glassoformer: a query-sparse transformer for post-fault power grid voltage prediction
This addresses the need for efficient and accurate voltage prediction in power grid management, though it appears incremental as it modifies an existing transformer method for a specific domain.
The paper tackled the problem of predicting post-fault voltage in power grids by proposing GLassoformer, a transformer architecture that uses group Lasso regularization to sparsify queries, resulting in better accuracy and stability compared to existing benchmarks.
We propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLassoformer shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.