NP-NDS: A Nature-Powered Nonlinear Dynamical System for Power Grid Forecasting

Chunshu Wu, Ruibing Song, Chuan Liu, Yuqing Wang, Yousu Chen, Ang Li, Dongfang Liu, Ying Nian Wu, Michael Huang, Tong Geng
Proceedings of the Third Learning on Graphs Conference, PMLR 269:27:1-27:14, 2025.

Abstract

The power grid is a critical dynamical system that forms the backbone of modern society, powering everything from household appliances to complex industrial machinery. However, this essential system is not without vulnerabilities – as electricity travels at lightspeed, unanticipated failures can cause catastrophic consequences such as country-wide blackouts in a cascading manner. In response to such threats, we introduce NP-NDS, a nature-powered nonlinear dynamical system designed to accurately and rapidly predict power grids as macroscopic dynamical systems in the real world. In particular, NP-NDS is established through a Hamiltonian-Hardware co-design: First, NP-NDS employs a hardware-friendly serial-additive Hamiltonian based on Chebyshev series for accurately capturing highly nonlinear interactions among power grid nodes, coupled with node-relation-aware training for high accuracy. Second, NP-NDS features a fully CMOS-based hardware dynamical system governed by the proposed Hamiltonian, facilitating inferences with "speed of electrons". Results show that NP-NDS achieves, on average, \textdollar 2.3\times 10\^{}3\textdollar speedup and \textdollar 10\^{}5\times\textdollar energy reduction with 23.6% and 28.2% decrease in MAE and RMSE compared to GNNs on power grid forecasting datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v269-wu25a, title = {NP-NDS: A Nature-Powered Nonlinear Dynamical System for Power Grid Forecasting}, author = {Wu, Chunshu and Song, Ruibing and Liu, Chuan and Wang, Yuqing and Chen, Yousu and Li, Ang and Liu, Dongfang and Wu, Ying Nian and Huang, Michael and Geng, Tong}, booktitle = {Proceedings of the Third Learning on Graphs Conference}, pages = {27:1--27:14}, year = {2025}, editor = {Wolf, Guy and Krishnaswamy, Smita}, volume = {269}, series = {Proceedings of Machine Learning Research}, month = {26--29 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v269/main/assets/wu25a/wu25a.pdf}, url = {https://proceedings.mlr.press/v269/wu25a.html}, abstract = {The power grid is a critical dynamical system that forms the backbone of modern society, powering everything from household appliances to complex industrial machinery. However, this essential system is not without vulnerabilities – as electricity travels at lightspeed, unanticipated failures can cause catastrophic consequences such as country-wide blackouts in a cascading manner. In response to such threats, we introduce NP-NDS, a nature-powered nonlinear dynamical system designed to accurately and rapidly predict power grids as macroscopic dynamical systems in the real world. In particular, NP-NDS is established through a Hamiltonian-Hardware co-design: First, NP-NDS employs a hardware-friendly serial-additive Hamiltonian based on Chebyshev series for accurately capturing highly nonlinear interactions among power grid nodes, coupled with node-relation-aware training for high accuracy. Second, NP-NDS features a fully CMOS-based hardware dynamical system governed by the proposed Hamiltonian, facilitating inferences with "speed of electrons". Results show that NP-NDS achieves, on average, \textdollar 2.3\times 10\^{}3\textdollar speedup and \textdollar 10\^{}5\times\textdollar energy reduction with 23.6% and 28.2% decrease in MAE and RMSE compared to GNNs on power grid forecasting datasets.} }
Endnote
%0 Conference Paper %T NP-NDS: A Nature-Powered Nonlinear Dynamical System for Power Grid Forecasting %A Chunshu Wu %A Ruibing Song %A Chuan Liu %A Yuqing Wang %A Yousu Chen %A Ang Li %A Dongfang Liu %A Ying Nian Wu %A Michael Huang %A Tong Geng %B Proceedings of the Third Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2025 %E Guy Wolf %E Smita Krishnaswamy %F pmlr-v269-wu25a %I PMLR %P 27:1--27:14 %U https://proceedings.mlr.press/v269/wu25a.html %V 269 %X The power grid is a critical dynamical system that forms the backbone of modern society, powering everything from household appliances to complex industrial machinery. However, this essential system is not without vulnerabilities – as electricity travels at lightspeed, unanticipated failures can cause catastrophic consequences such as country-wide blackouts in a cascading manner. In response to such threats, we introduce NP-NDS, a nature-powered nonlinear dynamical system designed to accurately and rapidly predict power grids as macroscopic dynamical systems in the real world. In particular, NP-NDS is established through a Hamiltonian-Hardware co-design: First, NP-NDS employs a hardware-friendly serial-additive Hamiltonian based on Chebyshev series for accurately capturing highly nonlinear interactions among power grid nodes, coupled with node-relation-aware training for high accuracy. Second, NP-NDS features a fully CMOS-based hardware dynamical system governed by the proposed Hamiltonian, facilitating inferences with "speed of electrons". Results show that NP-NDS achieves, on average, \textdollar 2.3\times 10\^{}3\textdollar speedup and \textdollar 10\^{}5\times\textdollar energy reduction with 23.6% and 28.2% decrease in MAE and RMSE compared to GNNs on power grid forecasting datasets.
APA
Wu, C., Song, R., Liu, C., Wang, Y., Chen, Y., Li, A., Liu, D., Wu, Y.N., Huang, M. & Geng, T.. (2025). NP-NDS: A Nature-Powered Nonlinear Dynamical System for Power Grid Forecasting. Proceedings of the Third Learning on Graphs Conference, in Proceedings of Machine Learning Research 269:27:1-27:14 Available from https://proceedings.mlr.press/v269/wu25a.html.

Related Material