Powerformer: A Section-adaptive Transformer for Power Flow Adjustment
This work addresses power flow adjustment for power system operators, but it appears incremental as it builds on existing transformer and graph neural network methods with domain-specific customizations.
The paper tackles the problem of optimizing power dispatch for power flow adjustment in power systems by proposing Powerformer, a transformer architecture with a section-adaptive attention mechanism, which achieved superior performance over baselines on systems including a large-scale 9241-bus European system.
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections. Specifically, our proposed approach, named Powerformer, develops a dedicated section-adaptive attention mechanism, separating itself from the self-attention used in conventional transformers. This mechanism effectively integrates power system states with transmission section information, which facilitates the development of robust state representations. Furthermore, by considering the graph topology of power system and the electrical attributes of bus nodes, we introduce two customized strategies to further enhance the expressiveness: graph neural network propagation and multi-factor attention mechanism. Extensive evaluations are conducted on three power system scenarios, including the IEEE 118-bus system, a realistic 300-bus system in China, and a large-scale European system with 9241 buses, where Powerformer demonstrates its superior performance over several baseline methods.