate the effectiveness of the proposed solution strategy and improvement over existing approaches, including a deterministic approach with point forecasts and the stochastic dual dynamic integer programming method. The results show that the proposed approach enjoys superior performance in terms of computational efficiency and incurred operational costs, with significant reduction in penalty costs caused by insufficient net load supply than the deterministic approach.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available