Dr. Adita Kulkarni Presents Her Research at Virtual EAI International Conference on Ad Hoc Networks 2020
Dr. Kulkarni, Department of Computing Sciences, presented her research titled "Model-Based and Machine Learning Approaches for Designing Caching and Routing Algorithms" at the virtual EAI International Conference on ADHOCNETS 2020 on November 17.
Abstract of research paper:
Over the last decade, cache networking research has gathered significant momentum and its benefits are likely to impact a variety of future communication systems including 5G networks, clouds, and IoT systems. One of the salient features of cache networks is improving user performance by serving content from in-network caches rather than the origin servers. To achieve this, several caching and routing strategies have been proposed over the last decade. In this work, we compare and contrast model-based and machine learning approaches for designing caching and routing strategies. We outline the key principles used in the design of model-based strategies and discuss the analytical results and bounds obtained for these approaches. By conducting experiments on real-world traces and networks, we identify the interplay between content popularity skewness and request stream correlation as an important factor affecting cache performance. We then discuss the applicability of multiple machine learning models, specifically reinforcement learning, deep learning, transfer learning, and probabilistic graphical models for the caching and routing problem.
posted by mkamal [2020-12-10]
Dr. Adita Kulkarni: firstname.lastname@example.org