Capturing ICT Emerging Technologies: Focusing on AI/ML Application and Networking Trends

Motivation and Background

The telecommunication service provider industry is one of the biggest businesses in the world. At the other side, Telecom operators are threatened by fast and highly efficient web-scale companies and are straining under the challenge posed by digital transformation. On top of all that, telecom operators must solve how to profitably manage and operate the dizzyingly complex next-generation 5G/Internet of Things (IoT) networks. It is an industry ripe for artificial intelligence (AI)-driven solutions, with their promise of lowering costs and boosting efficiencies through automation. Many operators have begun to experiment and deploy AI-driven solutions in both customer-facing and internal organizations. Some of organisations have identified seven key telecom AI use cases: network operations monitoring and management, predictive maintenance, fraud mitigation, cybersecurity, customer service and marketing virtual digital assistants (VDAs), intelligent customer relationship management (CRM) systems, and customer experience management (CEM).

One of key enablers of AI systems is based on the Machine learning (ML). It has recently regained attentions because of the successful applications of deep learning (DL) in computer vision (CV), automatic speech recognition (ASR), and natural language processing (NLP). Researchers are actively attempting to extend these technologies to other domains, including wireless communication. They have applied ML to the physical layer for modulation recognition, channel modelling and identification encoding and decoding, channel estimation, and equalization, however, ML has been unused commercially because handling physical channels is a complex process, and conventional ML algorithms have limited learning capacity. Embedding ML theories on a wide range of communication systems has had an extensive history and has achieved several successes, especially in the upper layers, such as in cognitive radio, resource management, link adaptation, and positioning. In contrast to the above mentioned straightforward applications, ML faces several challenges when applied to the physical layer. Also, extant conventional communication theories exhibit several inherent limitations in fulfilling the large data and ultra-high rate communication requirements in complex scenarios, listed as follows.

  1. Difficult channel modelling in complex scenarios
  2. Demand for effective and fast signal processing
  3. Limited block-structure communication

 

Researchers believe that ML can achieve further performance improvements by introducing Deep Learning (DL) to the physical layer. DL possesses essential characteristics, such as deep modularization, which significantly enhances feature extraction and structure flexibility, compared with conventional ML algorithms. In particular, DL-based systems can be used instead of manual feature extraction to learn features from raw data automatically and adjust the model structures flexibly via parameter tuning to optimize end-to-end performance.  

Scope of the Panel 

This panel will be devoted to the presentation of applications of Artificial Inteligence and Machine Learning methods in communication network problems, with the goal of reaching a better understanding of the potential achievements that can be expected. Additionally, contributions to the fields of AI/ML, building on existing methods from the fields of communication, signal processing, and information theory will also be discussed. Topics of interest may include, but are not limited to the following:

  • AI/ML/DL for communication networks and coding
  • Reinforcement learning for communication networks and coding
  • Deep reinforcement learning for communications networks and coding
  • Pattern recognition and classification for wireless networks and coding
  • Machine learning for network slicing optimization
  • Machine learning for 5G system and PHY/MAC optimization (massive MIMO, mmWave,...)
  • Machine learning for user behaviour prediction in communication networks
  • New innovative machine learning methods related to communication networks and coding
  • Progresses in partially supervised learning methods in communication networks and coding
  • Performance analysis of machine learning algorithms in communication networks and coding
  • Experimental evaluations of machine learning in communication networks and coding

 

Editorial:

With the rapid development of wireless communication technologies, the number of wireless users is increasing substantially. However, researches have shown that there is a big gap in terms of the current wireless communication technologies and the future requirements. Therefore, there is an urgent need that the wireless communication technologies should be more intelligent in order to better satisfy the requirement of future wireless users. Driven by this demand, Artificial Intelligence and Machine Learning which offers computers the ability to learn without being explicitly programmed is widely focused. In particular, evolving from pattern recognition and artificial intelligence, machine learning investigates the study and establishment of algorithms which can learn from and make predictions on complicated scenarios. Thus, with machine learning, the complicated scenarios analysis and prediction in wireless communication technologies could be facilitated in order to make optimal actions. In other words, the application of machine learning in wireless communication technologies is with great potential to obtain more intelligent wireless communication systems with better performance.

  •  

  (specify 5 questions to be discussed/answered in the panel)

1‐ Is AI/ML useful in communications?

2‐ What are the Impacts of AI/ML on Communication and Networking Technologies?

3‐ Changes on the convention algorithms in communications: How?

4‐ What are the evolutions on the users and networks interactions?

