@inproceedings{4969a82737a34b7ebb3124760c810c44,
title = "Distributed computing for smart meter data management for electrical utility applications",
abstract = "With the advent of Internet-of-Things (IoT) devices, including smart meters and sensors in the smart grid, there has been immense research interest in big data management, analytics, and parallel processing of data. However, complex hardware and software parameters configurations and in-depth understanding of the data processing design are essential for efficient utilization of big data analytics platforms. In this work, we analyze the parallelization of load prediction by utilizing spark regression python library to assess the performance with workloads of up to 8 nodes. The results of different configurations have been studied and analyzed against the performance of Apache Spark. It was found that a trade-off between the number of nodes and cores is necessary to perform efficient parallel computing. Multiple sets of combinations of nodes and cores are considered in this paper to evaluate the performance. The work also signifies the importance of high-performance computing capability for smart meters big data management. The obtained results indicate that the computational time is not only dependent on the data size but also on the number of compute nodes and the number of cores assigned to run the job.",
keywords = "Apache-Spark, Big data, High performance computing, Load forecast, Parallel computing, Smart grid",
author = "Ameema Zainab and Refaat, {Shady S.} and Haitham Abu-Rub and Othmane Bouhali",
note = "Funding Information: ACKNOWLEDGEMENT This publication was made possible by NPRP grant [NPRP10-0101-170082] from the Qatar National Research Fund (a member of Qatar Foundation) and the co-funding by IBERDROLA QSTP LLC. The statements made herein are solely the responsibility of the author[s]. Publisher Copyright: {\textcopyright} 2020 IEEE.; 30th International Conference on Cybernetics and Informatics, K and I 2020 ; Conference date: 29-01-2020 Through 01-02-2020",
year = "2020",
month = jan,
doi = "10.1109/KI48306.2020.9039899",
language = "English",
series = "Proceedings of the 30th International Conference on Cybernetics and Informatics, K and I 2020",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
editor = "Jan Ciganek and Stefan Kozak and Alena Kozakova",
booktitle = "Proceedings of the 30th International Conference on Cybernetics and Informatics, K and I 2020",
address = "United States",
}