Enduring data analytics for reliable data management in handling smart city services

Kalra, D and Pradhan, M R (2021) Enduring data analytics for reliable data management in handling smart city services. Soft Computing, 25. pp. 12213-12225.

[thumbnail of 15.pdf] Text
15.pdf - Published Version

Download (2MB)


Smart energy management improves the efficiency of the services and computing systems operated in a smart city environment. The heterogeneous environment makes use of artificial intelligence allied technologies for energy management. Depending upon the service data and its processing, energy management is proliferated for providing reliable service outcomes. In this paper, Enduring Data Analytics for Energy Management (EDA-EM) is proposed. The proposed method makes use of data distribution factors for optimal energy distribution. In this process, the cumulative and independent data streams require different energy requirements. This requirement is identified using principal component analysis for identifying other data streams. The data stream is a series of feature vectors describing one or more underlying patterns together. A stream framework demonstrates how the underlying patterns of different stream elements can be reconstructed. The stream classification helps to allocate desired energy without overloaded instances in the big data processing. The remaining and available renewable energy is distributed for the classified streams in handling big data. Big data streaming indicates that Big Data is processed rapidly to gain insight into it in virtual environments. The production data are in movement. The data are in trend. Ideally, big data streaming is a frequency solution that processes a prolonged data stream. In this allocation process, renewable energy available for the successive handling interval is predicted for improving the seamlessness in the data processing. The proposed method's performance is verified using energy distribution ratio, conservation rate, and data loses, processing rate, and processing delay. In EDA-EM, the achieved distribution ratio is 95.13% which is comparatively reasonable than other approaches.

Affiliation: Skyline University College
SUC Author(s): Kalra, D and Pradhan, M R ORCID: https://orcid.org/0000-0002-0115-2722
All Author(s): Kalra, D and Pradhan, M R
Item Type: Article
Uncontrolled Keywords: Big data analytics � Energy management � PCA � Sustainable energy
Subjects: B Information Technology > BD Big Data Analitics
Divisions: Skyline University College > School of IT
Depositing User: Mr Veeramani Rasu
Date Deposited: 02 Feb 2022 14:55
Last Modified: 02 Feb 2022 14:55
URI: https://research.skylineuniversity.ac.ae/id/eprint/76
Publisher URL: https://doi.org/10.1007/s00500-021-05892-1
Publisher OA policy: https://v2.sherpa.ac.uk/id/publication/28648
Related URLs:

Actions (login required)

View Item
View Item
Statistics for SkyRep ePrint 76 Statistics for this ePrint Item