5‐ What is the next?

  • Motivation and Background

The telecommunication service provider industry is one of the biggest businesses in the world. At the other side, Telecom operators are threatened by fast and highly efficient web-scale companies and are straining under the challenge posed by digital transformation. On top of all that, telecom operators must solve how to profitably manage and operate the dizzyingly complex next-generation 5G/Internet of Things (IoT) networks. It is an industry ripe for artificial intelligence (AI)-driven solutions, with their promise of lowering costs and boosting efficiencies through automation. Many operators have begun to experiment and deploy AI-driven solutions in both customer-facing and internal organizations. Some of organisations have identified seven key telecom AI use cases: network operations monitoring and management, predictive maintenance, fraud mitigation, cybersecurity, customer service and marketing virtual digital assistants (VDAs), intelligent customer relationship management (CRM) systems, and customer experience management (CEM).

One of key enablers of AI systems is based on the Machine learning (ML). It has recently regained attentions because of the successful applications of deep learning (DL) in computer vision (CV), automatic speech recognition (ASR), and natural language processing (NLP). Researchers are actively attempting to extend these technologies to other domains, including wireless communication. They have applied ML to the physical layer for modulation recognition, channel modelling and identification encoding and decoding, channel estimation, and equalization, however, ML has been unused commercially because handling physical channels is a complex process, and conventional ML algorithms have limited learning capacity. Embedding ML theories on a wide range of communication systems has had an extensive history and has achieved several successes, especially in the upper layers, such as in cognitive radio, resource management, link adaptation, and positioning. In contrast to the above mentioned straightforward applications, ML faces several challenges when applied to the physical layer. Also, extant conventional communication theories exhibit several inherent limitations in fulfilling the large data and ultra-high rate communication requirements in complex scenarios, listed as follows.

  1. Difficult channel modelling in complex scenarios
  2. Demand for effective and fast signal processing
  3. Limited block-structure communication

 

Researchers believe that ML can achieve further performance improvements by introducing Deep Learning (DL) to the physical layer. DL possesses essential characteristics, such as deep modularization, which significantly enhances feature extraction and structure flexibility, compared with conventional ML algorithms. In particular, DL-based systems can be used instead of manual feature extraction to learn features from raw data automatically and adjust the model structures flexibly via parameter tuning to optimize end-to-end performance.  

Scope of the Panel 

This panel will be devoted to the presentation of applications of Artificial Inteligence and Machine Learning methods in communication network problems, with the goal of reaching a better understanding of the potential achievements that can be expected. Additionally, contributions to the fields of AI/ML, building on existing methods from the fields of communication, signal processing, and information theory will also be discussed. Topics of interest may include, but are not limited to the following:

  • AI/ML/DL for communication networks and coding
  • Reinforcement learning for communication networks and coding
  • Deep reinforcement learning for communications networks and coding
  • Pattern recognition and classification for wireless networks and coding
  • Machine learning for network slicing optimization
  • Machine learning for 5G system and PHY/MAC optimization (massive MIMO, mmWave,...)
  • Machine learning for user behaviour prediction in communication networks
  • New innovative machine learning methods related to communication networks and coding
  • Progresses in partially supervised learning methods in communication networks and coding
  • Performance analysis of machine learning algorithms in communication networks and coding
  • Experimental evaluations of machine learning in communication networks and coding

 

Editorial:

With the rapid development of wireless communication technologies, the number of wireless users is increasing substantially. However, researches have shown that there is a big gap in terms of the current wireless communication technologies and the future requirements. Therefore, there is an urgent need that the wireless communication technologies should be more intelligent in order to better satisfy the requirement of future wireless users. Driven by this demand, Artificial Intelligence and Machine Learning which offers computers the ability to learn without being explicitly programmed is widely focused. In particular, evolving from pattern recognition and artificial intelligence, machine learning investigates the study and establishment of algorithms which can learn from and make predictions on complicated scenarios. Thus, with machine learning, the complicated scenarios analysis and prediction in wireless communication technologies could be facilitated in order to make optimal actions. In other words, the application of machine learning in wireless communication technologies is with great potential to obtain more intelligent wireless communication systems with better performance.

  • Questions

  (specify 5 questions to be discussed/answered in the panel)

1‐ Is AI/ML useful in communications?

2‐ What are the Impacts of AI/ML on Communication and Networking Technologies?

3‐ Changes on the convention algorithms in communications: How?

4‐ What are the evolutions on the users and networks interactions?

5‐ What is the next?