Optimizing Power Consumption in Converged Networks with Novel Deep Learning

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 8

Year of Publication : 2025

Authors : Kompella Phani, K. Karuna Kumari

10.14445/23488549/IJECE-V12I8P110

How to Cite?

Kompella Phani, K. Karuna Kumari, "Optimizing Power Consumption in Converged Networks with Novel Deep Learning," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 8, pp. 111-122, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I8P110

Abstract:

In the present-day world, high-speed internet demand is increasing day by day. Optical Fiber communication, which can cater to high bandwidth requirements, has a bottleneck for extending till the last mile for mobile User Equipment (UE). Converged networks, which use the combined advantage of Optical Fiber for the backbone network and wireless communication through Passive Optical Networks (PON) for the last mile, are the area of focus in this research paper. For effective utilization of available backbone bandwidth, it is essential to use Dynamic Bandwidth Allocation (DBA) techniques by the Optical Line Terminal (OLT) to allocate bandwidth to Optical Network Units (ONUs) to meet the requirements of UE devices. The growing density of UE devices demands power-saving techniques at the access network level. Significant research literature is available on the use of machine learning techniques for DBA in PON, but integration of spatial and temporal learning mechanisms is not widely explored for reducing power consumption in PON. A Hybrid dynamic bandwidth allocation technique is proposed in this work, which uses the temporal recognition capability of the Long Short-Term Memory (LSTM) algorithm and the spatial recognition capability of the Deep Q Network (DQN) Algorithm. The proposed hybrid model requires a considerably large dataset for training, which is achieved using the Generative Adversarial Network (GAN) method. The results of the proposed hybrid model are compared with the standalone Deep Q Network model, and it is verified that there is an 11% reduction in buffer occupancy at ONUs and a 20 % reduction in the Power consumption of the overall system.

Keywords:

Converged networks, Dynamic bandwidth allocation, Deep Q Learning, Generative Adversarial Networks, Long Short-Term Memory.

References:

[1] S.H. Shah Newaz et al., “Energy Conservation in Passive Optical Networks: A Tutorial and Survey,” IEEE Communications Surveys & Tutorials, vol. 27, no. 1, pp. 667-724, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Manjur Kolhar, Fadi Al-Turjman, and Abdalla Alameen, “Unified Dynamic Bandwidth Allocation Scheme for Ethernet Passive Optical Network,” IEEE Access, vol. 8, pp. 216176-216184, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Jun Shan Wey, “The Outlook for PON Standardization: A Tutorial,” Journal of Lightwave Technology, vol. 38, no. 1, pp. 31-42, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Pengcheng Li, Yunxin Lv, and Meihua Bi, “Bandwidth Prediction Based Resource Allocation Scheme for Low-Latency and Energy-Efficient PONs with Heterogeneous ONU Propagation Delays,” IEEE Photonics Journal, vol. 16, no. 1, pp. 1-15, 2024. [CrossRef] [Google Scholar] [Publisher Link]
[5] Yapeng Xie et al., “Machine Learning Applications for Short Reach Optical Communication,” Photonics, vol. 9, no. 1, pp. 30-68, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Ganesh C. Sankaran, and Krishna M. Sivalingam, “ONU Buffer Reduction for Power Efficiency in Passive Optical Networks,” Optical Switching and Networking, vol. 10, no. 4, pp. 416-429, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Sandra Arnaout et al., “Dynamic Resource Allocation for Converged Optical and Radio Architecture in 6G Networks,” 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), Madrid, Spain, pp. 329-334, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Shiwen Song et al., “A Bandwidth Allocation Scheme based on GRU Traffic Prediction in Passive Optical Networks,” Optics Communications, vol. 574, pp. 1-8, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Lihua Ruan, Elaine Wong, and Hongyi Zhu, “Reinforcement Learning-based Bandwidth Decision in Optical Access Networks: A Study of Exploration Strategy and Time with Confidence Guarantee,” IEEE Transactions on Communications, vol. 72, no. 11, pp. 6943-6955, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Alaelddin F.Y. Mohammed, Joohyung Lee, and Sangdon Park, “Dynamic Bandwidth Slicing in Passive Optical Networks to Empower Federated Learning,” Sensors, vol. 24, no. 15, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Garima, Vivekanand Jha, and Rakesh Kumar Singh, “Comprehensive Performance Analysis of Dynamic Bandwidth Allocation Schemes for XG-PON System,” Optical Switching and Networking, vol. 47, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Priyanka Singh et al., “QoS-Aware Reliable Architecture for Broadband Fiber-Wireless Access Networks,” IEEE Systems Journal, vol. 16, no. 4, pp. 5753-5764, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Huayu Zhu et al., “A Deep-Reinforcement-Learning-Based Optimization Approach for Real-Time Scheduling in Cloud Manufacturing,” IEEE Access, vol. 8, pp. 9987-9997, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] A. Shami et al., “Jitter Performance in Ethernet Passive Optical Networks,” Journal of Lightwave Technology, vol. 23, no. 4, pp. 1745-1753, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Razat Kharga et al., “Energy Savings in 25G-NGEPON for Spatial Computing Multimedia Services based on Vanilla-RNN,” Optical Fiber Technology, vol. 87, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Fares Fourati, and Mohamed-Slim Alouini, “Artificial Intelligence for Satellite Communication: A Review,” Intelligent and Converged Networks, vol. 2, no. 3, pp. 213-243, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Zhiyong Du et al., “Context-Aware Indoor VLC/RF Heterogeneous Network Selection: Reinforcement Learning with Knowledge Transfer,” IEEE Access, vol. 6, pp. 33275-33284, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] G.M. Shafiqur Rahman, Tian Dang, and Manzoor Ahmed, “Deep Reinforcement Learning based Computation Offloading and Resource Allocation for Low-Latency fog Radio Access Networks,” Intelligent and Converged Networks, vol. 1, no. 3, pp. 243-257, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Gyungmin Kim, Yohan Kim, and Hyuk Lim, “Deep Reinforcement Learning-Based Routing on Software-Defined Networks,” IEEE Access, vol. 10, pp. 18121-18133, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Federico Celi, Giacomo Baggio, and Fabio Pasqualetti, “Distributed Data-Driven Control of Network Systems,” IEEE Open Journal of Control Systems, vol. 2, pp. 93-107, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Claudio Savaglio et al., “Lightweight Reinforcement Learning for Energy Efficient Communications in Wireless Sensor Networks,” IEEE Access, vol. 7, pp. 29355-29364, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Mostafa Zaman Chowdhury et al., “Optical Wireless Hybrid Networks: Trends, Opportunities, Challenges, and Research Directions,” IEEE Communications Surveys and Tutorials, vol. 22, no. 2, pp. 930-966, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Xiang Liu et al., “Nonlinearity Mitigation in a Fiber-Wireless Integrated System based on Low-Complexity Autoencoder and BiLSTM-ANN Equalizer,” Optics Express, vol. 31, no. 12, pp. 20005-20018, 2023.
[CrossRef] [Google Scholar] [Publisher Link]