Aryan Kaushik’s research while affiliated with Manchester Metropolitan University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (104)


Performance of RIS-Aided Fluid Antenna-Enabled Multiuser NOMA Non-terrestrial Networks
  • Preprint

March 2025

·

3 Reads

·

·

Aryan Kaushik

·

Chih-Peng Li








RIS-Assisted Aerial Non-Terrestrial Networks: An Intelligent Synergy with Deep Reinforcement Learning

December 2024

·

13 Reads

Reconfigurable intelligent surface (RIS)-assisted aerial non-terrestrial networks (NTNs) offer a promising paradigm for enhancing wireless communications in the era of 6G and beyond. By integrating RIS with aerial platforms such as unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs), these networks can intelligently control signal propagation, extending coverage, improving capacity, and enhancing link reliability. This article explores the application of deep reinforcement learning (DRL) as a powerful tool for optimizing RIS-assisted aerial NTNs. We focus on hybrid proximal policy optimization (H-PPO), a robust DRL algorithm well-suited for handling the complex, hybrid action spaces inherent in these networks. Through a case study of an aerial RIS (ARIS)-aided coordinated multi-point non-orthogonal multiple access (CoMP-NOMA) network, we demonstrate how H-PPO can effectively optimize the system and maximize the sum rate while adhering to system constraints. Finally, we discuss key challenges and promising research directions for DRL-powered RIS-assisted aerial NTNs, highlighting their potential to transform next-generation wireless networks.


RIS-Assisted Aerial Non-Terrestrial Networks: An Intelligent Synergy with Deep Reinforcement Learning
  • Article
  • Full-text available

December 2024

·

351 Reads

·

2 Citations

IEEE Vehicular Technology Magazine

Reconfigurable intelligent surface (RIS)-assisted aerial non-terrestrial networks (NTNs) offer a promising paradigm for enhancing wireless communications in the era of 6G and beyond. By integrating RIS with aerial platforms such as unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs), these networks can intelligently control signal propa- gation, extending coverage, improving capacity, and enhancing link reliability. This article explores the application of deep reinforcement learning (DRL) as a powerful tool for optimizing RIS-assisted aerial NTNs. We focus on hybrid proximal policy optimization (H-PPO), a robust DRL algorithm well-suited for handling the complex, hybrid action spaces inherent in these networks. Through a case study of an aerial RIS (ARIS)-aided coordinated multi-point non-orthogonal multiple access (CoMP- NOMA) network, we demonstrate how H-PPO can effectively optimize the system and maximize the sum rate while adhering to system constraints. Finally, we discuss key challenges and promising research directions for DRL-powered RIS-assisted aerial NTNs, highlighting their potential to transform next- generation wireless networks.

Download

Citations (48)


... Recently, reconfigurable holographic surfaces (RHS) have emerged as a groundbreaking paradigm in wireless communications, offering unprecedented capabilities to enhance the performance and security of wireless systems [18], [19]. An RHS is an array of programmable elements that can dynamically manipulate electromagnetic waves, enabling fine-grained control over the wireless propagation environment [20]. ...

Reference:

Secrecy Rate Maximization for 6G Reconfigurable Holographic Surfaces Assisted Systems
Multi-Function Reconfigurable Intelligent and Holographic Surfaces for 6G Networks
  • Citing Article
  • January 2025

IEEE Network

... They demonstrate remarkable generalization abilities, capturing complex relationships within data and large-scale neural network (NN) architectures with millions of parameters, enabling their application in every field. Large language models (LLMs), when well suited for dynamic environments, have the potential to revolutionize decision-making, resource management, and intelligent real-time optimizations for wireless networks [1]. ...

RIS-Assisted Aerial Non-Terrestrial Networks: An Intelligent Synergy with Deep Reinforcement Learning

IEEE Vehicular Technology Magazine

... These systems adjust their beam patterns to optimize signal quality and coverage, actively adapting to changes in traffic patterns and signal conditions. This dynamic adjustment is achieved through techniques such as beamforming, which focuses the antenna array's power on specific directions to enhance signal strength and reduce interference from other directions (Al-Hilo et al., 2022;Katwe et al., 2024). ...

