Learning Regionally Decentralized AC Optimal Power Flows with ADMM
This work addresses the challenge of efficient decentralized optimization in smart grids, which is crucial for integrating renewable energy and managing power flow, but it is incremental as it builds on existing ADMM methods by adding machine learning enhancements.
The paper tackles the problem of speeding up the convergence of the Alternating Direction Method of Multipliers (ADMM) for solving AC Optimal Power Flow (AC-OPF) in decentralized smart grids, proposing a novel machine-learning approach called ML-ADMM that uses deep learning to learn consensus parameters and filtering mechanisms to select high-quality runs, with experimental results on French system test cases demonstrating significant convergence speed improvements.
One potential future for the next generation of smart grids is the use of decentralized optimization algorithms and secured communications for coordinating renewable generation (e.g., wind/solar), dispatchable devices (e.g., coal/gas/nuclear generations), demand response, battery & storage facilities, and topology optimization. The Alternating Direction Method of Multipliers (ADMM) has been widely used in the community to address such decentralized optimization problems and, in particular, the AC Optimal Power Flow (AC-OPF). This paper studies how machine learning may help in speeding up the convergence of ADMM for solving AC-OPF. It proposes a novel decentralized machine-learning approach, namely ML-ADMM, where each agent uses deep learning to learn the consensus parameters on the coupling branches. The paper also explores the idea of learning only from ADMM runs that exhibit high-quality convergence properties, and proposes filtering mechanisms to select these runs. Experimental results on test cases based on the French system demonstrate the potential of the approach in speeding up the convergence of ADMM significantly.