Research Group
Future Cities Research Network
Telecommunication Engineering Research Group (TERG)
Proposed supervisory team
Dr Sufian Yousef
Theme
Smart cities, 5G Networks
Summary of the research project
This topic goes in parallel with end-to-end performance and the ability for a network to know what device a user is using, what application is being used, the physical location and speed, and adapting the network performance to best serve those parameters. Work in that area is already ongoing. Big data analytics are already an area of interest for 5G, and researchers expect data-based intelligence to become more prevalent as part of contextual awareness. However, researchers acknowledged that as more and more content providers move to encrypted content, network providers have less visibility into those data streams. This is a very active area of research, and much can be inferred about the content of a data stream based on its behaviour. Many researchers expect to see content providers and network operators come around to sharing more information with one another, because both sides ultimately want an excellent end-user experience.
Data mining is considered to be one of the key enablers for the next generation of mobile networks. The building of knowledge models is expected to tackle the complexity of these networks and enable their dynamic management and operation.
Recently, this research area has attracted a lot of interest and several models have been proposed by the research community.
5G mobile networks target the provision of tailor-cut solutions not only for the telecommunications sector but also for the so called “vertical industries” (e.g., intelligent transportation systems, smart factories, the health sector, etc.). This result will be achieved by deploying multiple network slices over the same network infrastructure. Thus, 5G networks will be considerably more complex than the previous generations.
At the same time, the scientific community has identified that big data solutions can significantly improve the operation and management of existing and future mobile networks. Data mining is used to discover patterns and relationships between variables in large data sets. Several mechanisms that include statistical analysis, artificial intelligence and machine learning are applied in the data set to extract essentially knowledge from the examined data. data are collected from a number of network components. These data may include a variety of information fields such as the quality of the wireless channel, the network load, accounting information, configuration and fault indications, the profile of the subscribers, etc. These data are stored and updated regularly. When collected, they are passed through a pre-processing phase. During this phase transformation, discretization, normalization, outlier detection and dimensionality reduction is executed. The outcome of this phase is then passed to a data analysis phase where a model is built to extract knowledge from the processed data. For example, the result of this process will be the identification of situations where the occurrence of some specific events causes some specific result. The knowledge model may also include some solutions for specific situations (e.g., force the network components to place high moving users to macro cells). The list of the knowledge discovery results can then be communicated to either policy, management or control modules. These modules can use this information in order to optimize the operation of the network and improve the performance.
Where you'll study
Chelmsford
Funding
This project is self-funded.
Details of studentships for which funding is available are selected by a competitive process and are advertised on our jobs website as they become available.
Next steps
If you wish to be considered for this project, we strongly advise you contact the proposed supervisory team. You will also need to formally apply for our Engineering and the Built Environment PhD. In the section of the application form entitled 'Outline research proposal', please quote the above title and include a research proposal.
Continue with Facebook