An Overview of Intelligent Meta-Surfaces for 6G and Beyond: Opportunities, Trends, and Challenges
  • Citing Article
  • October 2024

IEEE Communications Standards Magazine

... By using the union-bound expression provided in (22) along with the PEP expressions in (28a), (28b), and (28c), a closedform upper-bound on the SEP performance for the unblocked direct channel case is obtained as shown in (29). In this expression, Γ m denotes the SNR for each m-th symbol and is defined considering σ hd = σ 2 h , as ...

Performance Analysis of Receive Diversity RIS and RPM Assisted Index Modulated Communication System
  • Citing Conference Paper
  • June 2024

... In such scenarios, NTN play a crucial role in increasing the capacity, coverage, and speed of Fully integrated NTN are poised to provide ubiquitous connectivity, delivering services anywhere, anytime, thus having a profound socioeconomic impact [28]. ...

Rate-Splitting Multiple Access for GEO-LEO Coexisting Satellite Systems: A Traffic-Aware Throughput Maximization Precoder Design

IEEE Transactions on Vehicular Technology

... Artificial Intelligence (AI) has been identified as a key 6G technological enabler to adapt the network to a fast-changing environment [29]- [34]. Similarly to human-brain functioning, data-assisted AI models can learn from previous experience and execute the same action when faced with a similar perceptual environment, reducing complexity and computational resources with respect to a pure optimization-based decision-making [35]- [37]. ...

Quantum-Enhanced DRL Optimization for DoA Estimation and Task Offloading in ISAC Systems

IEEE Journal on Selected Areas in Communications

... Under the scenario wherein IoT devices occupy state s t and undertake action a t , the resulting immediate reward r t is meticulously designed as follows: Figure 3 illustrates the developed framework for task offloading and scheduling. The algorithm of DQN, introduced by the DeepMind group, is a reinforcement learning algorithm integrating deep learning principles widely used in current complex satellite networks design [19,30,[52][53][54]. Unlike traditional Q-learning, DQN is adept at managing complex state spaces characterized by high dimensionality. ...

Collaborative Task Offloading Optimization for Satellite Mobile Edge Computing Using Multi-Agent Deep Reinforcement Learning
  • Citing Article
  • October 2024

IEEE Transactions on Vehicular Technology

... Therefore, exploring the real-world scenario where Eve is mobile requires further investigation [92]. Additionally, when covering NLOS region, the RIS can be integrated with NOMA to implement a spectrally efficient and secure network which is robust enough to operate despite variation in CSI [197]. ...

Secrecy Rate Maximization for Active RIS-aided Robust Uplink NOMA Communications
  • Citing Article
  • July 2024

IEEE Wireless Communications Letters

... • MA [3]: The transceiver panels are non-rotatable, while the antenna elements can be repositioned on the antenna panels based on the joint optimization. • RO [12]: The relative positions of the antenna elements on the panel are fixed with the antenna spacing of λ/2, while the entire panel can rotate around its center axis. • AS [13]: The transceivers are equipped with 12 antennas, arranged in a fixed square array with an antenna spacing of λ/2. ...

Spatial Multiplexing in Near-Field Line-of-Sight MIMO Communications: Paraxial and Non-Paraxial Deployments
  • Citing Article
  • January 2024

IEEE Transactions on Green Communications and Networking

... UAV-based ISAC systems represent a promising implementation, leveraging UAVs' unique capabilities to enhance integrated S&C [8]. They enable simultaneous S&C by sharing resources like spectrum and hardware, overcoming traditional ground-based limitations [11]. Unlike fixed infrastructure, UAVs can dynamically navigate three-dimensional (3D) space, enabling them to circumvent obstacles that hinder line-of-sight (LoS) links [12]. ...

Integrated Sensing and Communications for IoT: Synergies with Key 6G Technology Enablers
  • Citing Article
  • September 2024

IEEE Internet of Things Magazine