The growth of video volumes and increased DNN capabilities have led to a growing desire for video analytics, which demands intensive computation resources. Traditional resource provisioning strategies, such as configu...
The growth of video volumes and increased DNN capabilities have led to a growing desire for video analytics, which demands intensive computation resources. Traditional resource provisioning strategies, such as configuring a cluster per peak utilization, lead to low resource efficiency. Serverless computing is a promising way to avoid wasteful resource provisioning since video analytics regularly encounters bursty input workloads and finegrained video content dynamics. For serverless-based video analytics, the application configuration (frame rate, detection model, and computation resources) will impact several metrics, such as computation cost and analytics accuracy. In this paper, we investigate the joint configuration adjustment problem for video knobs and computation resources provided by the serverless platform. We propose an algorithm that can efficiently adapt configurations for video streams to address two key challenges in serverless-based video analytics systems, including the complex relationships between the configurations and the key performance metrics, and the dynamically best configuration. Our algorithm is developed based on Markov approximation to minimize the computation cost within an accuracy constraint. We have developed a prototype over AWS Lambda and conducted extensive experiments with real-world video streams. The results show that our algorithm can greatly reduce the computation cost under the constraint of target accuracy.
Cognitive radio network (CRN) has emerged as a promising solution to solve the problem of underutilization of licensed spectrum. It allows opportunistic access of unutilized spectrum (or white spaces) by unlicensed us...
详细信息
Cognitive radio network (CRN) has emerged as a promising solution to solve the problem of underutilization of licensed spectrum. It allows opportunistic access of unutilized spectrum (or white spaces) by unlicensed users (or secondary users, SUs) whilst minimizing interference to licensed users (or primary users, PUs). The dynamicity of channel availability has imposed additional challenges for routing in CRNs. Besides providing optimal routes to SUs for communication, one of the key requirements of routing in CRNs is to minimize interference to PUs. In this paper, we propose a joint channel selection and cluster-based routing scheme called SMART (SpectruM-Aware cluster-based RouTing) for CRNs. SMART enables SUs to form clusters in the network, and subsequently, it enables SU source node to search for a route to its destination node in the underlying clustered network. SMART applies an artificial intelligence approach called reinforcement learning in order to maximize network performance, such as SU-PU interference and packet delivery ratio. Simulation results show that SMART reduces significant interference to PUs without significance degradation of packet delivery ratio when compared to clustered scheme without cluster maintenance (i.e., SMART-NO-MNT) and non-clustered scheme (i.e., spectrum-aware AODV or SA-AODV).
暂无评论