About this Research Topic
Next-generation wireless systems conceptualize a transformative leap forward in connectivity, promising unprecedented speeds, ultra-low latencies, and ubiquitous service. Leveraging advanced technologies such as mmWaves, THz frequencies and massive MIMO, as well as intelligent network orchestration, next-gen wireless envisions seamless streaming of high-definition content, immersive virtual and augmented reality, and real-time collaboration on a global scale. Next-gen wireless will ultimately support a variety of interconnected devices, from smart cities and autonomous vehicles to IoT sensors and wearables, introducing a new era of digital transformation. While next-gen wireless presents a high potential for societal and economic growth, operation of such systems requires not only to be efficient and driven by actual, observable data, but also to meet certain (often strict) design specifications. To achieve these goals, optimal or at least effective wireless system design (across layers) arises as a fundamental, timely and perpetual task.
Recent advances in technical areas such as optimization, learning and signal processing have attracted significant interest among researchers due to their potential to tackle previously untouchable challenges in wireless system design. For instance, by harnessing the expressive power of learning representations such as neural networks (and beyond), pervasive tasks such as channel estimation, equalization, and interference cancellation can be successfully handled in ways that were not achievable with traditional methods. Moreover, novel techniques within the realms of nonconvex optimization and reinforcement learning enable adaptive and autonomous systems capable of dynamically adjusting to changing conditions.
Nevertheless, integration and deployment into real-world practical wireless communication systems is challenging. For instance, balancing the need for accuracy and efficiency while ensuring low-latency operation remains a critical issue. Further, robustness and reliability at the presence of dynamic and unpredictable wireless environments still need to be thoroughly validated to guarantee consistent performance under diverse conditions. Additionally, there are concerns regarding the interpretability and transparency of black-box machine learning models, particularly in critical or high-stakes applications. These are just some examples of the challenges towards the realization of the full potential of modern optimization, learning and signal processing approaches in shaping the future of wireless communications and networking.
We solicit high-quality original research papers broadly on themes including, but not limited to:
> Resource allocation (deterministic, stochastic, constrained, etc.),
> Random and multiple access,
> Beamforming and Interference Management,
> Scheduling and routing algorithms,
> Cross-layer design and optimization for next-gen wireless,
> AI and machine learning for wireless communications and networking (including approaches relying on deep learning, reinforcement learning, and federated learning in wireless),
> Cutting-edge technologies such as Integrated Sensing and Communications (ISAC), Intelligent Reflecting Surfaces (IRSs), mobility-enabled communication, and Movable Antennas (MAs),
> Fair, Reliable, Robust and Aware wireless communications and networking.
> Short/long-term, or multi-time scale optimization of wireless systems.
Recent advances in technical areas such as optimization, learning and signal processing have attracted significant interest among researchers due to their potential to tackle previously untouchable challenges in wireless system design. For instance, by harnessing the expressive power of learning representations such as neural networks (and beyond), pervasive tasks such as channel estimation, equalization, and interference cancellation can be successfully handled in ways that were not achievable with traditional methods. Moreover, novel techniques within the realms of nonconvex optimization and reinforcement learning enable adaptive and autonomous systems capable of dynamically adjusting to changing conditions.
Nevertheless, integration and deployment into real-world practical wireless communication systems is challenging. For instance, balancing the need for accuracy and efficiency while ensuring low-latency operation remains a critical issue. Further, robustness and reliability at the presence of dynamic and unpredictable wireless environments still need to be thoroughly validated to guarantee consistent performance under diverse conditions. Additionally, there are concerns regarding the interpretability and transparency of black-box machine learning models, particularly in critical or high-stakes applications. These are just some examples of the challenges towards the realization of the full potential of modern optimization, learning and signal processing approaches in shaping the future of wireless communications and networking.
We solicit high-quality original research papers broadly on themes including, but not limited to:
> Resource allocation (deterministic, stochastic, constrained, etc.),
> Random and multiple access,
> Beamforming and Interference Management,
> Scheduling and routing algorithms,
> Cross-layer design and optimization for next-gen wireless,
> AI and machine learning for wireless communications and networking (including approaches relying on deep learning, reinforcement learning, and federated learning in wireless),
> Cutting-edge technologies such as Integrated Sensing and Communications (ISAC), Intelligent Reflecting Surfaces (IRSs), mobility-enabled communication, and Movable Antennas (MAs),
> Fair, Reliable, Robust and Aware wireless communications and networking.
> Short/long-term, or multi-time scale optimization of wireless systems.
Keywords: Emerging Optimization; Wireless Communications; Networking
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
