Intelligent management message routing in ubiquitous sensor networks
ICCCI'11 Proceedings of the Third international conference on Computational collective intelligence: technologies and applications - Volume Part I
Intelligent ubiquitous sensor network for agricultural and livestock farms
ICA3PP'11 Proceedings of the 11th international conference on Algorithms and architectures for parallel processing - Volume Part II
Genetic algorithm-based charging task scheduler for electric vehicles in smart transportation
ACIIDS'12 Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part I
Time Synchronization Errors in Loosely Coupled GPS-Aided Inertial Navigation Systems
IEEE Transactions on Intelligent Transportation Systems
| Hi-index | 0.00 |
Upon the ubiquitous sensor network capable of deciding control actions by a sophisticated inference engine, this paper designs an actuator controller which coordinates the actuator operations over the multiple farms. Basically, not beginning tasks as soon as they get triggered, local schedulers determine the operation plan according to genetic algorithms, for the sake of reducing peak power consumption for the given scheduling window. For global scheduling, each local scheduler retrieves the current load information maintained in the coordinator, runs its own schedule, and finally sends to the coordinator. The fitness function gives penalty to the allocation which assigns much power to the heavily loaded time slots. The procedure reduces the peak load by up to 22.8 % for the given task set. Moreover, all schedules are not necessarily run with tight concurrency control. Our simulation shows that 40 % of schedulers can run in parallel just with negligible performance loss.