IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions

Usman Ali; Muhammad Umer Ramzan; Waqas Ali; Muhammad Ehsan Rana; Abdul Qayyum

doi:10.1109/SCOReD60679.2023.10563825

IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions

Usman Ali
, Muhammad Umer Ramzan
, Waqas Ali
, Muhammad Ehsan Rana
, Abdul Qayyum

GIFT University
University of Engineering and Technology Lahore
Asia Pacific University of Technology and Innovation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper unveils a meticulous creation process for an Internet of Things (IoT)-powered intelligent energy monitoring framework. This system adeptly gauges current, voltage, active power, power factor, energy, and unit consumption in real-time, spanning hourly, weekly, and monthly intervals. This instantaneous data is seamlessly relayed via the integrated WiFi module within the ESP32 module. Subsequently, the cloud orchestrates the dissemination of these measurements to an Android application, wherein real-time values are conveniently visualized. The Android application, far from being restricted to visualization, demonstrates an additional facet by harnessing machine learning-powered time-series forecasting models to predict future unit consumption. Remarkably, the implementation of the ARIMA, Prophet, and LSTM models for future unit prediction highlights LSTM's superiority in accuracy over the other models.

Original language	English
Title of host publication	2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	672-677
Number of pages	6
ISBN (Electronic)	9798350318821
DOIs	https://doi.org/10.1109/SCOReD60679.2023.10563825
Publication status	Published - 2023
Externally published	Yes
Event	21st IEEE Student Conference on Research and Development, SCOReD 2023 - Kuala Lumpur, Malaysia Duration: 13 Dec 2023 → 14 Dec 2023

Publication series

Name	2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023

Conference

Conference	21st IEEE Student Conference on Research and Development, SCOReD 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	13/12/23 → 14/12/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

ESP32
Internet of Things
Machine Learning
Smart Meter
Time Series Forecasting

Access to Document

10.1109/SCOReD60679.2023.10563825

Cite this

Ali, U., Ramzan, M. U., Ali, W., Rana, M. E., & Qayyum, A. (2023). IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions. In 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023 (pp. 672-677). (2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCOReD60679.2023.10563825

Ali, Usman ; Ramzan, Muhammad Umer ; Ali, Waqas et al. / IoT-Driven Smart Energy Monitoring : Real-time Insights and AI-Based Unit Predictions. 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 672-677 (2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023).

@inproceedings{7a8a03526eef4fcb939031944760850b,

title = "IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions",

abstract = "This paper unveils a meticulous creation process for an Internet of Things (IoT)-powered intelligent energy monitoring framework. This system adeptly gauges current, voltage, active power, power factor, energy, and unit consumption in real-time, spanning hourly, weekly, and monthly intervals. This instantaneous data is seamlessly relayed via the integrated WiFi module within the ESP32 module. Subsequently, the cloud orchestrates the dissemination of these measurements to an Android application, wherein real-time values are conveniently visualized. The Android application, far from being restricted to visualization, demonstrates an additional facet by harnessing machine learning-powered time-series forecasting models to predict future unit consumption. Remarkably, the implementation of the ARIMA, Prophet, and LSTM models for future unit prediction highlights LSTM's superiority in accuracy over the other models.",

keywords = "ESP32, Internet of Things, Machine Learning, Smart Meter, Time Series Forecasting",

author = "Usman Ali and Ramzan, \{Muhammad Umer\} and Waqas Ali and Rana, \{Muhammad Ehsan\} and Abdul Qayyum",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 21st IEEE Student Conference on Research and Development, SCOReD 2023 ; Conference date: 13-12-2023 Through 14-12-2023",

year = "2023",

doi = "10.1109/SCOReD60679.2023.10563825",

language = "English",

series = "2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "672--677",

booktitle = "2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023",

}

Ali, U, Ramzan, MU, Ali, W, Rana, ME & Qayyum, A 2023, IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions. in 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023. 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023, Institute of Electrical and Electronics Engineers Inc., pp. 672-677, 21st IEEE Student Conference on Research and Development, SCOReD 2023, Kuala Lumpur, Malaysia, 13/12/23. https://doi.org/10.1109/SCOReD60679.2023.10563825

IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions. / Ali, Usman; Ramzan, Muhammad Umer; Ali, Waqas et al.
2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 672-677 (2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - IoT-Driven Smart Energy Monitoring

T2 - 21st IEEE Student Conference on Research and Development, SCOReD 2023

AU - Ali, Usman

AU - Ramzan, Muhammad Umer

AU - Ali, Waqas

AU - Rana, Muhammad Ehsan

AU - Qayyum, Abdul

PY - 2023

Y1 - 2023

N2 - This paper unveils a meticulous creation process for an Internet of Things (IoT)-powered intelligent energy monitoring framework. This system adeptly gauges current, voltage, active power, power factor, energy, and unit consumption in real-time, spanning hourly, weekly, and monthly intervals. This instantaneous data is seamlessly relayed via the integrated WiFi module within the ESP32 module. Subsequently, the cloud orchestrates the dissemination of these measurements to an Android application, wherein real-time values are conveniently visualized. The Android application, far from being restricted to visualization, demonstrates an additional facet by harnessing machine learning-powered time-series forecasting models to predict future unit consumption. Remarkably, the implementation of the ARIMA, Prophet, and LSTM models for future unit prediction highlights LSTM's superiority in accuracy over the other models.

AB - This paper unveils a meticulous creation process for an Internet of Things (IoT)-powered intelligent energy monitoring framework. This system adeptly gauges current, voltage, active power, power factor, energy, and unit consumption in real-time, spanning hourly, weekly, and monthly intervals. This instantaneous data is seamlessly relayed via the integrated WiFi module within the ESP32 module. Subsequently, the cloud orchestrates the dissemination of these measurements to an Android application, wherein real-time values are conveniently visualized. The Android application, far from being restricted to visualization, demonstrates an additional facet by harnessing machine learning-powered time-series forecasting models to predict future unit consumption. Remarkably, the implementation of the ARIMA, Prophet, and LSTM models for future unit prediction highlights LSTM's superiority in accuracy over the other models.

KW - ESP32

KW - Internet of Things

KW - Machine Learning

KW - Smart Meter

KW - Time Series Forecasting

UR - https://www.scopus.com/pages/publications/85197679635

U2 - 10.1109/SCOReD60679.2023.10563825

DO - 10.1109/SCOReD60679.2023.10563825

M3 - Conference contribution

AN - SCOPUS:85197679635

T3 - 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023

SP - 672

EP - 677

BT - 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 December 2023 through 14 December 2023

ER -

Ali U, Ramzan MU, Ali W, Rana ME, Qayyum A. IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions. In 2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 672-677. (2023 IEEE 21st Student Conference on Research and Development, SCOReD 2023). doi: 10.1109/SCOReD60679.2023.10563825

IoT-Driven Smart Energy Monitoring: Real-time Insights and AI-Based Unit Predictions

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this