Multi-Agent Hybrid Deep Reinforcement Learning Approach for Resource Allocation in Multi-IRS-Assisted AAV-Aided V2X communication Neeraj Joshi, Ishan Budhiraja, Abhay Bansal IEEE Transactions on Consumer Electronics, 2026 !Vehicle-to-everything (V2X) communication has emerged as a key paradigm that has garnered proliferating interest by researchers providing seamless connectivity among vehicles, roadside infrastructures and aerial platforms. However, its dynamic nature, privacy and poor V2X channel quality can be a challenge in offloading tasks and resource optimization. This paper proposes a data-preserving, energy-efficient task offloading strategy in an aerial autonomous vehicle (AAV)-assisted V2X network by deploying multiple intelligent reflecting surfaces (IRSs) devices and by jointly optimizing the IRS reflection coefficient matrix, task vehicle offloading mode, and beamforming vector. It helps in minimizing the average offloading delay in an energy-efficient manner. The article proposes a feasible joint optimization algorithm based on twin-delayed multi-agent deep deterministic policy gradient with a federated learning framework (MAF-TD3), designing a practical partially observable Markov Decision Process (POMDP). Diverse, distributed agents, enabled by federated learning (FL), can collaborate to generate secure, energy-efficient global models without exchanging raw data, thereby protecting privacy and reducing communication overhead. Whereas the twin-delayed deep deterministic policy gradient (TD3) provides faster learning for continuous actions under partially observable dynamic scenarios. Unlike centralized TD3, MAF-TD3 enables scalable and privacy-preserving learning by aggregating only actor policies via federated coordination, while retaining local twin critics to ensure stability under partial observability in dense multi-IRS V2X networks. Numerical simulation results show a reduction in the latency by approximately 61.5%, 48.7%, and 28.5%, respectively, when compared to other MARL-based conventional DRL algorithms MAF-DDPG, MATD3 and MADDPG. It also minimizes the average energy consumption by 52%, 39.5%, and 28%, providing a performance boost in convergence, highlighting the importance of IRS and V2X task offloading in improving system performance.
Preface Signal Processing Roadmap Technologies Applications and Future Directions, 2026
Signal Processing Roadmap Signal Processing Roadmap Technologies Applications and Future Directions, 2026
Quantum-Driven Deep Reinforcement Learning for Energy-Efficient and Interference-Aware NOMA-Based D2D Groups Underlaying Cellular Networks in 6G Haneef Khan, Ishan Budhiraja, Atul Srivastava, Yogendra Chhetri, Suneet Kumar Gupta, Theyazn H.H. Aldhyani IEEE Transactions on Consumer Electronics, 2026 With the rapid proliferation of energy-constrained applications and ultra-dense user deployments in sixth-generation (6G) networks, improving energy efficiency (EE) has become a critical and challenging problem in uplink non-orthogonal multiple access (NOMA)-based device-to-device (D2D) communication underlaying cellular networks. The increasing D2D density, dynamic interference patterns, and heterogeneous service requirements demand intelligent, scalable, and decentralized resource management solutions. To address these challenges, this paper proposes a quantum-driven deep reinforcement learning (QDDRL) framework for joint subchannel (SC) and power allocation aimed at maximizing EE in D2D-enabled 6G systems. The resource allocation problem is formulated as a decentralized Markov decision process, where each D2D transmitter operates as an autonomous learning agent. By integrating quantum amplitude encoding (QAE) and variational quantum circuits (VQCs) within an actor–critic architecture, QDDRL efficiently handles high-dimensional state spaces, accelerates policy convergence, and improves learning stability under dynamic and interference-limited environments. Unlike conventional deep reinforcement learning and optimization-based approaches, QDDRL exploits quantum superposition and parallelism to evaluate multiple state–action combinations simultaneously, reducing exploration overhead and enhancing adaptability. Extensive simulation results demonstrate that QDDRL consistently outperforms existing baseline schemes, including hybrid quantum deep learning (HQDL), quantum reinforcement learning-based dynamic spectrum access (QRL-DS), quantum learning with relay and power selection (QL-RPS), and Quadratic Unconstrained Binary Optimization (QUBO)-based optimization. In particular, QDDRL achieves up to 7.1%, 11.1%, 25%, and 95% higher EE compared to HQDL, QRL-DS, QL-RPS, and QUBO, respectively in dense network scenarios, while also exhibiting faster convergence, lower reward variance, improved robustness to imperfect CSI and residual SIC errors, and reduced control overhead.
