Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?

By Alessio Zappone, M. Di Renzo, Merouane Debbah. IEEE Transactions on Communications, 2019

563 citations recorded by the source corpus.

This paper deals with the use of emerging deep learning techniques in future wireless communication networks. It will be shown that the data-driven approaches should not replace, but rather complement, traditional design techniques based on mathematical models. Extensive motivation is given for why deep learning based on artificial neural networks will be an indispensable tool for the design and operation of future wireless communication networks, and our vision of how artificial neural networks should be integrated into the architecture of future wireless communication networks is presented. A thorough description of deep learning methodologies is provided, starting with the general machine learning paradigm, followed by a more in-depth discussion about deep learning and artificial neural networks, covering the most widely used artificial neural network architectures and their training methods. Deep learning will also be connected to other major learning frameworks, such as reinforcement learning and transfer learning. A thorough survey of the literature on deep learning for wireless communication networks is provided, followed by a detailed description of several novel case studies wherein the use of deep learning proves extremely useful for network design. For each case study, it will be shown how the use of (even approximate) mathematical models can significantly reduce the amount of live data that needs to be acquired/measured to implement the data-driven approaches. Finally, concluding remarks describe those that, in our opinion, are the major directions for future research in this field.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/407fe62032a0d69cf77a13fb86645858f46ee9c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How it Works, State of Research, and Road Ahead (2020, methodology): “ against each other. It is shown that RISs are capable of providing a similar average rate as relays, but without necessitating a power ampliﬁer and provided that they are sufﬁciently large. In [26], [27], [28], the potential need and applications of machine learning and AI to SREs are investigated.”
Toward Smart Wireless Communications via Intelligent Reflecting Surfaces: A Contemporary Survey (2019, background): “By integrating the smart radio environment into the network optimization problems, IRS-assisted wireless networks are envisioned to revolutionize the current network optimization paradigm and expected to play an active role in future wireless networks [3], [26].”
Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review (2020, background): “3 shows the working algorithm of both ML and DL, and their performance with the amount of data [34].”
A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, background): “With the focus on the smart radio environment, Zappone et al. [21] proposed to integrate deep learning with traditional model-based technologies in future wireless networks.”
A Survey of Rate-Optimal Power Domain NOMA With Enabling Technologies of Future Wireless Networks (2019, methodology): “Another developing trend for next-generation wireless networks, such as B5G cellular networks, is the advent of a data-driven approach using machine learning (ML) to complement or even replace the traditional model-driven approach [141], [142] used in communication systems.”
Reconfigurable Intelligent Surfaces: Principles and Opportunities (2020, background): “arning (DL) has shown great potentials to revolutionize communication systems. It can be applied in diverse areas of the RIS-enhanced wireless networks due to its powerful learning capabilities [105]–[107]. The acquisition of timely and accurate CSI plays a pivotal role in wireless systems, especial”
Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges (2022, background): “Otherwise, they are required to go through additional re-design and re-training phases until the validation tests are successful [129].”
Holistic Network Virtualization and Pervasive Network Intelligence for 6G (2023, methodology): “For more discussions on challenges in hybrid data-model driven methods for networks, interested readers are referred to [232], [248], [249].”
Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges (2019, background): “Detailed description of DL Methodologies and artificial neural networks can be found in [122].”
Convergent Communication, Sensing and Localization in 6G Systems: An Overview of Technologies, Opportunities and Challenges (2021, background): “The advantages of IRS technology over current solutions (e.g., densiﬁcation and massive MIMO) are discussed in [34].”
Smart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come (2019, methodology): “We think, in addition, that the future of wireless networks may be towards the realization of reconfigurable intelligent meta-surfaces with memory and computing power where machine learning is executed directly on the meta-surfaces by leveraging federated learning concepts [160, 163].”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “, [11]–[13], [15]–[17], [19], [21], [24], [26], [27] and [30]–[38], respectively.”