Surge detection for smart grid power distribution using a regression-based signal processing model

The smart grid depends on cutting-edge internet and communication technology, which elimi-nates the need for human intervention and enhances automation of electricity distribution. Power connections convey actuator and monitoring signals to allow transmission distortions to be identified over long distances. This paper introduces a Surge-Detection Signal Processing Model (SDSPM) to augment the detection of signals in smart grids, which relies on the signal-to -distortion ratio observed between definite power distributions. A linear regression model pro-vides decision-making support to prevent backdrops in smart grids. Through the use of this regression model, the measurement of definitive power distribution and surge occurrence means that backdrops and detection time can be reduced. The power surges and abnormal distribution are minimized, and the available power at each terminal is maximized. A 9.72% lower surge rate, an 11.86% higher distribution ratio, an 8.13% higher signal strength and an improvement in the detection rate of 12.92% were achieved.

Automated summary

This paper introduces a model to enhance signal detection in smart grids. Through the use of a linear regression model, the model reduces background and detection time, maximizing available power at each terminal. Experimental results show that the model achieves a lower surge rate, higher distribution ratio, signal strength, and detection rate.