Push-based Services Research Articles

When QoE meets learning: A distributed traffic-processing framework for elastic resource provisioning in HetNets

In heterogeneous networks (HetNets), dynamics of user requirements across the temporal domain lead to the order of magnitude traffic to be processed by macro cells. To achieve high quality of experience (QoE) for users and to perform resource allocation for cells intelligently, we first propose a distributed traffic-processing framework (SDVTS) for elastic resource partitioning, to accommodate dynamics from the user-centric and resource-oriented perspectives respectively. Assisted by a software defined infrastructure, SDVTS fulfills the responsibilities of the request-based and push-based services in an interactive loop. Second, we formulate a traffic-processing time model that computes the delay of handling traffic. The non-convex model is decomposed and a dual evolution algorithm is explored to approximate the optimal solution. Furthermore, we introduce a low-complexity reinforcement learning algorithm with the personalized QoE profiling. A distributed algorithm in coalition between user and cell is designed for seamless connection of an advanced reinforcement learning system (ARLS) components and engines embedded in SDVTS. Extensive simulation results with thorough analysis demonstrate that our framework SDVTS dominates in terms of QoE and cell′s system performance when compared with competing approaches.

LISA: Lightweight context-aware IoT service architecture

Internet-of-Things (IoT) promises to provide services to the end users by connecting physical things around them through Internet. The conventional services build for web are primarily based on the pull technology, where the user actively engages with system to get the services. However, in IoT environment, the services are based on push-based, where information and value added services will be pushed towards the user. Unless, these push-based services are properly managed they would overwhelm the user with unnecessary information, thus, it will soon start annoying the user.In this paper, we propose a lightweight context-aware IoT service architecture namely LISA to support IoT push services in an efficient manner. In particular, LISA filter and forward the most important and relevant services to the users by understanding their context. To achieve its goals, LISA formulates a user model to resolve local decision making by using agents and available web services paradigm. The proposed user model describes the user in an abstract way by considering the context and profile information of the user. For evaluation, we simulate LISA by considering an IoT tourist guide system as a use case scenario, and we show the performance of the our user model concerning precision and recall metrics. The results of our preliminary experiments confirm that LISA successfully reduces the information provided to the user by selecting only the most relevant among those. The evaluation shows that LISA can extract services for a user by selecting from 15000 services with precision upto 0.3 and recall upto 0.8, and it can be further optimized by tuning the user-specific design settings. Additionally, our approach shows improvements in query processing time which also includes the query generation time.