Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 135 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Cold Start Mitigation Approach for Serverless Applications Based on Adaptive Container Pool | |||
LI Zhuo,WANG Chun | |||
Computer Science and Technology 08 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the development of cloud computing technology, Serverless is becoming increasingly popular among developers as an emerging paradigm for building applications in the cloud. Serverless allows developers to focus on the logic of applications without worrying about underlying server management. However, the performance of serverless applications is easily affected when facing cold start issues. In order to mitigate the impact of cold start issues on serverless applications, this paper proposes a cold start mitigation approach for serverless applications based on adaptive container pools to reduce the overall latency caused by cold start issues. This approach optimizes the cold start latency of serverless applications based on the internal structure of serverless applications, through the analysis of container pool mechanisms and request history. Experiments show that this approach has achieved significant effects in improving the performance of serverless applications and the efficiency of cloud resource utilization. | |||
TO cite this article:LI Zhuo,WANG Chun. Cold Start Mitigation Approach for Serverless Applications Based on Adaptive Container Pool[OL].[ 8 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762581 |
2. Proactive Edge Computing for Video Streaming: A Mutual Conversion Model for Varying Requirements on Representations | |||
XIONG Guangzheng,DAI Zhitao | |||
Computer Science and Technology 04 November 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The vast proliferation of video streaming traffic imposed unprecedented challenges to origin servers in the Core Network (CN), further exacerbated by the diversity of requirements on video encoding format, resolution, and frame rate. Multi-access Edge Computing (MEC) has been introduced to mitigate the problem by storing and transcoding videos at the network edges to reduce traffic to CN. This work proposes a novel mutual conversion model with a conversion graph among representations by applying the space-time video super-resolution (STVSR) algorithm and transcoding on edge servers. These mutual conversions generate high-definition representations from lower ones and vice versa. The model measures and estimates the qualities of conversion outputs to maintain high Quality of Experience (QoE). Moreover, an off-peak proactive cache replacement algorithm is introduced to utilize the remaining resources by prefetching and pre-converting popular representations, capturing the trend of clients' interests. Transmission history between the edge servers and clients is collected to predict bandwidth and calculate playback buffer length. The experimental results demonstrate that the proposed approach significantly reduces traffic to the origin server while achieving high QoE. | |||
TO cite this article:XIONG Guangzheng,DAI Zhitao. Proactive Edge Computing for Video Streaming: A Mutual Conversion Model for Varying Requirements on Representations[OL].[ 4 November 2022] http://en.paper.edu.cn/en_releasepaper/content/4758328 |
3. Fast, Scalable and Robust Centralized Routing for Data Center Networks | |||
LIN Fusheng,CHEN Guo,WANG Hongyu, ZHOU Guihua, XU Tingting,WEI Dehui,CHEN Li ,LU Yuanwei,QU Andrew,SHAO Hua,JIANG Hongbo | |||
Computer Science and Technology 09 May 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents a fast and robust centralized data center network (DCN) routing solution called \name. For fast routing calculation, \name uses centralized controller to collect/disseminates the network's link-states (LS), and offload the actual routing calculation onto each switch. Observing that the routing changes can be classified into a few fixed patterns in DCNs which have regular topologies, we simplify each switch's routing calculation into a table-lookup manner, i.e., comparing LS changes with pre-installed base topology and updating routing paths according to predefined rules. For efficient controller fault-tolerance, \name purposely uses reporter switch to ensure the LS updates successfully delivered to all affected switches. As such, \name can use multiple stateless controllers and little redundant traffic to tolerate failures, which incurs little overhead under normal case. Primus maintains good routing controllability/manageability thanks to its centralized architecture, which enables us to build several advanced routing features in our testbed, including routing failure visualization and weighted-cost-multi-path routing. | |||
TO cite this article:LIN Fusheng,CHEN Guo,WANG Hongyu, et al. Fast, Scalable and Robust Centralized Routing for Data Center Networks[OL].[ 9 May 2022] http://en.paper.edu.cn/en_releasepaper/content/4757665 |
4. Delay-Sensitive and Energy-Efficient Dependent Task Offloading in Edge-Cloud Collaboration | |||
Chong Li,Haiyang Zhang | |||
