Suvidha Mhatre

Suvidha Mhatre

Auto-generated profile, based on publicly available information

Suvidha Mhatre

Universitat Politècnica de Catalunya Barcelona Spain

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Open access
SMSuvidha Mhatre
Suvidha Mhatre
FAFerran Adelantado
Ferran Adelantado
KRKostas Ramantas
Kostas Ramantas
CVChristos Verikoukis
Christos Verikoukis
The escalating demands of next-generation, beyond5G services necessitate innovative approaches to dynamic resource management, critical for satisfying end-user expectations and maintaining quality of service (QoS). This study leverages the Open Radio Access Network (O-RAN) architecture's flexibility and programmability to introduce a novel deep reinforcement learning (DRL) strategy for QoS-aware intraslice resource allocation. By employing intelligent agents and a Deep Q-Network (DQN)-based framework, our approach precisely tailors resource distribution within O-RAN, optimizing for enhanced mobile broadband (eMBB) and ultra-reliable lowlatency communications (URLLC) slices. The proposed method, featuring intelligent QoS-aware resource allocation (IQRA) and its low-complexity variant (LIQRA), demonstrates significant throughput improvements for eMBB by 11.5% compared to state-of-the-art (SOTA) methods and reduces URLLC latency by 19.94% and 16.54%, achieving up to 45.5% lower latency than baseline. A streamlined algorithm effectively reduces computational complexity, ensuring robust performance under resource constraints. Simulation results underscore the algorithm's ability to substantially enhance 5G network slice performance, offering a parameterized solution for user association in O-RAN networks using DRL. This research not only meets high key performance indicators (KPIs) but also advances edge intelligence, fostering a more responsive network ecosystem.

20 March 2025 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Open access
SMSuvidha Mhatre
Suvidha Mhatre
FAFerran Adelantado
Ferran Adelantado
KRKostas Ramantas
Kostas Ramantas
CVChristos Verikoukis
Christos Verikoukis
Leveraging the power of deep reinforcement learning (DRL) and strategic knowledge transfer, our study introduces PIRA-DRL-DTRL, a novel approach to optimizing resource allocation in emerging 6G networks. Central to this research is the innovative application of artificial intelligence (AI) at the network’s edge, enabling efficient management of resources across diverse timeframes while enhancing overall network performance. Implemented within an Open Radio Access Network (O-RAN) architecture, PIRA-DRL-DTRL employs a two-tiered decision-making system to dynamically adapt to varying network demands, ensuring optimal resource allocation for enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC). Our proposed algorithm achieves significant performance gains, providing a 14.28% and 10.67% improvement in throughput for eMBB slices compared to DRL-only and state-of-the-art (SOTA) methods, respectively. Additionally, it reduces delay by 23.57% and 7.48% compared to baseline and SOTA approaches for eMBB slices. By predicting and adapting to network slice demands, PIRA-DRL-DTRL ensures seamless service delivery. This research lays the groundwork for smarter, more efficient 6G networks capable of meeting the dynamic needs of users and applications.

17 January 2025 in arXiv
Verified
Preprint
Open access
PDF file
SMSuvidha Mhatre
Suvidha Mhatre
FAFerran Adelantado
Ferran Adelantado
KRKostas Ramantas
Kostas Ramantas
CVChristos Verikoukis
Christos Verikoukis
This research introduces an advanced Explainable Artificial Intelligence (XAI) framework designed to elucidate the decision-making processes of Deep Reinforcement Learning (DRL) agents in ORAN architectures. By offering network-oriented explanations, the proposed scheme addresses the critical challenge of understanding and optimizing the control actions of DRL agents for resource management and allocation. Traditional methods, both model-agnostic and model-specific approaches, fail to address the unique challenges presented by XAI in the dynamic and complex environment of RAN slicing. This paper transcends these limitations by incorporating intent-based action steering, allowing for precise embedding and configuration across various operational timescales. This is particularly evident in its integration with xAPP and rAPP sitting at near-real-time and non-real-time RIC, respectively, enhancing the system's adaptability and performance. Our findings demonstrate the framework's significant impact on improving Key Performance Indicator (KPI)-based rewards, facilitated by the ability to make informed multimodal decisions involving multiple control parameters by a DRL agent. Thus, our work marks a significant step forward in the practical application and effectiveness of XAI in optimizing ORAN resource management strategies.