Using Neural Networks in Reliability Prediction
IEEE Software
Trio: enabling sustainable and scalable outdoor wireless sensor network deployments
Proceedings of the 5th international conference on Information processing in sensor networks
An opportunistic reconfiguration strategy for environmentally powered devices
Proceedings of the 3rd conference on Computing frontiers
Harvesting aware power management for sensor networks
Proceedings of the 43rd annual Design Automation Conference
Design considerations for solar energy harvesting wireless embedded systems
IPSN '05 Proceedings of the 4th international symposium on Information processing in sensor networks
Perpetual environmentally powered sensor networks
IPSN '05 Proceedings of the 4th international symposium on Information processing in sensor networks
Real-Time Scheduling with Regenerative Energy
ECRTS '06 Proceedings of the 18th Euromicro Conference on Real-Time Systems
Everlast: long-life, supercapacitor-operated wireless sensor node
Proceedings of the 2006 international symposium on Low power electronics and design
Adaptive power management in energy harvesting systems
Proceedings of the conference on Design, automation and test in Europe
Power management in energy harvesting sensor networks
ACM Transactions on Embedded Computing Systems (TECS) - Special Section LCTES'05
ISLPED '07 Proceedings of the 2007 international symposium on Low power electronics and design
An efficient solar energy harvester for wireless sensor nodes
Proceedings of the conference on Design, automation and test in Europe
Robust and low complexity rate control for solar powered sensors
Proceedings of the conference on Design, automation and test in Europe
Solar harvest prediction supported by cloud cover forecasts
Proceedings of the 1st International Workshop on Energy Neutral Sensing Systems
| Hi-index | 0.00 |
Small size photovoltaic modules can harvest enough energy to power many personal devices and wireless sensor nodes. The prediction of solar energy intake is possible thanks to the periodical availability of the sunlight and its cyclic behavior. Thus, smart and innovative power management strategies can take advantage from intake prediction algorithms to optimize the energy usage by keeping the system in low power state as long as possible. On the other hand, very accurate predictions need time and energy because of complex calculations, thus an algorithm that can provide the optimal trade-off between computational effort and accuracy is a breakthrough for systems with tight power constraints. In this paper we introduce an innovative, efficient and reliable solar prediction algorithm, the weather conditioned moving average (WCMA). The algorithm has been further enhanced to increase performance using a phase displacement regulator (PDR) which reduces the average error to less than 9.2% at a minimum energy cost. The proposed new algorithm compares favorably with several competing approaches.