Data-Driven Load Frequency Control for Stochastic Power Systems: A Deep Reinforcement Learning Method With Continuous Action Search

By Ziming Yan, Yan Xu. IEEE Transactions on Power Systems, 2019

307 citations recorded by the source corpus.

This letter proposes a data-driven, model-free method for load frequency control (LFC) against renewable energy uncertainties based on deep reinforcement learning (DRL) in continuous action domain. The proposed method can nonlinearly derive control strategies to minimize frequency deviation with faster response speed and stronger adaptability for unmolded system dynamics. It consists of offline optimization of LFC strategies with DRL and continuous action search, and online control with policy network where features are extracted by stacked denoising auto-encoders. Numerical simulations verify the effectiveness and advantages of proposed method over existing approaches.

Subfields: Control and Systems Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/022f6e38b1973cb4ba88f3de260f8d2c4e33ed0b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Yujie Tang
2. Frede Blaabjerg
3. Zhe Chen
4. Na Li
5. Steven H. Low
6. Xin Chen
7. Guannan Qu
8. Fangxing Li

In Electrical and Electronic Engineering

1. Na Li
2. Steven H. Low
3. Yujie Tang
4. Zhe Chen
5. Frede Blaabjerg
6. Xin Chen
7. Guannan Qu
8. Yan Du

Citations in the corpus

• Intelligent Multi-Microgrid Energy Management Based on Deep Neural Network and Model-Free Reinforcement Learning (2020, background): “The feasibility of applying deep RL to load frequency control with stochastic renewable energy penetration is investigated in [24].”
• Deep-Reinforcement-Learning-Based Autonomous Voltage Control for Power Grid Operations (2020, methodology): “In [6], a DDPG method is applied for load frequency control.”
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges (2021, methodology): “Reference [64] applies the stacked denoising autoencoders to extract compact and useful features from the raw measurement data for FR. • Select RL Algorithm .”
• A Multi-Agent Deep Reinforcement Learning Method for Cooperative Load Frequency Control of a Multi-Area Power System (2020, background): “[23] proposes a deep reinforcement learning (DRL) model in continuous action domain to improve the LFC performance for single-area power systems.”
• Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review (2020, methodology): “To address that, in [99], the state-of-the-art DDPG, which has continuous action domain search capability, is applied as the basic method for load frequency control to minimize frequency deviation with faster response characteristics and robustness.”