Application of Big Data in Smart Grids: Energy Analytics

Azamat Marlen, Askar Maxim, Ikechi Augustine Ukaegbu, H S V S Kumar Nunna

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The data that can be extracted from Smart Grids contains a lot of valuable information that would expose hidden opportunities to efficient utilization of existing resources. The data comes in the form of measurements from smart meters/devices. Energy Analytics is irreplaceable for this kind of task. It is a process of collecting data from smart meters/devices both real time and from archival stores and applying some sort of data analysis technique to gain some insight into important correlations, trends, and patterns. This paper offers elaborate discussion on the application of big data in smart grids and describes future prospects for this technology in Kazakhstan. Furthermore, this paper demonstrates a case study of load profiling using the data set that contains energy consumption readings for London households between November 2011 and February 2014. To analyse the data set the K-means clustering algorithm for unsupervised learning is used here. The results of this overview clearly demonstrated the fields where energy analytics can impact the energy segment of Kazakhstan infrastructure and introduces possible ways of overcoming challenges that are present in power systems. However, it is apparent that, in order to realize all these possibilities, it is important to increase the awareness of both government (i.e. the ones to implement the policy) and citizens (i.e. the ones who would make it possible).
Original languageEnglish
Title of host publication21st International Conference on Advanced Communication Technology (ICACT)
PublisherIEEE
Pages402
Number of pages407
Publication statusPublished - May 2 2019

Fingerprint

Smart meters
Unsupervised learning
Clustering algorithms
Energy utilization
Big data

Cite this

Marlen, A., Maxim, A., Ukaegbu, I. A., & Nunna, H. S. V. S. K. (2019). Application of Big Data in Smart Grids: Energy Analytics. In 21st International Conference on Advanced Communication Technology (ICACT) (pp. 402). IEEE.

Application of Big Data in Smart Grids: Energy Analytics. / Marlen, Azamat; Maxim, Askar; Ukaegbu, Ikechi Augustine; Nunna, H S V S Kumar.

21st International Conference on Advanced Communication Technology (ICACT). IEEE, 2019. p. 402.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Marlen, A, Maxim, A, Ukaegbu, IA & Nunna, HSVSK 2019, Application of Big Data in Smart Grids: Energy Analytics. in 21st International Conference on Advanced Communication Technology (ICACT). IEEE, pp. 402.
Marlen A, Maxim A, Ukaegbu IA, Nunna HSVSK. Application of Big Data in Smart Grids: Energy Analytics. In 21st International Conference on Advanced Communication Technology (ICACT). IEEE. 2019. p. 402
Marlen, Azamat ; Maxim, Askar ; Ukaegbu, Ikechi Augustine ; Nunna, H S V S Kumar. / Application of Big Data in Smart Grids: Energy Analytics. 21st International Conference on Advanced Communication Technology (ICACT). IEEE, 2019. pp. 402
@inproceedings{675a13ea54444ba9adb4ce0814738872,
title = "Application of Big Data in Smart Grids: Energy Analytics",
abstract = "The data that can be extracted from Smart Grids contains a lot of valuable information that would expose hidden opportunities to efficient utilization of existing resources. The data comes in the form of measurements from smart meters/devices. Energy Analytics is irreplaceable for this kind of task. It is a process of collecting data from smart meters/devices both real time and from archival stores and applying some sort of data analysis technique to gain some insight into important correlations, trends, and patterns. This paper offers elaborate discussion on the application of big data in smart grids and describes future prospects for this technology in Kazakhstan. Furthermore, this paper demonstrates a case study of load profiling using the data set that contains energy consumption readings for London households between November 2011 and February 2014. To analyse the data set the K-means clustering algorithm for unsupervised learning is used here. The results of this overview clearly demonstrated the fields where energy analytics can impact the energy segment of Kazakhstan infrastructure and introduces possible ways of overcoming challenges that are present in power systems. However, it is apparent that, in order to realize all these possibilities, it is important to increase the awareness of both government (i.e. the ones to implement the policy) and citizens (i.e. the ones who would make it possible).",
author = "Azamat Marlen and Askar Maxim and Ukaegbu, {Ikechi Augustine} and Nunna, {H S V S Kumar}",
year = "2019",
month = "5",
day = "2",
language = "English",
pages = "402",
booktitle = "21st International Conference on Advanced Communication Technology (ICACT)",
publisher = "IEEE",

}

TY - GEN

T1 - Application of Big Data in Smart Grids: Energy Analytics

AU - Marlen, Azamat

AU - Maxim, Askar

AU - Ukaegbu, Ikechi Augustine

AU - Nunna, H S V S Kumar

PY - 2019/5/2

Y1 - 2019/5/2

N2 - The data that can be extracted from Smart Grids contains a lot of valuable information that would expose hidden opportunities to efficient utilization of existing resources. The data comes in the form of measurements from smart meters/devices. Energy Analytics is irreplaceable for this kind of task. It is a process of collecting data from smart meters/devices both real time and from archival stores and applying some sort of data analysis technique to gain some insight into important correlations, trends, and patterns. This paper offers elaborate discussion on the application of big data in smart grids and describes future prospects for this technology in Kazakhstan. Furthermore, this paper demonstrates a case study of load profiling using the data set that contains energy consumption readings for London households between November 2011 and February 2014. To analyse the data set the K-means clustering algorithm for unsupervised learning is used here. The results of this overview clearly demonstrated the fields where energy analytics can impact the energy segment of Kazakhstan infrastructure and introduces possible ways of overcoming challenges that are present in power systems. However, it is apparent that, in order to realize all these possibilities, it is important to increase the awareness of both government (i.e. the ones to implement the policy) and citizens (i.e. the ones who would make it possible).

AB - The data that can be extracted from Smart Grids contains a lot of valuable information that would expose hidden opportunities to efficient utilization of existing resources. The data comes in the form of measurements from smart meters/devices. Energy Analytics is irreplaceable for this kind of task. It is a process of collecting data from smart meters/devices both real time and from archival stores and applying some sort of data analysis technique to gain some insight into important correlations, trends, and patterns. This paper offers elaborate discussion on the application of big data in smart grids and describes future prospects for this technology in Kazakhstan. Furthermore, this paper demonstrates a case study of load profiling using the data set that contains energy consumption readings for London households between November 2011 and February 2014. To analyse the data set the K-means clustering algorithm for unsupervised learning is used here. The results of this overview clearly demonstrated the fields where energy analytics can impact the energy segment of Kazakhstan infrastructure and introduces possible ways of overcoming challenges that are present in power systems. However, it is apparent that, in order to realize all these possibilities, it is important to increase the awareness of both government (i.e. the ones to implement the policy) and citizens (i.e. the ones who would make it possible).

M3 - Conference contribution

SP - 402

BT - 21st International Conference on Advanced Communication Technology (ICACT)

PB - IEEE

ER -