Energy saving methods reduce neural operator costs in virtual sensing
Energy-efficient operation of neural operators for virtual sensing
Machine LearningPerformance
Summary
Virtual sensing is a way to recreate physical fields (like temperature or flow) using changing measurements on a fixed setup. The authors show that reusing parts of the neural network’s spatial calculations lowers the energy used for updates while keeping prediction accuracy. In their tests on a heat exchanger, energy savings ranged from about 1% to over 20% depending on how often updates happened. They found that reusing computation is more effective at higher update frequencies and is influenced by overhead costs like setup time. This helps understand when and how to save energy in repeated virtual sensing tasks.
What this means in practice
- •For industrial process engineers: Operate neural virtual sensors more efficiently in systems like heat exchangers by reducing repeated computation energy costs during frequent state updates.
- •For cloud infrastructure managers: Manage and schedule neural operator computations to reduce energy consumption and hardware load when virtual sensing tasks run repeatedly at varying rates.
Authors
Jason Yoo, Samrendra Roy, Souvik Chakraborty, Syed Bahauddin Alam
Abstract
Virtual sensing repeatedly reconstructs physical fields from changing observations, often on a fixed geometry. We investigate how shared spatial computation reduces the energy of these updates while retaining the selected checkpoint and its evaluated predictions. In a heat-exchanger service, standard compiler freezing and explicit trunk reuse give similar operating energy reductions relative to graph replay: approximately 1% at one request per second and 20% at forty requests per second. In 15 W mode with fixed clocks, reuse with graph replay completes the same request sequence with 22.0 to 22.5% less energy than eager execution, including preparation and waiting. DeepONet and Fourier neural operator (FNO) controls distinguish the effects of reusable arithmetic and launch overhead. Preparation, artifact construction, and worker replacement add costs outside repeated inference. These results connect operator structure to operating energy and show how update frequency and execution lifetime govern the benefit of computation reuse in physical-field virtual sensing.