Skip to main content
School of Electronic Engineering and Computer Science
  1. School of Electronic Engineering and Computer Science
  2. PhD
  3. PhD studentships
  4. AI-Native Cross-Layer Resource Allocation for Intelligent 6G Networks

AI-Native Cross-Layer Resource Allocation for Intelligent 6G Networks

Supervisor: Dr Antonino Masaracchia

Project Description

Over the past decades, we have witnessed a rapid proliferation of smart devices, edge intelligence, and data-intensive services. These trends are pushing mobile data traffic to unprecedented levels. It is anticipated that by 2030, mobile wireless networks will need to support traffic volumes of approximately 500 exabytes per month, representing a growth factor of around 2.4 compared to current levels. Simultaneously, emerging applications such as autonomous driving, Industrial Internet of Things (IIoT), extended reality (XR), and mission-critical communications demand sub-millisecond latency, ultra-reliable transmission with error rates below 10⁻⁹, high spectrum and energy efficiency, and ubiquitous connectivity. These increasingly stringent requirements place significant pressure on mobile network operators, who must continuously evolve their infrastructure to meet diverse and dynamic Quality of Service (QoS) and Quality of Experience (QoE) targets. To address these challenges, next-generation (6G) networks are expected to incorporate transformative technologies, including:

  • The usage of Terahertz (THz) frequency;
  • Unmanned Aerial Vehicles (UAVs) as aerial base stations;
  • Non-terrestrial networks (NTN) leveraging satellites;
  • Reconfigurable Intelligent Surfaces (RIS) to manipulate radio waves to optimize wireless communication.

While these technologies offer unprecedented opportunities, they also create highly complex and dynamic communication environments in which current resource allocation policies for the Radio Access Network (RAN) may no longer be sufficient to satisfy stringent Key Performance Indicators (KPIs) across heterogeneous services. Although Artificial Intelligence (AI), particularly deep reinforcement learning (DRL), is widely recognized as a cornerstone for closed-loop RAN optimization in future architectures, most existing solutions remain largely reactive, confined to single-layer optimisation, and lack the scalability, robustness, and cross-layer coordination required for real-world 6G deployments. More specifically, they focus predominantly on physical (PHY) layer tasks, often neglecting critical cross-layer interactions with the Medium Access Control (MAC) and Radio Link Control (RLC) layers of the network.

Research Objectives

The project will investigate how hierarchical, multi-agent DRL (HMARL) can transform RAN resource allocation from reactive optimisation to predictive cross-layer intelligence embedded directly into the RAN control loop. The successful candidate will develop novel AI-driven frameworks capable of learning, adapting, and optimising network behaviour in highly dynamic environments.

Research directions may include, but are not limited to:

  • Hierarchical Multi-Agent DRL Architectures: Design and evaluate HMARL frameworks where agents operate at different layers (PHY, MAC, RLC) and network segments, enabling cross-layer cooperation for predictive resource allocation and interference management.
  • AI-Driven Radio Resource Management (RRM): Investigate DRL-based solutions for joint optimization of RAN configurations, considering trade-offs between throughput, latency, energy efficiency, and reliability.
  • Data-Centric AI for Wireless Network Optimization: Develop methodologies that improve the quality, representativeness, and robustness of training data used in AI-driven RAN control. This may include intelligent data collection strategies, handling non-stationarity and distribution shifts, synthetic data generation for rare network events, cross-layer dataset design (PHY–MAC–RLC), and continual learning mechanisms to enhance the stability, generalisation, and deployment of DRL-based resource allocation policies.
  • Predictive Traffic and Mobility Modelling: Develop AI models that anticipate network load, user mobility patterns, and service demand, integrating these predictions into proactive RAN scheduling, handover management, and dynamic spectrum allocation.

Your research direction will be shaped by the intersection of your interests and expertise, which you will refine into a detailed proposal during the early months of the PhD. We welcome candidates with backgrounds in Computer Science, Electrical or Electronic Engineering, Telecommunications, or Artificial Intelligence. Strong programming skills (e.g., Python, PyTorch/TensorFlow), experience with machine learning ─ particularly reinforcement learning ─ networking protocols for wireless communication systems are highly desirable. A demonstrated interest in research (e.g., MSc thesis, publications, or relevant projects), as well as familiarity with simulation tools like NS3 and SIONNA and/or data engineering for AI applications will be an advantage.

Expected Outcomes:

  • Novel HMARL-based algorithms for cross-layer RAN optimization.
  • Predictive resource allocation models for ultra-reliable low-latency communications (URLLC) and high-capacity services.
  • Data-centric AI methodologies for wireless network optimization, including curated cross-layer datasets, robust training pipelines for DRL, and continual learning mechanisms to handle non-stationarity and distribution shifts in dynamic network environments.
  • Publications in leading journals and conferences in wireless communications and AI for networking.
  • Open-source simulation frameworks or toolkits to facilitate further research in 6G network intelligence.

This PhD provides the opportunity to pioneer AI-native RAN architectures, integrating hierarchical reinforcement learning and data-centric intelligence to enable truly autonomous and predictive 6G networks. If you are passionate about pushing the boundaries of artificial intelligence and shaping the technological foundations of 6G, this project offers a unique platform to make a lasting research impact.

Tuition fees and stipend

The PhD student will receive tuition fees at the home rate and a London stipend at QMUL stipend rates (currently in 2025/26 of £21,874 per year, to be confirmed for 2026/27) annually during the PhD period, which can span for 3 years.

For more information about the project, please contact Dr. Antonino Masaracchia (a.masaracchia@qmul.ac.uk).

Supervisor

Dr Antonino Masaracchia (he/his) – a.masaracchia@qmul.ac.uk

Personal Homepage: https://sites.google.com/view/drantoninomasaracchia/home
Google Scholar:  https://scholar.google.com/citations?user=R1B58e4AAAAJ&hl=it
Centre for Networks, Communications and Systems
https://www.seresearch.qmul.ac.uk/cncs/people/amasaracchia/

Communication Systems Research (CSR) Group
https://csr.eecs.qmul.ac.uk/

How to apply 

Queen Mary is interested in developing the next generation of outstanding researchers and decided to invest in specific research areas. Applicants should submit their application following the instructions at: http://eecs.qmul.ac.uk/phd/how-to-apply/   

The application should include the following: 

  • CV (max 2 pages)  
  • Cover letter (max 4,500 characters) stating clearly in the first page whether you are eligible for a scholarship as a UK resident (https://epsrc.ukri.org/skills/students/guidance-on-epsrc-studentships/eligibility)   
  • Research proposal (max 500 words) 
  • 2 References  
  • Certificate of English Language (for students whose first language is not English)  
  • Other Certificates  

Please note that to qualify as a home student for the purpose of the scholarships, a student must have no restrictions on how long they can stay in the UK and have been ordinarily resident in the UK for at least 3 years prior to the start of the studentship.  For more information please see: (https://epsrc.ukri.org/skills/students/guidance-on-epsrc-studentships/eligibility)  

Application Deadline 

The deadline for applications is the 15th May 2026. 

Interviews will be held in early June. The successful candidate will start in September 2026.

For specific enquiries, contact Dr Antonino Masaracchia at a.masaracchia@qmul.ac.uk

For general enquiries contact Mrs Melissa Yeo at m.yeo@qmul.ac.uk (administrative enquiries) or Dr Arkaitz Zubiaga at a.zubiaga@qmul.ac.uk (academic enquiries) with the subject “EECS 2026 PhD scholarships enquiry”.  

Back to top