Information Technology, Artificial Intelligence and Machine Learning in Smart Grid – Performance Comparison between Topology Identification Methodology and Neural Network Identification Methodology for the Branch Number Approximation of Overhead Low-Voltage Broadband over Power Lines Network Topologies

Abstract

Broadband over Power Lines (BPL) networks that are deployed across the smart grid can benefit from the usage of machine learning, as smarter grid diagnostics are collected and analyzed. In this paper, the neural network identification methodology of Overhead Low-Voltage (OV LV) BPL networks that aims at identifying the number of branches for a given OV LV BPL topology channel attenuation behavior is proposed, which is simply denoted as NNIM-BNI. In order to identify the branch number of an OV LV BPL topology through its channel attenuation behavior, NNIM-BNI exploits the Deterministic Hybrid Model (DHM), which has been extensively tested in OV LV BPL networks for their channel attenuation determination, and the OV LV BPL topology database of Topology Identification Methodology (TIM). The results of NNIM-BNI towards the branch number identification of OV LV BPL topologies are compared against the ones of a newly proposed TIM-based methodology, denoted as TIM-BNI.

Artificial Intelligence, Machine Learning and Neural Networks for Tomography in Smart Grid – Performance Comparison between Topology Identification Methodology and Neural Network Identification Methodology for the Distribution Line and Branch Line Length Approximation of Overhead Low-Voltage Broadband over Power Lines Network Topologies

“…The evolution of the today's traditional power grid to a modern power grid that is upgraded with an intelligent IP-based communications network may support a myriad of broadband applications [1][2][3][4][5]. Among the communications solutions that may allow this smart grid transformation, Broadband over Power Lines (BPL) technology exploits the available wired power grid infrastructure while permitting the coexistence with other communications solutions through their BPL wireline/wireless interfaces [5][6][7][8].…”

“…Until now, a plethora of channel models has been proposed or properly adjusted from other communications technologies in the literature for characterizing BPL channels; say, deterministic, statistical, bottom-up, top-down BPL channel models or appropriate syntheses of the aforementioned ones [9], [11], [16][17][18][19][20][21][22][23][24][25][26][27][28]. Similarly to [1], the deterministic hybrid model (DHM) is here applied in the overhead low voltage (OV LV) BPL networks for modeling BPL signal propagation and transmission across them and thus providing critical broadband performance metrics, which further act as the big data feed for the broadband applications. In this extension paper, Topology Identification Methodology (TIM), which has been proposed in [29,30] and is one of the broadband applications supported by BPL technology in the smart grid, stores in its TIM BPL topology database, analyzes and reports with the DHM the channel attenuation measurements of various BPL topologies.…”

“…In [29,30], TIM approximates the exact topological characteristics (i.e., number of branches, length of branches, length of main lines and branch terminations) of an examined BPL topology by comparing its channel attenuation measurements with the theoretical channel attenuation results stored in the TIM BPL topology database. In [1], TIM has been extended to TIM-based Branch Number Identification methodology (TIM-BNI) so that the number of branches of an OV LV BPL topology whose theoretical channel attenuation results are known can be approximated when this examined OV LV BPL topology is not among the OV LV BPL topologies of the TIM BPL topology database. In this extension paper, TIM and TIM-BNI are further extended to the new TIM-based methodology for approximating the distribution line and branch line lengths (TIM-LLA) of an examined OV LV BPL topology when the examined topology is not among the OV LV BPL ones of the TIM BPL topology database.…”

“…In [1], the set of the supported broadband applications by the smart grid has been enriched by experimenting with artificial intelligence (AI) and machine learning (ML) capabilities. By exploiting the available big data of the TIM BPL topology database for the OV LV BPL topologies and the neural network architectures / training, the neural network identification methodology for the branch number identification (NNIM-BNI) of OV LV BPL topologies has been proposed in [1].…”

“…

Until now, the neural network identification methodology for the branch number identification (NNIM-BNI) has identified the number of branches for a given overhead low-voltage broadband over powerlines (OV LV BPL) topology channel attenuation behavior [1]. In this extension paper, NNIM-BNI is extended so that the lengths of the distribution lines and branch lines for a given OV LV BPL topology channel attenuation behavior can be approximated; say, the tomography of the OV LV BPL topology.

…”