AI-based methods to resolve Real time scheduling for embedded systems

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.

Download Full-text

Real-Time Embedded Systems Scheduling Optimization

International Journal of Applied Evolutionary Computation ◽

10.4018/ijaec.2021010104 ◽

2021 ◽

Vol 12 (1) ◽

pp. 43-73

Author(s):

Fateh Boutekkouk

Keyword(s):

Embedded Systems ◽

Real Time ◽

Design Space ◽

Artificial Immune Systems ◽

Scheduling Problem ◽

Future Directions ◽

Real Time Scheduling ◽

Energy Consumption Reduction ◽

Consumption Reduction ◽

Time Scheduling

The embedded real-time scheduling problem is qualified as a hard multi-objective optimization problem under constraints since it should compromise between three key conflictual objectives that are tasks deadlines guarantee, energy consumption reduction, and reliability enhancement. On this fact, conventional approaches can easily fail to find a good tradeoff in particular when the design space is too vast. On the other side, bio-inspired meta-heuristics have proved their efficiency even if the design space is very large. In this framework, the authors review the most pertinent works of literature targeting the application of bio-inspired methods to resolve the real-time scheduling problem for embedded systems, notably artificial immune systems, machine learning, cellular automata, evolutionary algorithms, and swarm intelligence. A deep discussion is conducted putting the light on the main challenges of using bio-inspired methods in the context of embedded systems. At the end of this review, the authors highlight some of the future directions.

Download Full-text

Multiagentensysteme in der Agilen Montage/Multi-agent systems in agile assembly – Real-time scheduling of flexible operation sequences on multifunctional assembly stations

wt Werkstattstechnik online ◽

10.37544/1436-4980-2020-04-4 ◽

2020 ◽

Vol 110 (04) ◽

pp. 170-176

Author(s):

Peter Burggräf ◽

Matthias Dannapfel ◽

Tobias Adlon ◽

Hannes Kahmann ◽

Esben Schukat ◽

...

Keyword(s):

Real Time ◽

Degrees Of Freedom ◽

Multi Agent Systems ◽

Cycle Times ◽

Real Time Scheduling ◽

Agent Systems ◽

Automotive Assembly ◽

Time Scheduling ◽

Multi Agent ◽

Flexible Operation

In der variantenreichen Automobilindustrie gewinnen Montagesysteme mit frei vernetzten und taktzeitunabhängigen Montagestationen stetig an Bedeutung. Durch zunehmende Freiheitsgrade und den damit verbundenen Komplexitätsanstieg stellt sich jedoch die Frage, wie die Anforderungen nach Robustheit und Echtzeitfähigkeit in der Ablaufplanung erfüllt werden können. In diesem Beitrag wird ein Konzept zur Ablaufplanung in der „Agilen Montage“ unter Verwendung von Multiagentensystemen vorgestellt, das auch hinsichtlich der Anwendbarkeit in der Automobilmontage geprüft wurde.   Assembly systems with flexibly linked assembly stations independent of cycle times are becomimg more important in the multi-variant automotive industry. Due to increasing degrees of freedom and the associated increase in complexity, the question arises how the requirements for robustness and real-time capability in sequence planning can be met. In this article, a concept for scheduling in the agile assembly using multi-agent systems is presented and examined with regard to its applicability in automotive assembly.

Download Full-text

Multithreading MAS Platform for Real-Time Scheduling

International Journal of Software Innovation ◽

10.4018/ijsi.2016010104 ◽

2016 ◽

Vol 4 (1) ◽

pp. 48-60 ◽

Cited By ~ 3

Author(s):

Yaroslav Shepilov ◽

Daria Pavlova ◽

Daria Kazanskaia

Keyword(s):

Real Time ◽

Scheduling Problem ◽

Optimal Resource Allocation ◽

Dynamic Changes ◽

Real Time Scheduling ◽

Fast Solution ◽

Agent Scheduling ◽

Time Scheduling ◽

Optimal Resource ◽

Multi Agent

The scheduling is the process of the optimal resource allocation that is widely used both in everyday life and specific domains. In the paper the description of scheduling problem is given. The authors consider traditional methods and tools for solving this problem, then describe the proposed approach based on multi-agent technologies and multithreading application. Nowadays there exist numerous approaches to solving of the scheduling problem. In the most of cases this process has to be supported and managed by the complex tools, sometimes based on mathematical principles. The suggested method of multithreading multi-agent scheduling allows efficient and fast solution of complex problems in real-time featuring rapid dynamic changes and uncertainty that cannot be handled by the other methods and tools.

Download Full-text