An Adaptive CPU Scheduling for Embedded Operating Systems using Genetic Algorithms

This paper explains novel CPU scheduling approach for embedded operating Systems. In this approach we have used genetic algorithm (GA). Proposed Adaptive algorithm combines both EDF and GA based algorithms, Basically the new algorithm uses EDF algorithm but when the system becomes overloaded, it will switch to GA based scheduling algorithm. Again, when the overload disappears, the system will switch to EDF algorithm. Therefore the proposed algorithm takes the advantages of both algorithms and overcome their limitations. We have simulated, proposed adaptive algorithm along with both EDF and GA based algorithms for real time systems. The performance is measured in terms of Success Ratio and Effective CPU Utilization. From analysis and experiments it reveals that the proposed algorithm is fast as well as efficient in both under loaded and overloaded conditions.