Time-Reversibility for Real-Time Scheduling on Multiprocessor Systems

Lee, Jinkyu

doi:10.1109/tpds.2016.2533615

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since we focus on the ( − C k + 1) time slots, the amount of execution of jobs of τ i at those slots is upperbounded by ( − C k + 1). This reduces the amount of calculated interference from [26]. Therefore, if the sum of the WCET of J q k itself and its interference at the ( − C k + 1) time slots in [r q k , r q k + ) is no larger than , J q k finishes its execution before r q k + , which is recorded in the following lemma.…”

Section: A Existing Rta Frameworkmentioning

confidence: 98%

See 1 more Smart Citation

FT-PIP: Flush Task Incorporated Priority-Inheritance Protocol to Reduce Information Leakage on Multiprocessor Real-Time Systems

Baek

Lee

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

In a traditional real-time system, the major requirement is to finish every real-time task within its predefined time. However, as a modern real-time system is connected to external networks and its subsystems are developed by different vendors, it becomes an important requirement to address the problem of information leakage on resources shared by different real-time tasks. This triggers studies that incorporate security mechanisms into the real-time scheduling. While it is one of the most well-known approaches to add the flush task (FT) mechanism and analyze its effect on timing guarantees, the existing FT approaches have been limited to a real-time system that employs at most one resource shared by real-time tasks executed on a uniprocessor platform. In this paper, we propose a flush task incorporated priority-inheritance protocol (FT-PIP) for global fixed-priority multiprocessor scheduling and develop its schedulability analysis, which is the first attempt that not only (a) supports timing guarantees but also (b) satisfies security constraints for (c) a multiprocessor platform with multiple shared resources. Via simulations, we demonstrate that FT-PIP and its schedulability analysis are effective in achieving both (a) and (b) for (c).INDEX TERMS Real-time scheduling, multiprocessor systems, flush task incorporated priority-inheritance protocol, information leakage

show abstract

Section: A Existing Rta Frameworkmentioning

confidence: 98%

“…Lemma 1: (From [3], [26]) A task τ k ∈ τ is schedulable, if every job J q k satisfies the following inequality for at least one…”

Section: A Existing Rta Frameworkmentioning

confidence: 99%

FT-PIP: Flush Task Incorporated Priority-Inheritance Protocol to Reduce Information Leakage on Multiprocessor Real-Time Systems

Baek

Lee

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…They are connected through a high-speed network to form a heterogeneous system. Heterogeneous computing systems are highly competitive because they can provide parallel processing and high performance at a low cost [27], which is one of the reasons why they are widely used in scientific and industrial applications. More than half of the world's top ten supercomputing systems use GPU or CPU accelerator heterogeneous architectures, which are designed to maximize performance and efficiency [28,29].…”

Section: Introductionmentioning

confidence: 99%

List Scheduling Algorithm Based on Virtual Scheduling Length Table in Heterogeneous Computing System

Zhou

Liao

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Edge computing needs the close cooperation of cloud computing to better meet various needs. Therefore, ensuring the efficient implementation of applications in cloud computing is not only related to the development of cloud computing itself but also affects the promotion of edge computing. However, resource management and task scheduling strategy are important factors affecting the efficient implementation of applications. Therefore, aiming at the task scheduling problem in cloud computing environment, this paper proposes a new list scheduling algorithm, namely, based on a virtual scheduling length (BVSL) table algorithm. The algorithm first constructs the predicted remaining length table based on the prescheduling results, then constructs a virtual scheduling length table based on the predicted remaining length table, the current task execution cost, and the actual start time of the task, and calculates the task priority based on the virtual scheduling length table to make the overall path the longest task is scheduled first, thus effectively shorten the scheduling length. Finally, the processor is selected for the task based on the predicted remaining length table. The selected processor may not be the earliest for the current task, but it can shorten the finish time of the task in the next phase and reduce the scheduling length. To verify the effectiveness of the scheduling method, experiments were carried out from two aspects: randomly generated graphs and real-world application graphs. Experimental results show that the BVSL algorithm outperforms the latest Improved Predict Priority Task Scheduling (IPPTS) and RE-18 scheduling methods in terms of makespan, scheduling length ratio, speedup, and the number of occurrences of better quality of schedules while maintaining the same time complexity.

show abstract

“…The same optimality claim holds for the LRT mechanism. For more information about the proof, the reader is referred to [83].…”

Section: Latest Release Timementioning

confidence: 99%

SALSA: A Formal Hierarchical Optimization Framework for Smart Grid

Azar¹

View full text Add to dashboard Cite

The smart grid, by the integration of advanced control and optimization technologies, provides the traditional grid with an indisputable opportunity to deliver and utilize the electricity more efficiently. Building smart grid applications is a challenging task, which requires a formal modeling, integration, and validation framework for various smart grid domains. The design flow of such applications must adapt to the grid requirements and ensure the security of supply and demand. This dissertation, by proposing a formal framework for customers and operations domains in the smart grid, aims at delivering a smooth way for: i) formalizing their interactions and functionalities, ii) upgrading their components independently, and iii) evaluating their performance quantitatively and qualitatively.The framework follows an event-driven demand response program taking no historical data and forecasting service into account. A scalable neighborhood of prosumers (inside the customers domain), which are equipped with smart appliances, photovoltaics, and battery energy storage systems, are considered. They individually schedule their appliances and sell/purchase their surplus/demand to/from the grid with the purposes of maximizing their comfort and profit at each instant of time. To orchestrate such trade relations, a bilateral multi-issue negotiation approach between a virtual power plant (on behalf of prosumers) and an aggregator (inside the operations domain) in a non-cooperative environment is employed. The aggregator, with the objectives of maximizing its profit and minimizing the grid purchase, intends to match prosumers' supply with demand. As a result, this framework particularly addresses the challenges of: i) scalable and hierarchical load demand scheduling, and ii) the match between the large penetration of renewable energy sources being produced and consumed. It is comprised of two generic multi-objective mixed integer nonlinear programming models for prosumers and the aggregator. These models support different scheduling mechanisms and electricity consumption threshold policies.The effectiveness of the framework is evaluated through various case studies based on economic and environmental assessment metrics. An interactive web service for the framework has also been developed and demonstrated.iii ResuméEt smart grid, ved at integrere avancerede styrings-og optimeringsteknologier, giver det traditionelle net en ubestridelig mulighed for at levere og udnytte el mere effektivt. Opbygning af smart grid applikationer er en udfordrende opgave, som kraever et formelt rammevaerk for modellering-, integration og validering af forskellige domaener. Designflowet af sådanne applikationer skal tilpasse sig netkravene og sikre forsynings-og efterspørgselssikker-heden. Denne afhandling, ved at foreslå et formelt rammevaerk for kundeog driftdomaener i smart grid, sigter mod at levere en smidig måde at: i) formalisere deres interaktioner og funktionaliteter, ii) opgradere deres komponenter uafhaengigt og iii) vurdere deres...

show abstract

Time-Reversibility for Real-Time Scheduling on Multiprocessor Systems

Cited by 7 publications

References 20 publications

FT-PIP: Flush Task Incorporated Priority-Inheritance Protocol to Reduce Information Leakage on Multiprocessor Real-Time Systems

FT-PIP: Flush Task Incorporated Priority-Inheritance Protocol to Reduce Information Leakage on Multiprocessor Real-Time Systems

List Scheduling Algorithm Based on Virtual Scheduling Length Table in Heterogeneous Computing System

SALSA: A Formal Hierarchical Optimization Framework for Smart Grid

Contact Info

Product

Resources

About