Email this article Footprint Analysis of the Gaussian Mixture Model (GMM) for Populating Overhead Low Voltage Broadband over Power Lines (OV LV BPL) Topology Class Maps
Abstract
Until now, Neural Network Topology Generator Methodology (NNTGM) has been theoretically proposed and assessed so that its generated overhead low voltage broadband over power lines topologies (NNTGM OV LV BPL topologies) may populate the existing OV LV BPL topology classes in different footprint patterns on the OV LV BPL topology class maps. With reference to the OV LV BPL topology class maps, which are defined by the graphical combination of average theoretical channel attenuation (ACA) and the standard deviation of the theoretical channel attenuation (SDCA) of the OV LV BPL topologies, Gaussian Mixture Model (GMM) is here proposed and treated as an alternative yet simple population method. In fact, GMM is a weighted sum of multiple Normal Distributions (NDs), which have been until now exploited as error distributions for describing the measurement differences during the BPL topology channel attenuation analysis. In this paper, the effect of the parameters of the GMM on the relative position and the size of the GMM OV LV BPL topology footprints on the OV LV BPL topology class maps is here examined. The effect study of the GMM population is supported by the suitable Graphical Performance Indicators (GPIs) already used during the NNTGM population.
Citation: Lazaropoulos, A. (2026). Footprint Analysis of the Gaussian Mixture Model (GMM) for Populating Overhead Low Voltage Broadband over Power Lines (OV LV BPL) Topology Class Maps. Trends in Renewable Energy, 12(1), 33-65. doi:http://dx.doi.org/10.17737/tre.2026.12.1.00199
Keywords
Full Text:
FULL TEXT (PDF)References
Lazaropoulos, A. G., & Leligou, H. C. (2022). Fiber optics and broadband over power lines in smart grid: a communications system architecture for overhead high-voltage, medium-voltage and low-voltage power grids. Progress in Electromagnetics Research B, 95, 185-205. doi: https://doi.org/10.2528/PIERB22062502
Lazaropoulos, A. G., & Leligou, H. C. (2024). Integration of LiFi, BPL, and Fiber Optic Technologies in Smart Grid Backbone Networks: A Proposal for Exploiting the LiFi LED Street Lighting Networks of Power Utilities and Smart Cities. Sustainability, 16(2), 686.
Kippke Salomón, M. A., Carou Álvarez, J. M., Suárez Ramón, L., & Arboleya, P. (2025). Self-Diagnostic Advanced Metering Infrastructure Based on Power-Line Communication: A Study Case in Spanish Low-Voltage Distribution Networks. Energies (19961073), 18(7).
Kalula, S. R., Dida, A. M., & Zaipuna, Y. O. (2024). Towards a low-cost sustainable broadband solution in rural areas of low and middle-income countries: Tanzania’s backhaul perspective. International Journal of Engineering, Science and Technology, 16(1), 20-34.
Fernandez, J. H., Jarouf, A., Omri, A., & Di Pietro, R. (2025). Leveraging Power Line Communications for Grid Intelligence: A Comprehensive Review of Signal-Based Techniques to Infer Grid Information. IEEE Access, 13, 118423-118437. DOI: 10.1109/ACCESS.2025.3586095
Goktas, P., & Ibrahim, S. (2025). Energy Management and Smart Grid Communication. AI and ML Techniques in IoT‐based Communication: A Path to Sustainable Development Goals, 179-212.
Lazaropoulos, A.G. (2024). Virtual Topologies for Populating Overhead Low-Voltage Broadband over Powerlines Topology Classes by Exploiting Neural Network Topology Generator Methodology (NNTGM) - Part 1: Theory. Trends in Renewable Energy, 10(3), 301-314. doi: http://dx.doi.org/10.17737/tre.2024.10.3.00181
Lazaropoulos, A.G. (2024). Virtual Topologies for Populating Overhead Low-Voltage Broadband over Powerlines Topology Classes by Exploiting Neural Network Topology Generator Methodology (NNTGM) – Part 2: Numerical Results. Trends in Renewable Energy, 10(3), 315-334. doi: http://dx.doi.org/10.17737/tre.2024.10.3.00182
Lazaropoulos, A. G. (2025). The Impact of Operating Frequencies and Neural Network Training Program Properties on the Performance of Neural Network Topology Generator Methodology. Trends in Renewable Energy, 11(2), 237-254.
