AI and Coalition Game Interplay for Efficient Resource Allocation in D2D Communication

• Published in: GLOBECOM 2023 - 2023 IEEE Global Communications Conference pp. 3058 - 3063
• Main Authors: Rathod, Tejal, Gupta, Rajesh, Nehra, Anushka, Kumar Jadav, Nilesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.12.2023
• Subjects: Artificial intelligence; Coalition game; D2D communication; Device-to-device communication; Games; Gaussian processes; Resource allocation; Resource management; Spectral efficiency; Support vector machines; Wireless networks
• ISSN: 2576-6813
• DOI: 10.1109/GLOBECOM54140.2023.10437084

Fifth-generation (5G) offers more advanced and promising wireless communication technology as Device-to-device (D2D) communication. It refers to the direct data exchange between two users' equipment in a wireless network without routing their data through the base station. The close proximity of the devices offers a higher data rate with low communication latency and increases spectral efficiency. Despite the advantages mentioned above, there are still some challenges, such as interference, power control, and security, that need to be addressed concerning D2D communication. There exist many game theory-based solutions for efficient resource allocation. However, they face issues when there are many users in the communication environment. Hence, we proposed artificial intelligence (AI) and game theory-based solutions for efficient resource allocation in this paper. Initially, we proposed different machine learning (ML) classifiers, such as isolation forest (IF), support vector machine (SVM), gradient boosting (GB) classifier, K-nearest neighbours (KNN), and Gaussian naive Bayes (GNB) that select best D2D users. Then, we formulate a coalition game that gives efficiently allocates resources to the best-selected D2D users. Further, we considered different performance evaluation parameters, such as accuracy, validation loss, sum rate, and convergence rate. The empirical results represent that the GB classifier achieves the highest accuracy, 98.23%, because it trains faster with the large dataset size, and the coalition game-based approach maximizes the overall system sum rate for efficient resource allocation in D2D communication.