Edge-Cloud Collaboration Enabled Video Service Enhancement A Hybrid Human-Artificial Intelligence Scheme
ABSTARCT :
In this paper, a video service enhancement strategy is investigated under an edge-cloud collaboration framework, where video caching and delivery decisions are made in the cloud and edge respectively. We aim to guarantee the user fairness in terms of video coding rate under statistical delay constraint and edge caching capacity constraint. A hybrid human-artificial intelligence approach is developed to improve the user hit rate for video caching. Specifically, individual user interest is first characterized by merging factorization machine (FM) model and multi-layer perceptron (MLP) model, where both low-order and high-order features can be well learned simultaneously. Thereafter, a social aware similarity model is constructed to transferred individual user interest to group interest, based on which, videos can be selected to cache. Furthermore, a double bisection exploration scheme is proposed to optimize wireless resource allocation and video coding rate. The effectiveness of the proposed video caching scheme and video delivery scheme is finally validated by extensive experiments with a real-world data set.
EXISTING SYSTEM :
? In the practice of cloud manufacturing, there still exist some major challenges, including: 1) cloud based big data analytics and decision-making cannot meet the requirements of many latencysensitive applications on shop floors; 2) existing manufacturing systems lack enough reconfigurability, openness and evolvability to deal with shop-floor disturbances and market changes; and 3) big data from shop-floors and the Internet has not been effectively utilized to guide the optimization and upgrade of manufacturing systems.
? This paper proposes an open evolutionary architecture of the intelligent cloud manufacturing system with collaborative edge and cloud processing.
DISADVANTAGE :
? In, an optimization problem for the joint caching and recommendation decisions was formulated with object to maximize the caching hit rate under minimal controllable distortion of the inherent user content preferences, where a heuristic algorithm was proposed to realize lightweight control over recommendations.
? In this paper, we propose to design a video caching scheme with data-driven approach, which can also be considered as a suboptimal solution for problem P2.
? A fundamental problem for video service enhancement is how to send videos to the users as soon as possible.
PROPOSED SYSTEM :
• The proposed architecture (iCMfg) should support flexible re-configuration of smart devices (objects and assets, such as smart pallets, grippers, fixtures, feeders, and robotic mechanisms) involved in a typical workcell will present how to achieve this from a software defined perspective.
• Considering the goals, uncertainties and stakeholders’ preferences to incorporate big data analytics in manufacturing systems, a goal-oriented modelling and fuzzy logic-based approach, was proposed to reason and select suitable big data solution architecture
ADVANTAGE :
? We develop a edge-cloud collaboration framework to enhance video service performance, where the cloud server decides which videos should be cached, and the edge server decides resource allocations for each user.
? In order to further improve service performance, researchers recently pay attention on joint content caching and delivery.
? In order to characterize the delay performance more intuitively, we model the delay metric according to the philosophy behind 5G ultra reliable low latency communications (uRLLC).
? The performance of the proposed individual interest prediction model is first evaluated in terms of Area Under Curve (AUC) and model accuracy (ACC).
|