Artificial intelligence enhanced edge server placement for workload balancing and energy efficiency in B5G networks Vaibhav Tiwari, Chandrasen Pandey, Shamila J. Francis, Ishan Budhiraja, Pronaya Bhattacharya, Zhu Zhu, Thippa Reddy Gadekallu Digital Communications and Networks, 2025 The Internet of Things (IoT) and allied applications have made real-time responsiveness for massive devices over the Internet essential. Cloud-edge/fog ensembles handle such applications' computations. For Beyond 5th Generation (B5G) communication paradigms, Edge Servers (ESs) must be placed within Information Communication Technology infrastructures to meet Quality of Service requirements like response time and resource utilisation. Due to the large number of Base Stations (BSs) and ESs and the possibility of significant variations in placing the ESs within the IoTs geographical expanse for optimising multiple objectives, the Edge Server Placement Problem (ESPP) is NP-hard. Thus, stochastic evolutionary metaheuristics are natural. This work addresses the ESPP using a Particle Swarm Optimization that initialises particles as BS positions within the geography to maintain the workload while scanning through all feasible sets of BSs as an encoded sequence. The Workload-Threshold Aware Sequence Encoding (WTASE) Scheme for ESPP provides the number of ESs to be deployed, similar to existing methodologies and exact locations for their placements without the overhead of maintaining a prohibitively large distance matrix. Simulation tests using open-source datasets show that the suggested technique improves ESs utilisation rate, workload balance, and average energy consumption by 36%, 17%, and 32%, respectively, compared to prior works.
Metaverse for Connected World: Key Enablers, Challenges and Opportunities Deepanshi, Yash Motiani, Gaurav Singh, Ishan Budhiraja, Haneef Khan, Pronaya Bhattacharya, Kai Fang, Thippa Reddy Gadekallu Journal of Circuits Systems and Computers, 2025 Metaverse is the convergence of various technologies such as virtual reality (VR), augmented reality (AR) and artificial intelligence (AI), which allows users to engage in interactive experiences within a three-dimensional virtual environment. This convergence has been fueled by advances in internet technologies which facilitate highly interactive digital encounters across a wide range of applications. This survey provides an in-depth review of the present status of the metaverse, encompassing an analysis of its diverse technologies. We provide an in-depth study of the interdependence of connected technologies in the development of immersive digital realities. Our review encompasses many aspects, including graphical representation, user interaction and security and privacy protocols. We present an in-depth study of the metaverse’s diverse applications in entertainment, education, e-commerce and social interactions. These applications demonstrate the metaverse’s potential to fundamentally transform how we educate, socially interact with each other, or conduct business. The emergence and acceptance of the metaverse also give rise to significant challenges which include the digital divide, ethical considerations, legal frameworks, privacy and security, as well as the potential implications for mental and physical health. This survey will provide a comprehensive guide for researchers, policymakers and technologists as they navigate the transformative digital frontier of the evolving and expanding metaverse.
IoT and Blockchain Integration Challenges Haneef Khan, Ishan Budhiraja, Sarfaraz Ahmad Wahaj, Malik Zaib Alam, Shams Tabrez Siddiqui, Md Imran Alam Proceedings of 2022 IEEE International Conference on Current Development in Engineering and Technology Ccet 2022, 2022
Quantum Federated Reinforcement Learning-Based Resource Allocation Scheme for Digital Twin-Aided D2D Groups With NOMA in 6G Networks H Khan, I Budhiraja, A Srivastava Vehicular Communications, 101038 , 2026 2026
Quantum federated reinforcement learning-based energy efficiency optimization for IRS-assisted underlaying UAV communication H Khan, N Joshi, A Jabbari, H Zangoti, HT Alrakah, I Budhiraja VEHICULAR COMMUNICATIONS 58 , 2026 2026