Computer Science and Technology 08 March 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:As an emerging computing paradigm, Mobile Edge Computing (MEC) can dramatically reduce latency and system energy consumption, which provides better quality of service for mobile users.One of the main challenges of MEC is determining a feasible task offloading decision of a mobile application to minimize the makespan or energy consumption. However, previous works on task offloading often ignore the interdependency between tasks, which is common in applications.In this paper, we focus on the problem of task offloading for a mobile application with several dependent tasks in an edge-cloud collaboration architecture. We aim to find a decision to minimize the weighted sum of makespan and total energy consumption. Since the problem is NP-hard, we propose a multi-objective optimization based heuristic algorithm to tackle this problem. Specifically, the algorithm first obtains a sub-optimal solution by eliminating some constraints and relaxing the original problem. Then, it allocates a priority for each task under dependency constraints. Finally, in each iteration, it generates several intermediate solutions and selects the first few solutions greedily.Extensive simulation results using both real applications and randomly generated applications show that our algorithm substantially outperform other alternatives. | |||
TO cite this article:Chong Li,Haiyang Zhang. Delay-Sensitive and Energy-Efficient Dependent Task Offloading in Edge-Cloud Collaboration[OL].[ 8 March 2022] http://en.paper.edu.cn/en_releasepaper/content/4756541 |
5. A Multi-path Non-overlapping Routing Algorithm for Deterministic Networking | |||
Jiwang Shao,Gengyu Wei | |||
Computer Science and Technology 17 February 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Deterministic Networking (DetNet) is a new network architecture proposed by IETF DetNet working group for industrial Internet of Things and other application scenarios. Its communication service with high reliability and low delay needs multi-path non-overlapping routing algorithm. Because it is different from the existing routing algorithms on the Internet, it is an important subject to study the routing algorithms that meet the requirements of DetNet. Based on the routing characteristics of DetNet, we study a multi-routing algorithm -- Bhandari algorithm. Aiming at the problem that the algorithm can not calculate non-overlapping routes in some cases, we improved the algorithm, then we also make the improved algorithm more efficient by introducing Tarjan algorithm. The algorithm is verified and tested in the simulation environment and results show the effectiveness of the improved algorithm. | |||
TO cite this article:Jiwang Shao,Gengyu Wei. A Multi-path Non-overlapping Routing Algorithm for Deterministic Networking[OL].[17 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756297 |
6. Research and implementation of congestion control technology in real-time streaming media conference scene | |||
He Wei,Qi Qi | |||
Computer Science and Technology 21 January 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The Google Congestion Control algorithm (GCC) is a key algorithm in the Web Real-Time Communication (WebRTC) network transport module and has been widely used in real-time streaming media transport. the goal of the GCC algorithm is to improve the quality of service as much as possible on the basis of low latency, so the delay sensitivity threshold parameter takes into account various networks, but the performance of the traffic model in the meeting scenario still needs to be improved . In this paper, we propose to introduce a neural network to evaluate the current network quality based on the QOS parameters of the network and further adaptively adjust the delay sensitivity threshold parameters to better adapt to the conference traffic. The final improved algorithm achieves an 11.8\% improvement in bandwidth utilization for conference traffic, and a 7.16\% improvement in bandwidth utilization for dynamic network link capacity variations. | |||
TO cite this article:He Wei,Qi Qi. Research and implementation of congestion control technology in real-time streaming media conference scene[OL].[21 January 2022] http://en.paper.edu.cn/en_releasepaper/content/4756149 |
7. Load-Aware Transmission Mechanism for NVMeoF Storage Networks | |||
Qiao Xinghan,Xie Xuchao,Xiao Liquan | |||
Computer Science and Technology 21 October 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:NVMe over TCP is a key technology for building large-scale high-performance storage systems.It can realize NVMeoF (NVMe over Fabrics) storage network based on the existing data center network infrastructure and standard TCP/IP software protocol stack. This article designs and implements the Load-Aware NVMeoF message processing mechanism LANoT (Load-Aware NVMe over TCP). Firstly, the interrupt merging technology based on aggregated PDU is used to alleviate the interrupt storm problem and achieve high throughput. Secondly, matching the special message processing mechanism, which can effectively improve its key performance indicators for applications according to the I/O characteristics of different dedicated queues . This paper implements the LANoT prototype system in the Linux kernel. The performance test results show that compared to the NVMe over TCP implementation in the standard Linux kernel, LANoT can reduce CPU resource consumption by more than 50% and increase IOPS by more than twice. | |||
