Energy Prediction and Task Optimization for Efficient IoT Task Offloading and Management
Keywords:
Energy Prediction, IoT Task Offloading, Edge Computing, Adaptive Offloading, Energy EfficiencyAbstract
This research addresses energy-aware task offloading within the Internet of Things (IoT) networks. In today’s interconnected world, IoT devices play an increasingly pivotal role. However, they often face limitations regarding energy consumption, which hinders their prolonged operation and effectiveness. Existing IoT task offloading strategies focus on isolated aspects of energy optimization, overlooking the holistic nature of energy management. This leads to suboptimal utilization of device resources, reduced device lifespans, and potential performance bottlenecks. This proposes the Energy Prediction and Task Optimization (EPTO) algorithm; we leverage multi-dimensional profiling, real-time monitoring, and adaptive decision-making. EPTO consistently outperforms traditional strategies, enhancing energy efficiency, device lifespan and quality of service. EPTO combines innovative methods, including LSTM-based energy prediction, adaptive offloading policies, and dynamic resource allocation. It employs a comprehensive mathematical modeling approach that integrates data from diverse sources, offering unparalleled adaptability in dynamic IoT environments.in this paper we employed a diverse dataset comprising various IoT devices, each characterized by battery levels, computation intensity, data transmission energy, historical energy consumption patterns, and task characteristics. This dataset enabled realistic simulations and robust performance evaluations. Our proposed work evaluated with the following performance metrics, including Energy Efficiency Ratio (EER), Task Completion Time (TCT), Battery Lifetime Extension (BLE), Resource Utilization (RU), and Rate of Offloaded Tasks (ROB). Our quantitative results demonstrate substantial improvements in energy efficiency, with EER values exceeding 0.85. Task Completion Time is notably reduced, with TCT averaging 65 seconds, while BLE metrics show significant device lifespan extensions of up to 30%. EPTO's adaptability suits various IoT domains like smart cities, healthcare, and industrial automation. Its responsive resource management supports diverse IoT scenarios. EPTO addresses IoT sustainability and optimization, shaping greener and more efficient ecosystems. It revolutionizes energy management, paving the way for smarter IoT networks.
Downloads
References
E. Samikwa, A. Di Maio, and T. Braun, “Adaptive early exit of computation for energy-efficient and low-latency machine learning over IoT networks,” in 2022 IEEE 19th Annual Consumer Communications & Networking Conference (CCNC), 2022.
V. Rishiwal, P. Yadav, O. Singh, and B. G. Prasad, “Optimizing energy consumption in IoT-based scalable Wireless Sensor Networks,” Int. J. Syst. Dyn. Appl., vol. 10, no. 4, pp. 1–20, 2021.
Kaipa Chandana Sree, G, P., & Nikitha Rao , N. R. (2023). Optimizing Resource Allocation in MECC for AI and DL Applications in Healthcare with Task Offloading. International Journal of Computer Engineering in Research Trends, 10(5), 17–25.
Allal, B. Mongazon-Cazavet, K. Al Agha, S.-M. Senouci, and Y. Gourhant, “A green small cells deployment in 5G — Switch ON/OFF via IoT networks & energy efficient mesh backhauling,” in 2017 IFIP Networking Conference (IFIP Networking) and Workshops, 2017.
Z. Zlatev, T. Georgieva, A. Todorov, and V. Stoykova, “Energy efficiency of IoT networks for environmental parameters of Bulgarian cities,” Computers, vol. 11, no. 5, p. 81, 2022.
Zappone, M. Di Renzo, and R. K. Fotock, “Surface-based techniques for IoT networks: Opportunities and challenges,” IEEE Internet Things M., vol. 5, no. 4, pp. 72–77, 2022.
Sheikh, S. Kumar, and A. Ambhaikar, “To study variation of energy consumption in iot networks,” 2020.
Homssi, A. Al-Hourani, S. Chandrasekharan, K. M. Gomez, and S. Kandeepan, “On the bound of energy consumption in cellular IoT networks,” arXiv [cs.IT], 2021.
G, P., T, S., & S, R. (2023). Deep Learning Approaches for Ensuring Secure Task Scheduling in IoT Systems. International Journal of Computer Engineering in Research Trends, 8(5), 102–110.
N. Jinaporn and P. Saengudomlert, “Impact of gateway placement and energy consumption for data processing on lifetime of IoT networks,” in 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2021.
H.-T. Ye, X. Kang, J. Joung, and Y.-C. Liang, “Optimization for wireless-powered IoT networks enabled by an energy-limited UAV under practical energy consumption model,” IEEE Wirel. Commun. Lett., vol. 10, no. 3, pp. 567–571, 2021.
M. Ateeq, F. Ishmanov, M. Afzal, and M. Naeem, “Multi-parametric analysis of reliability and Energy Consumption in IoT: A deep learning approach,” Sensors (Basel), vol. 19, no. 2, p. 309, 2019.
J. Karjee, S. Praveen Naik, and N. Srinidhi, “Energy profiling based load-balancing approach in IoT-edge for split computing,” in 2021 IEEE 18th India Council International Conference (INDICON), 2021.
Sabovic, A. K. Sultania, C. Delgado, L. D. Roeck, and J. Famaey, “An energy-aware task scheduler for energy-harvesting batteryless IoT devices,” IEEE Internet Things J., vol. 9, no. 22, pp. 23097–23114, 2022.
H. Hu, D. Wu, F. Zhou, S. Jin, and R. Q. Hu, “Dynamic task offloading in MEC-enabled IoT networks: A hybrid DDPG-D3QN approach,” in 2021 IEEE Global Communications Conference (GLOBECOM), 2021.
M. Chen, Y. Hao, and Y. Li, “Computation Offloading for IoT Devices: A Survey,” IEEE Internet of Things Journal, vol. 5, no. 2, pp. 758–769, 2018.
Bezawada , M., & P, V. K. (2023). Comparative Study on Techniques Used for Anomaly Detection in IoT Data. International Journal of Computer Engineering in Research Trends, 10(4), 177–181.
Y. Sun, Y. Zhang, K. B. Letaief, and R. Q. Hu, “A Survey of Edge Computing: From Vision to Implementation,” IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, 2016.
X. Zhang, H. Zhang, X. Zhou, and D. Yuan, “Energy minimization task offloading mechanism with edge-cloud collaboration in IoT networks,” in 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 2021.
G, P., Dunna, N. R., & Kaipa , C. S. (2023). Enhancing Cloud-Based IoT Security: Integrating AI and Cyber security Measures. International Journal of Computer Engineering in Research Trends, 10(5), 26–32.
Pasha, M. J., Pingili, M., Sreenivasulu, K., Bhavsingh, M., Saheb, S. I., & Saleh, A. (2022). Bug2 algorithm-based data fusion using mobile element for IoT-enabled wireless sensor networks. Measurement: Sensors, 24, 100548.
Prakash, P. S., Janardhan, M., Sreenivasulu, K., Saheb, S. I., Neeha, S., & Bhavsingh, M. (2022). Mixed Linear Programming for Charging Vehicle Scheduling in Large-Scale Rechargeable WSNs. Journal of Sensors, 2022.
Makarand L, M. . (2021). Earlier Detection of Gastric Cancer Using Augmented Deep Learning Techniques in Big Data with Medical Iot (Miot). Research Journal of Computer Systems and Engineering, 2(2), 22:26. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/28
Kumavat, K. S. ., & Gomes, J. . (2023). Common Mechanism for Detecting Multiple DDoS Attacks. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4), 81–90. https://doi.org/10.17762/ijritcc.v11i4.6390
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.