Multi-Agent Hybrid Deep Reinforcement Learning Approach for Resource Allocation in Multi-IRS-Assisted AAV-Aided V2X communication N Joshi, I Budhiraja, A Bansal IEEE Transactions on Consumer Electronics , 2026 2026
Signal Processing Roadmap: Technologies, Applications, and Future Directions PK Dutta, P Raj, P Bhattacharya, I Budhiraja, D Kaplun Morgan Kaufmann , 2026 2026
Quantum-Driven Deep Reinforcement Learning for Energy-Efficient and Interference-Aware NOMA-Based D2D Groups Underlaying Cellular Networks in 6G H Khan, I Budhiraja, A Srivastava, Y Chhetri, SK Gupta, THH Aldhyani IEEE Transactions on Consumer Electronics , 2026 2026 Citations: 2
Quantum Federated Reinforcement Learning-Based Energy Efficiency Optimization for IRS-Assisted Underlaying UAV Communication N Joshi, A Jabbari, H Zangoti, HT Alrakah, I Budhiraja Vehicular Communications, 101003 , 2026 2026 Citations: 1
Optimization techniques in 6 G communication: from foundations to AI-driven solutions N Joshi, I Budhiraja, A Bansal Signal Processing Roadmap, 205-221 , 2026 2026
Quantum Deep Q Network Technique for Latency Minimization in STAR-RIS assisted VRCS S Chaudhary, I Budhiraja, R Chaudhary, N Kumar, I Woungang GLOBECOM 2025-2025 IEEE Global Communications Conference, 575-580 , 2025 2025
Enhancing Zero-Trust Architecture with Artificial Intelligence Techniques N Rastogi, I Budhiraja, S Ahmad Available at SSRN 5791722 , 2025 2025
PPO-Driven Dynamic Power Allocation for D2D Communication in NOMA H Khan, I Budhiraja, A Srivastava 2025 IEEE DELCON-International Conference on Recent Smart Technologies in … , 2025 2025
Metaverse for connected world: Key enablers, challenges and opportunities Deepanshi, Y Motiani, G Singh, I Budhiraja, H Khan, P Bhattacharya, ... Journal of Circuits, Systems and Computers 34 (15), 2530007 , 2025 2025 Citations: 5
An Opportunistic Energy Harvesting Scheme for Tactile NOMA-Based D2D Users Using Federated Learning A Barnawi, I Budhiraja, N Kumar, H Khan, H Zangoti IEEE Transactions on Consumer Electronics , 2025 2025 Citations: 2
Elevating Connectivity and Security in Wireless Sensor Networks deployment through Innovative Key Selection Strategy for Smart Cities R Priyadarshi, EA Mattar, S Chintham, H Khan, H Zangoti, MZ Alam, ... HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES 15 , 2025 2025
Energy and Latency Tradeoff for STAR-IRS assisted Vehicle Road Cooperative System in Carbon Intelligent IIoT Leveraging Quantized Federated Reinforcement Learning S Chaudhary, I Budhiraja, R Chaudhary IEEE Internet of Things Journal , 2025 2025 Citations: 6
Energy efficient resource allocation and trajectory optimization method for secure digital twin-enabled UAV-assisted MEC in 6G networks V Kumar, I Budhiraja, A Singh, S Garg, G Kaddoum, MM Hassan Computer Networks, 111679 , 2025 2025 Citations: 3
Artificial intelligence enhanced edge server placement for workload balancing and energy efficiency in B5G networks V Tiwari, C Pandey, SJ Francis, I Budhiraja, P Bhattacharya, Z Zhu, ... Digital Communications and Networks , 2025 2025 Citations: 2
Cross Layer Interference Management for STAR-RIS-Assisted VRCS Using GAI Augmented TinyFRL S Chaudhary, I Budhiraja, S Srivastava, H Khan, A Jabbari, S Duraibi, ... IEEE Transactions on Intelligent Transportation Systems , 2025 2025 Citations: 4
Asynchronous Federated Learning Technique for Latency Reduction in STAR-RIS enabled VRCS S Chaudhary, I Budhiraja, R Chaudhary, N Kumar, S Biswas ICC 2025-IEEE International Conference on Communications, 361-366 , 2025 2025 Citations: 5
Energy efficient task-offloading for DT-powered IRS-aided vehicular communication network underlaying UAV N Joshi, I Budhiraja, A Bansal, N Kumar, A Almuhaideb, B Unhelkar IEEE Transactions on Intelligent Transportation Systems , 2025 2025 Citations: 8
Efficient blockchain interoperability design for cross-chain transactions in future internet-of-value V Kumar, I Budhiraja, A Jabbari, D Garg, D Singh, N Mengani Peer-to-Peer Networking and Applications 18 (3), 110 , 2025 2025 Citations: 12
MOST CITED SCHOLAR PUBLICATIONS
A Systematic Review on NOMA Variants for 5G and Beyond I BUDHIRAJA, N KUMAR, S TYAGI, S TANWAR, ZHU HAN, MDJ PIRAN, ... 2021 Citations: 252