TO cite this article:Qiao Xinghan,Xie Xuchao,Xiao Liquan. Load-Aware Transmission Mechanism for NVMeoF Storage Networks[OL].[21 October 2021] http://en.paper.edu.cn/en_releasepaper/content/4755658 |
8. Helm: Credit-based Data Center Congestion Control to Achieve Near Global-Optimal SRTF | |||
SHI Jia-Ming, ZHANG Jiao | |||
Computer Science and Technology 29 January 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:To satisfy the ultra-low latency requirement of cloud services, a lot of congestion control mechanisms have been proposed to reduce the Flow Completion Time (FCT) in data center networks.Theoretically, SRTF could achieve minimal FCT. However, existing congestion control mechanisms either do not achieve SRTF or are difficult to be deployed.This paper analyzes the challenges of achieving global-optimal Shortest Remaining Time First (SRTF) scheduling in a congestion control mechanism. Then a credit-based congestion control mechanism, Helm, is proposed. Helm solves the challenges by carefully combining the finite priority queues at switches and infinite rate setting at receivers and thus achieves near global-optimal SRTF. With theoretically analysis, Helm can achieve near global-optimal SRTF. Besides, extensive simulations are conducted and the results show that Helm reduces the mean and tail FCT by up to 62\% and 75\%, respectively, compared with Homa. | |||
TO cite this article:SHI Jia-Ming, ZHANG Jiao. Helm: Credit-based Data Center Congestion Control to Achieve Near Global-Optimal SRTF[OL].[29 January 2021] http://en.paper.edu.cn/en_releasepaper/content/4753526 |
9. Adaptive packet scheduling algorithm for time-sensitive service | |||
ZHANG Zhenjie,Jianfeng Guan | |||
Computer Science and Technology 18 December 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of mobile Internet and Internet of things, a series of time sensitive services such as video conferencing, cloud games, AR / VR have emerged. In order to meet the above time sensitive services, IETF proposed Deterministic Network(DetNet) architecture, which provides an ideal deterministic delay through clock synchronization, zero congestion loss and other mechanisms. At the same time, Tsinghua University proposed Deadline-aware transport protocol(DTP), hoping to specify the deadline in the application layer, and then meet the requirements in the transport layer. These strategies and ideas for time delay sensitive services are worth learning from. However, the current packet transmission mechanisms are all rule-based and relatively static strategies, which can’t meet the demand of time sensitive service in dynamic network. Therefore, based on the idea of DTP and reinforcement learning, this paper proposes an algorithm to dynamically adjust the transmission priority. More specifically, we design the reward and penalty function according to the requirements of DTP protocol, and design the algorithm of congestion control and packet scheduling in the transport layer. We consider not only the priority but also the service deadline. Comprehensive experiments show that compared to traditional packet scheduling strategies, our algorithm performs better in the transmission of time-sensitive services | |||
TO cite this article:ZHANG Zhenjie,Jianfeng Guan. Adaptive packet scheduling algorithm for time-sensitive service[OL].[18 December 2020] http://en.paper.edu.cn/en_releasepaper/content/4753219 |
10. Reducing Web Latency with Coding-Based Fast Multi-Path Loss Recovery | |||
LIU Yi,CHEN Guo | |||
Computer Science and Technology 14 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:TCP latency is critical to the performance of web services. However, packet loss greatly impairs the TCP performance due to its poor loss recovery mechanisms. Recent work FUSO addressed this problem by leveraging multi-path diversity for proactive loss recovery, it used "good" paths to proactively retransmit the potentially lost packet on "bad" paths. However, because it's impossible to predict which packet is truly lost, FUSO tended to retransmit the oldest unACKed packet. Through analysis and comprehensive experiments, this paper shows that in the Internet scenario, such simple proactive retransmission of the oldest unACKed packet is not accurate enough to recover the lost packets, which causes performance penalty. To address the problem, this paper presents \name, a \fullname. Different from FUSO, when there is a chance for proactive loss recovery, \name generates a coding packet that codes all (or multiple) unACKed packets together. As such, \name can always proactively retransmit the ``right'' lost packet, since the receiver side can decode the lost packet by combining the coding packet with other received packets. \name is implemented in Linux kernel with \approx2K lines of code.Testbed and simulation results show that, under lossy condition, \name can greatly decrease the average and $99^{th}$ percentile flow completion time (FCT) by \approx12\% and \approx59\% in the testbed, and up to \approx16.9\% and \approx54.5\% in the simulation, respectively. | |||
TO cite this article:LIU Yi,CHEN Guo. Reducing Web Latency with Coding-Based Fast Multi-Path Loss Recovery[OL].[14 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752040 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated