Real-Time Scheduling Approach of Reconfigurable Embedded Systems Based On Neural Networks with Minimization of Power Consumption

Rehaiem, Ghofrane; Gharsellaoui, Hamza; Ahmed, Samir Ben

doi:10.1016/j.ifacol.2016.07.848

Cited by 7 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors proposed the application of a k l -out-of-N 1 classical rule on the horizontal sets of neurons and an at-most-k 2 -among-N 2 rule on the vertical sets of neurons. (Rehaiem et al, 2016) presented an ANN model which is a Hopfield model for energy-aware online RT non-preemptive scheduling with hard constraints based on the combination of DVS and Neural Feedback Scheduling (NFS) with the priority-energy earliest-deadline-first (PEDF) algorithm. A flexible BP (Back Propagation) learning algorithm is adopted in which only the symbol of gradient to the error function is needed rather than the increase amplitude of gradient.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

AI-Based Methods to Resolve Real-Time Scheduling for Embedded Systems

Boutekkouk

2022

International Journal of Cognitive Informatics and Natural Intelligence

View full text Add to dashboard Cite

Artificial Intelligence is becoming more attractive to resolve nontrivial problems including the well known real time scheduling (RTS) problem for Embedded Systems (ES). The latter is considered as a hard multi-objective optimization problem because it must optimize at the same time three key conflictual objectives that are tasks deadlines guarantee, energy consumption reduction and reliability enhancement. In this paper, we firstly present the necessary background to well understand the problematic of RTS in the context of ES, then we present our enriched taxonomies for real time, energy and faults tolerance aware scheduling algorithms for ES. After that, we survey the most pertinent existing works of literature targeting the application of AI methods to resolve the RTS problem for ES notably Constraint Programming, Game theory, Machine learning, Fuzzy logic, Artificial Immune Systems, Cellular Automata, Evolutionary algorithms, Multi-agent Systems and Swarm Intelligence. We end this survey by a discussion putting the light on the main challenges and the future directions.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

AI-Based Methods to Resolve Real-Time Scheduling for Embedded Systems

Boutekkouk

2022

International Journal of Cognitive Informatics and Natural Intelligence

View full text Add to dashboard Cite

show abstract

“…For multiprocessor systems, Iterative Dynamic Voltage Scheduling (IDVS) and a Dynamic Voltage Loop Scheduling (DVLS) algorithms are proposed by Rehaiem et al [19]. Task scheduling with deadline-miss tolerance on a system with two processors is considered in [20].…”

Section: Literature Reviewmentioning

confidence: 99%

“…A child is infeasible if at least one task in the schedule violates the deadline constraint. Stochastic evolution is then applied to a feasible child with a probability p h (line [10][11][12][13][14][15][16][17][18][19][20][21][22][23]. That is, stochastic evolution is applied to only a subset of feasible children.…”

Section: Task Scheduling Using Hybrid Genetic Algorithmmentioning

confidence: 99%

Energy-Aware Real-Time Task Scheduling in Multiprocessor Systems Using a Hybrid Genetic Algorithm

et al. 2017

View full text Add to dashboard Cite

Abstract:Minimizing power consumption to prolong battery life has become an important design issue for portable battery-operated devices such as smartphones and personal digital assistants (PDAs). On a Dynamic Voltage Scaling (DVS) enabled processor, power consumption can be reduced by scaling down the operating frequency of the processor whenever the full processing speed is not required. Real-time task scheduling is a complex and challenging problem for DVS-enabled multiprocessor systems. This paper first formulates the real-time task scheduling for DVS-enabled multiprocessor systems as a combinatorial optimization problem. It then proposes a genetic algorithm that is hybridized with the stochastic evolution algorithm to allocate and schedule real-time tasks with precedence constraints. It presents specialized crossover and perturb operations as well as a topology preserving algorithm to generate the initial population. A comprehensive simulation study has been done using synthetic and real benchmark data to evaluate the performance of the proposed Hybrid Genetic Algorithm (HGA) in terms of solution quality and efficiency. The performance of the proposed HGA has been compared with the genetic algorithm, particle swarm optimization, cuckoo search, and ant colony optimization. The simulation results show that HGA outperforms the other algorithms in terms of solution quality.

show abstract

“…The algorithm is used for energy efficient equipment as mobile devices, sensor networks; data centre, and distributed computing networks. Rehaiem et al [11] have discovered a scheduling priority based algorithms of real time scheduling for embedded systems. In this method, authors used embedded systems with neural networks for low power consumption optimization.…”

Section: Related Workmentioning

confidence: 99%

Optimization of Energy Consumption for Task Scheduling on Uni-Processor and Multiprocessor for Step Topology under Distributed Environment

Verma¹,

Saxena²

2017

IJCA

View full text Add to dashboard Cite

Distributed computer networking plays a very crucial role in the Business, Industries, Education, Research and Development areas. Many users work on the heterogeneous devices which have different configurations. In distributed network communication takes place from one to one machine, one to many machines or many to one machine. Hence, tasks are migrated from one device to another device which is the important property of the distributed system. Due to rapid increase of the users on the devices connected across the distributed network, the management of the computer networks is a very big and challenging area of research. In the present work, different devices are connected across the step topological networks and an attempt is made to reduce the overall energy consumption when data is flowing from one device to another device. Optimization of energy consumption reduces the overall cost of transfer of data. Multiprocessor and Uni-processor cases are considered in special cases and computed results are represented in the form of tables. A well known Hungarian methodology is used for optimization of the overall energy.

show abstract

Real-Time Scheduling Approach of Reconfigurable Embedded Systems Based On Neural Networks with Minimization of Power Consumption

Cited by 7 publications

References 2 publications

AI-Based Methods to Resolve Real-Time Scheduling for Embedded Systems

AI-Based Methods to Resolve Real-Time Scheduling for Embedded Systems

Energy-Aware Real-Time Task Scheduling in Multiprocessor Systems Using a Hybrid Genetic Algorithm

Optimization of Energy Consumption for Task Scheduling on Uni-Processor and Multiprocessor for Step Topology under Distributed Environment

Contact Info

Product

Resources

About