ItemBook Chapter

A novel approach to optimize power utilization and scheduling in dynamic networks through generative adversarial network-based prediction of network parameters

Title
A novel approach to optimize power utilization and scheduling in dynamic networks through generative adversarial network-based prediction of network parameters
Creator
Suhaas, K.P.; Senthil, S.; Deepa, B.G.
Description
The infrastructure-less network communication has been in an ever-increasing demand to cater to the needs of effective communication while the network dynamism exists. The quality of service (QoS)quality of service (QoS) demands increasing the efficiency of network by reducing the time taken for a data packet to reach the destination, increasing the probability of successful data transmissiondata transmission, minimizing packet loss,packet loss and optimizing power utilizationpower utilization. In this study, a generative adversarial network-based learning modelgenerative adversarial network-based learning model has been developed that considers the previous network statistics, as realized data, to predict future network patterns by the generatorgenerator to make such predictions, called as unrealized data, as near to the realized data. Further, the proposed model uses penalty-award criteria by the discriminatordiscriminator, to fine-tune the predicted network parameters. Now, having the set of realized and unrealized data, the model uses Markov decision processMarkov decision process to perform power scheduling and effective utilization of buffer space. The buffer utilization in the intermediate nodes necessitates the model to stochastically schedule the data transmission, depending on the percentage of utilization of buffer. Simulation results denote the effective utilization of buffer that makes continued transmission of data, whenever possible, without having data packet lossdata packet loss. Also, power scheduling, by the use of goodput function and increased transmission probability improves the power utilization that ultimately increases the lifetime of the network. 2026 Walter de Gruyter GmbH, Berlin/Boston, Genthiner Stra 13, 10785 Berlin.
Source
Quantum Computing;Volume;5;pp.103-122
Date
01-01-2026
Publisher
Walter de Gruyter GmbH
Subject
Ad hoc networks; buffer overflow; channel fading coefficient; generative adversarial networks; Goodput; Markov decision process; network parameters; power scheduling; quality of service; reinforcement learning; resource optimization; transition probability
Coverage
Suhaas K.P., Department of Information Science and Engineering, The National Institute of Engineering, Mysuru, India; Senthil S., Department of Computer Applications, Dayanand Sagar University, Bengaluru, India; Deepa B.G., Department of Computer Science, Christ University, Bengaluru, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 29400112;
Format
online
Language
English
Type
Book chapter

Citation

Suhaas, K.P.; Senthil, S.; Deepa, B.G., “A novel approach to optimize power utilization and scheduling in dynamic networks through generative adversarial network-based prediction of network parameters,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/24485.

Output Formats