Author Login IJIRT Partner Network (IPN) Login

Neuro-Biomimetic Power Flow Control in Smart Grids Using Spiking Neural Networks

  • Unique Paper ID: 182032
  • Volume: 12
  • Issue: 2
  • PageNo: 509-512
  • Abstract:
  • The emergence of decentralized and intermittently powered smart grids necessitates real-time, scalable control systems capable of handling nonlinear dynamics and frequent disturbances. This study presents a neuro-biomimetic control framework employing Spiking Neural Networks (SNNs) to manage active and reactive power flows. The proposed architecture integrates Leaky Integrate-and-Fire (LIF) neurons and Spike-Timing-Dependent Plasticity (STDP) learning to emulate synaptic plasticity observed in biological systems. Electrical parameters such as voltage magnitudes and frequency deviations are encoded into spike trains using rate coding and processed in an event-driven manner to generate dynamic control signals. The SNN controller operates in closed-loop conjunction with a Newton-Raphson power flow solver and is deployed on IEEE 14-bus and 39-bus test systems. Simulations using Brian2 and MATLAB demonstrate that the SNN-based controller significantly enhances voltage regulation and transient response. Specifically, the system achieves up to 40% reduction in voltage deviation and 30% faster convergence under dynamic loading and contingency scenarios compared to conventional ANN and PID-based approaches. The event-driven computation and unsupervised online learning enable low-power implementation and robustness to topological changes. Furthermore, the architecture is compatible with neuromorphic hardware platforms such as Intel Loihi, enabling real-time on-chip grid control. These results validate the applicability of biologically inspired neural systems to next-generation grid automation and decentralized energy management.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 12
  • Issue: 2
  • PageNo: 509-512

Neuro-Biomimetic Power Flow Control in Smart Grids Using Spiking Neural Networks

Related Articles

Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry