A neuro-fuzzy fan speed controller for dynamic thermal management of multi-core processors
Abad, Javad Mohebbi Najm; Salami, Bagher; Noori, Hamid; Soleimani, Ali; Madipour, Farhad
Citation:Abad, J. M. N. ; Salami, B. ; Noori, H. ; Soleimani, A. ; Mehdipour, F. (2014, May). A Neuro-Fuzzy Fan Speed Controller for Dynamic Thermal Management of Multi-core Process. Association for Computing Machinery (ACM) (Ed.), CF '14 Proceedings of the 11th ACM Conference on Computing Frontiers (pp.29-33).
Permanent link to Research Bank record:http://hdl.handle.net/10652/3815
Cooling equipments is a thermal management technique that reduces the thermal resistance of the heat sink without any performance degradation. However, higher fan speed produces a lower thermal resistance, but at the expense of higher power consumption. Our proposed Neuro-Fuzzy fan controller (NFSC), minimizes fan power consumption while avoiding the temperature increase above a certain threshold. The experimental results indicate that our proposed model can significantly decrease the average fan power with negligible temperature overhead compared to the traditional fan controller.