Answers are grounded in this paper and cite their sources.
Spiking neural network (SNN) offers event‐driven and spatio‐temporal information processing capabilities that are potentially well suited to modern power system applications. This survey systematically reviews the development and application of SNN in power systems. The survey emphasises neuron models, network architectures, spike encoding methods, learning rules, reasoning mechanisms and implementation strategies. In the present work, a state‐of‐the‐art review is presented on SNN covering diverse power system applications including load forecasting, fault diagnosis, renewable energy integration, distributed energy resources, energy management and synchrophasor‐based monitoring etc. The benchmark power system datasets, spike‐based data representation, neuromorphic and conventional hardware and the computational and energy requirements of SNN relative to conventional neural networks are also covered. The survey identifies key limitations related to data availability, spike encoding, training complexity, hardware dependence and application‐specific validation. Nevertheless, the present work also highlights research directions for SNN deployment in modern power systems.
No takes yet. Share an insight, caveat, or question.
Jha et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: