EPSRC DTP PhD studentship: Real-¬time big data analytics for automatic network optimisation in future Internet

University of Exeter - College of Engineering, Mathematics and Physical Sciences

Main supervisor: Yulei Wu (University of Exeter)
Co-supervisor:  Geyong Min (University of Exeter)

Project Description:
Automatic network optimisation plays an increasingly important role in improving the Quality-­of-­Service (QoS) in large-­scale future Internet. Recent studies have demonstrated that the network big data hold much valuable information that could be used to significantly improve the effective and intelligent optimisation of future Internet. However, the unstructured, heterogeneous, sheer volume and complex natures of network big data pose great challenges on current computing, storage and networking architecture/protocols and thus call for efficient data representation, processing and analysis algorithms to effectively discover hidden information available for network optimisation. The existing state-­of-­the-­art machine learning algorithms cannot scale up for big data analytics and large-scale networks due to very high computation overhead and non-­real-­time response. This project aims to propose real-­ time mining algorithms based on incremental computation to efficiently process the collected big data with robust data representation methods for intelligent optimisation of future Internet, and further evaluates the network performance under the developed algorithms by virtue of the cost-effective analytical modelling.

Automatic network optimisation plays an increasingly important role in improving the Quality-­of-­Service of future Internet. Recent studies have demonstrated that the network big data hold much valuable information that could be used to significantly improve the effective and intelligent optimisation of future Internet. However, the existing state-­of-­the-­art algorithms cannot scale up for big data analytics and large-scale networks due to very high computation overhead and non-­real-­time response.

The student to be involved will focus on the following three tasks, and will form an important role in this project:

Task 1: Devise efficient pre-­processing algorithms and robust data representation methods to adapt for the unstructured, heterogeneous, sheer volume and complex natures of network big data.

Task 2: Devise real-­time mining algorithms based on incremental computation to efficiently handle the pre-­processed big data for intelligent optimisation of resource allocation and fault localisation in future Internet.

Task 3: Develop novel system-­level analytical models and simulations to evaluate the network performance under the proposed algorithms.

The research topics of this project are the key technologies to realise automatic network optimisation for big data future Internet. The Internet service provider, e.g.BT, and content/service provider, e.g., Sky and Youtube, are demanding automatic network optimisation to intelligently manage their operational network and achieve root fault localisation. In addition, Gartner, a famous information technology research and advisory company, has reported that big data will create big jobs in the near future. Therefore, the deep training through this project will make the student highly competitive in their future job hunting and future progression.

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

South West England