Active Distribution System Coordinated Control Method via Artificial Intelligence
This addresses the problem of voltage and loading variations in power distribution systems for grid operators, but it appears incremental as it builds on existing AI methods.
The paper tackles the challenge of controlling active distribution systems with many small, variable power resources to maintain reliable and secure power under normal voltages and frequency, and presents a neural network with self-attention mechanism that shows promising preliminary results.
The increasing deployment of end use power resources in distribution systems created active distribution systems. Uncontrolled active distribution systems exhibit wide variations of voltage and loading throughout the day as some of these resources operate under max power tracking control of highly variable wind and solar irradiation while others exhibit random variations and/or dependency on weather conditions. It is necessary to control the system to provide power reliably and securely under normal voltages and frequency. Classical optimization approaches to control the system towards this goal suffer from the dimensionality of the problem and the need for a global optimization approach to coordinate a huge number of small resources. Artificial Intelligence (AI) methods offer an alternative that can provide a practical approach to this problem. We suggest that neural networks with self-attention mechanisms have the potential to aid in the optimization of the system. In this paper, we present this approach and provide promising preliminary results.