Future Wireless Networks: 5G/6G Technology
Softerization and Network Function Virtualization introduced by 5G technology has enabled unprecedented opportunities for introducing new dynamic networking paradigms that will enable further increase in network capacity, improved network latency, significant network densification with improved energy efficiency.
Participants with background in either Networks Design or Networks/Internet Economics should benefit from participation.
The course discusses these new incoming technologies with emphasis for the need of joint optimization of technology and business models, including new monetary systems, with significant involvement of Artificial Intelligence.
Artificial Intelligence in Wireless Networks
By increasing the density and number of different functionalities in wireless networks there is more and more need for the use of artificial intelligence for planning the network deployment, running their optimization and dynamically controlling their operation.
Machine learning algorithms are used for the prediction of traffic and network state in order to timely reserve resources for smooth communication with high reliability and low latency. Big data mining is used to predict customer behavior and timely pre-distribute (cashing) the information content across the network so that it can be efficiently delivered as soon as requested.
Intelligent agents can search the internet on behalf of the customer in order to find the best options when it comes to buying any product on line
The course covers a review of AI based learning algorithms with a number of case studies supported by Python and R programs.
It provides a discussion of the learning algorithms used in decision making based on game theory and a number of specific applications in wireless networks such as channel, network state and traffic prediction
When moving from 5G to 6G/7G communication networks there will be need for more sophisticated network optimization tools with respect to both, computational speed and efficiency of optimization algorithms.
It looks like that Quantum Computing (QC) technology offers significant improvements in both of these aspects. Due to inherent parallelism in the processing of quantum information, unpresented increases in computation speed are anticipated. Similarly a number of algorithms developed within the umbrella of quantum technology, like quantum search algorithms (QSA) developed for big data analysis, could be used to help us with more efficient optimization of communication networks. In the past, most of the time we would end up with a formulation of the optimization problem that would need exhaustive search through all combination of the system parameters. This would be unacceptable solution when it comes to complexity and as a consequence we would be looking for simplifications that would on the other hand reduce the performance. By combining the advantageousness of both, unprecedented increase of computational speed and efficiency of QSA we will be able to significantly improve the optimization algorithms for network, deployment and optimization.
For these reasons, the focus of the course will be on discussing the principles of QC and detailed presentations of possibilities of using QSA in communication networks.