Lazaropoulos, A. G., & Leligou, H. C. (2023). 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. Trends in Renewable Energy, 9(1), 34-77. doi: http://dx.doi.org/10.17737/tre.2023.9.1.00149
Lazaropoulos, A. G., & Leligou, H. C. (2024). Big Data and Neural Networks in Smart Grid - Part 1: The Impact of Piecewise Monotonic Data Approximation Methods on the Performance of Neural Network Identification Methodology for the Distribution Line and Branch Line Length Approximation of Overhead Low-Voltage Broadband over Powerlines Networks. Trends in Renewable Energy, 10, 30-66. doi: https://doi.org/10.17737/tre.2024.10.1.00164
Lazaropoulos, A. G., & Leligou, H. C. (2024). Big Data and Neural Networks in Smart Grid - Part 2: The Impact of Piecewise Monotonic Data Approximation Methods on the Performance of Neural Network Identification Methodology for the Distribution Line and Branch Line Length Approximation of Overhead Low-Voltage Broadband over Powerlines Networks. Trends in Renewable Energy, 10, 67-97. doi: https://doi.org/10.17737/tre.2024.10.1.00165
Lazaropoulos, A. G. (2020). Business Analytics and IT in Smart Grid - Part 1: The Impact of Measurement Differences on the iSHM Class Map Footprints of Overhead Low-Voltage Broadband over Power Lines Topologies. Trends in Renewable Energy, 6(2), 156-186. doi: http://dx.doi.org/10.17737/tre.2020.6.2.00117
Lazaropoulos, A. G. (2020). Business Analytics and IT in Smart Grid - Part 2: The Qualitative Mitigation Impact of Piecewise Monotonic Data Approximations on the iSHM Class Map Footprints of Overhead Low-Voltage Broadband over Power Lines Topologies Contaminated by Measurement Differences. Trends in Renewable Energy, 6(2), 187-213. doi: http://dx.doi.org/10.17737/tre.2020.6.2.00118
Lazaropoulos, A. G. (2020). Business Analytics and IT in Smart Grid - Part 3: New Application Aspect and the Quantitative Mitigation Analysis of Piecewise Monotonic Data Approximations on the iSHM Class Map Footprints of Overhead Low-Voltage Broadband over Power Lines Topologies Contaminated by Measurement Differences. Trends in Renewable Energy, 6(2), 214-233. doi: http://dx.doi.org/10.17737/tre.2020.6.2.00119
Lazaropoulos, A. G. (2017). Main Line Fault Localization Methodology in Smart Grid - Part 2: Extended TM2 Method, Measurement Differences and L1 Piecewise Monotonic Data Approximation for the Overhead Medium-Voltage Broadband over Power Lines Networks Case. Trends in Renewable Energy, 3, 26-61. doi: https://doi.org/10.17737/tre.2017.3.3.0037
Lazaropoulos, A. G. (2018). Smart Energy and Spectral Efficiency (SE) of Distribution Broadband over Power Lines (BPL) Networks - Part 2: L1PMA, L2WPMA and L2CXCV for SE against Measurement Differences in Overhead Medium-Voltage BPL Networks. Trends in Renewable Energy, 4(2), 185-212.
Lazaropoulos, A. G. (2016). Measurement Differences, Faults and Instabilities in Intelligent Energy Systems - Part 1: Identification of Overhead High-Voltage Broadband over Power Lines Network Topologies by Applying Topology Identification Methodology (TIM). Trends in Renewable Energy, 2, 85-112. doi: https://doi.org/10.17737/tre.2016.2.3.0026
Lazaropoulos, A. G. (2016). Best L1 piecewise monotonic data approximation in overhead and underground medium-voltage and low-voltage broadband over power lines networks: Theoretical and practical transfer function determination. Hindawi Journal of Computational Engineering, 2016, 6762390, 24 pp. doi: https://doi.org/10.1155/2016/6762390
Okoh, D., 2016. Computer Neural Networks on MATLAB. CreateSpace Independent Publishing Platform.
Okoh, D. (2020). Neural Network Training Code. Available at: https://www.mathworks.com/matlabcentral/fileexchange/59362-neural-network-training-code (Accessed: 22 April 2020).
Lazaropoulos, A. G., & Cottis, P. G. (2010). Broadband transmission via underground medium-voltage power lines—Part I: Transmission characteristics. IEEE Transactions on Power Delivery, 25(4), 2414-2424. doi: https://doi.org/10.1109/TPWRD.2010.2073829
Lazaropoulos, A. G. (2012). Towards modal integration of overhead and underground low-voltage and medium-voltage power line communication channels in the smart grid landscape: Model expansion, broadband signal transmission characteristics, and statistical performance metrics (Invited paper). ISRN Signal Processing, 2012, 1-17. doi: https://doi.org/10.1155/2012/121628
Lazaropoulos, A. G. (2019). Virtual Indicative Broadband over Power Lines Topologies for Respective Subclasses by Adjusting Channel Attenuation Statistical Distribution Parameters of Statistical Hybrid Models (Class Maps) – Part 1: Theory. Trends in Renewable Energy, 5(3), 237-257. doi: http://dx.doi.org/10.17737/tre.2019.5.3.0099
Lazaropoulos, A. G. (2019). Virtual Indicative Broadband over Power Lines Topologies for Respective Subclasses by Adjusting Channel Attenuation Statistical Distribution Parameters of Statistical Hybrid Models (Class Maps) – Part 2: Numerical Results for the Overhead and Underground Medium-Voltage Power Grids. Trends in Renewable Energy, 5(3), 258-281. doi: http://dx.doi.org/10.17737/tre.2019.5.3.00100
Lazaropoulos, A. G. (2019). Virtual Indicative Broadband over Power Lines Topologies for Respective Subclasses by Adjusting Channel Attenuation Statistical Distribution Parameters of Statistical Hybrid Models (Class Maps) – Part 3: The Case of Overhead Transmission Power Grids. Trends in Renewable Energy, 5(3), 282-306. doi: http://dx.doi.org/10.17737/tre.2019.5.3.00101
DOI: http://dx.doi.org/10.17737/tre.2026.12.1.00199
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Athanasios G. Lazaropoulos
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 License.Copyright @2014-2026 Trends in Renewable Energy (ISSN: 2376-2136, online ISSN: 2376-2144)