Electrical power grids used to compute image recognition tasks
Infrastructure-Native Computing with Electric Power Grids
Emerging Technologies
Summary
Computers usually process information using specialized hardware. This paper explores using electric power grids—systems built for supplying electricity—to perform computing tasks by manipulating voltages and currents. The authors show through simulations that an electrical network can classify images like handwritten numbers and clothes with good accuracy. They also find that how the system is connected and controlled affects its computing ability. This work suggests power grids could double as computing devices in some settings.
What this means in practice
- •For power grid engineers: Use electric grid topology and control to perform scalable computations alongside energy delivery for monitoring or ancillary grid tasks.
- •For industrial control designers: Design power electronics controllers that exploit electrical network laws for low-overhead feature extraction in sensing applications.
Authors
Yubo Song, Subham Sahoo, Freja Basse
Abstract
Computing is conventionally implemented by hardware engineered for information processing. Here we investigate infrastructure-native computing: the use of a physical system built for another primary function as a fixed computational operator. In time-domain simulations of an IEEE 14-bus electrical network, Kirchhoff's current law and Ohm's law relate voltage-reference perturbations applied at distributed controllable nodes interfaced by power electronics converters to current responses through a topology-dependent transformation. A trained digital encoder and decoder exploit this transformation for image classification, reaching 91.5% accuracy on MNIST and 82.25% on Fashion-MNIST. The modeled operator is represented by 933 surrogate parameters, compared with 12,340 task-trained parameters for an accuracy-matched fully connected core transformation. Current superposition further supports concurrent spatial sharing of the operator and sequential temporal reuse, with per-stream accuracies above 85% and 93%, respectively, in surrogate-model evaluations. Evaluations on CIFAR-10 and repeated 10-class tasks sampled from a Butterflies-and-Moths dataset show that the incremental utility of the physical operator depends on the representation supplied by upstream digital feature extraction. These results provide a simulation-based proof of concept for infrastructure-native computing with electrical networks and identify topology, accessible control channels, and input representation as determinants of its computational utility.