Tactile Internet for Smart Communities in 5G: An Insight for NOMA-Based Solutions I Budhiraja, S Tyagi, S Tanwar, N Kumar, JJPC Rodrigues IEEE Transactions on Industrial Informatics 15 (5), 3104-3112 , 2019 2019 Citations: 140
Metaverse for 6G and beyond: The next revolution and deployment challenges AM Aslam, R Chaudhary, A Bhardwaj, I Budhiraja, N Kumar, S Zeadally IEEE Internet of Things Magazine 6 (1), 32-39 , 2023 2023 Citations: 119
Tactile internet for autonomous vehicles: Latency and reliability analysis S Tanwar, S Tyagi, I Budhiraja, N Kumar IEEE Wireless Communications 26 (4), 66-72 , 2019 2019 Citations: 113
Deep Reinforcement Learning Based Proportional Fair Scheduling Control Scheme for Underlay D2D Communication I Budhiraja, N Kumar, S Tyagi IEEE Internet of Things Journal 8 (5), 3143-3156 , 2021 2021 Citations: 97
A hybrid task offloading and resource allocation approach for digital twin-empowered UAV-assisted MEC network using federated reinforcement learning for future wireless network P Consul, I Budhiraja, D Garg, N Kumar, R Singh, AS Almogren IEEE Transactions on Consumer Electronics 70 (1), 3120-3130 , 2024 2024 Citations: 94
A systematic analysis of enhancing cyber security using deep learning for cyber physical systems S Gaba, I Budhiraja, V Kumar, S Martha, J Khurmi, A Singh, KK Singh, ... IEEe Access 12, 6017-6035 , 2024 2024 Citations: 84
Energy consumption minimization scheme for NOMA-based mobile edge computation networks underlaying UAV I Budhiraja, N Kumar, S Tyagi, S Tanwar IEEE Systems Journal 15 (4), 5724-5733 , 2021 2021 Citations: 80
Cross Layer NOMA Interference Mitigation for Femtocell Users in 5G Environment I Budhiraja, S Tyagi, S Tanwar, N Kumar, M Guizani IEEE Transactions on Vehicular Technology 68 (5), 4721-4733 , 2019 2019 Citations: 77
Large-language-models (llm)-based ai chatbots: Architecture, in-depth analysis and their performance evaluation V Kumar, P Srivastava, A Dwivedi, I Budhiraja, D Ghosh, V Goyal, R Arora International Conference on Recent Trends in Image Processing and Pattern … , 2023 2023 Citations: 66
DIYA: Tactile Internet Driven Delay Assessment NOMA-based Scheme for D2D Communication I Budhiraja, S Tyagi, S Tanwar, N Kumar, JJPC Rodrigues IEEE Transactions on Industrial Informatics 15 (12), 6354-6366 , 2019 2019 Citations: 64
A federated calibration scheme for convolutional neural networks: Models, applications and challenges S Gaba, I Budhiraja, V Kumar, S Garg, G Kaddoum, MM Hassan Computer Communications 192, 144-162 , 2022 2022 Citations: 59
ETMA: Efficient Transformer Based Multilevel Attention framework for Multimodal Fake News Detection A Yadav, S Gaba, H Khan, I Budhiraja, A Singh, KK Singh IEEE Transactions on Computational Social Systems , 2022 2022 Citations: 57
SWIPT-Enabled D2D Communication Underlaying NOMA-Based Cellular Networks in Imperfect CSI I Budhiraja, N Kumar, S Tyagi, S Tanwar, M Guizani IEEE Transactions on Vehicular Technology 70 (1), pp. 692-699 , 2021 2021 Citations: 56
ISHU: Interference Reduction Scheme for D2D Mobile Groups Using Uplink NOMA I Budhiraja, N Kumar, S Tyagi IEEE Transactions on Mobile Computing 21 (9), 3208 - 3224 , 2021 2021 Citations: 52
A deep reinforcement learning scheme for sum rate and fairness maximization among D2D pairs underlaying cellular network with NOMA V Vishnoi, I Budhiraja, S Gupta, N Kumar IEEE Transactions on Vehicular Technology 72 (10), 13506-13522 , 2023 2023 Citations: 51
Cross Layer Interference Management Scheme for D2D Mobile Users Using NOMA I Budhiraja, N Kumar, S Tyagi IEEE Systems Journal 15 (2), 3109 - 3120 , 2020 2020 Citations: 49
A hybrid secure resource allocation and trajectory optimization approach for mobile edge computing using federated learning based on WEB 3.0 P Consul, I Budhiraja, D Garg IEEE Transactions on Consumer Electronics 70 (1), 1167-1179 , 2023 2023 Citations: 45
An Energy-Efficient Resource Allocation Scheme for SWIPT-NOMA Based Femtocells Users With Imperfect CSI I Budhiraja, N Kumar, S Tyagi, S Tanwar, M Guizani IEEE Transactions on Vehicular Technology 69 (7), 7790-7805 , 2020 2020 Citations: 44
CR-NOMA based Interference Mitigation Scheme for 5G Femtocells Users I Budhiraja, S Tyagi, S Tanwar, N Kumar, M Guizani 2018 IEEE Global Communications Conference (GLOBECOM), 1-6 , 2018 2018 Citations: 44
