Performance Modeling of a General GPS Scheduling Under Long Range Dependent Traffic

Zhang, Ran; Liu, Lei; Lu, Xudong; Yan, Zhongmin; Li, Hui

doi:10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00111

Cited by 3 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…multi-queue GPS mainly refers to a GPS system with more than two queues, and it is difficult to analyze its performance. Based on this, Zhang et al [11] gave an approximate analytical solution of the queue length distribution for multi-queue GPS. In order to further improve the accuracy of the multi-queue GPS performance prediction results, Zhang et al [12] designed a knowledge-driven performance prediction method based on a deep learning network by combining GPS theoretical analysis and deep learning.…”

Section: Approximate Analytical Methodsmentioning

confidence: 99%

“…Though it is significantly hard to derive the performance of each queue in the multiqueue GPS system by utilizing the analytical methods, the approximate analytical methods have played a vital role in the performance prediction of the multi-queue GPS system. In this benchmark, the approximate analytical methods for the total queue (MPPA) [9] and for each queue (EBA_Multi) [11] have been compared. In terms of the complicated relationship among the queues and the server, only the upper and lower bounds can be devised exactly.…”

Section: Analytical Approximate Methodsmentioning

confidence: 99%

“…EBA_Multi: To obtain the queue length of each queue in the multi-queue GPS system, Zhang et al [11] further utilized the empty buffer approximate (EBA) method to estimate the service capability actually obtained cap = (c 1 , c 2 , ..., c M ) as the probability of the queue length of each queue. We substitute M = 1 into Equation (3); then, the determining function and the bounds for each queue can be obtained by referring to Equations ( 3) and ( 4), respectively.…”

Section: Analytical Approximate Methodsmentioning

confidence: 99%

“…For example, Mannersalo et al [9] employed large deviation principle-based (LDPs) analytical methods to derive the total queue length distribution for overall GPS scheduling. In [11], the authors use empty buffer approximate (EBA)-based analytical methods to derive the queue length distribution of each application service. Due to the limitations of analytical methods, only approximate solutions for performance prediction can be obtained.…”

Section: Performance Prediction Of the Multi-queue Gps System In The ...mentioning

confidence: 99%

“…For example, in [9,10], the authors employed large deviation principles-based (LDPs) analytical methods to derive the total queue length distribution for the overall GPS scheduling. In [11], the authors used empty buffer approximate (EBA)-based analytical methods to derive the queue length distribution of each application service. In addition, to obtain accurate performance metrics, Zhang et al [12] tried to predict the performance of the GPS scheduling mechanism by employing a deep learning-based method, where the queue theory and the attention network are combined.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

On-Demand Centralized Resource Allocation for IoT Applications: AI-Enabled Benchmark

Zhang,

Liu,

Dong

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

The development of emerging information technologies, such as the Internet of Things (IoT), edge computing, and blockchain, has triggered a significant increase in IoT application services and data volume. Ensuring satisfactory service quality for diverse IoT application services based on limited network resources has become an urgent issue. Generalized processor sharing (GPS), functioning as a central resource scheduling mechanism guiding differentiated services, stands as a key technology for implementing on-demand resource allocation. The performance prediction of GPS is a crucial step that aims to capture the actual allocated resources using various queue metrics. Some methods (mainly analytical methods) have attempted to establish upper and lower bounds or approximate solutions. Recently, artificial intelligence (AI) methods, such as deep learning, have been designed to assess performance under self-similar traffic. However, the proposed methods in the literature have been developed for specific traffic scenarios with predefined constraints, thus limiting their real-world applicability. Furthermore, the absence of a benchmark in the literature leads to an unfair performance prediction comparison. To address the drawbacks in the literature, an AI-enabled performance benchmark with comprehensive traffic-oriented experiments showcasing the performance of existing methods is presented. Specifically, three types of methods are employed: traditional approximate analytical methods, traditional machine learning-based methods, and deep learning-based methods. Following that, various traffic flows with different settings are collected, and intricate experimental analyses at both the feature and method levels under different traffic conditions are conducted. Finally, insights from the experimental analysis that may be beneficial for the future performance prediction of GPS are derived.

show abstract

Section: Approximate Analytical Methodsmentioning

confidence: 99%

Section: Analytical Approximate Methodsmentioning

confidence: 99%

Section: Analytical Approximate Methodsmentioning

confidence: 99%

Section: Performance Prediction Of the Multi-queue Gps System In The ...mentioning

confidence: 99%