Pregled bibliografske jedinice broj: 833398
Sensors Definitions and Positioning for Load Balancing Algorithms
Sensors Definitions and Positioning for Load Balancing Algorithms // Proceedings of the 38th International Convention for Information and Communication Technology, Electronics and Microelectronics (MIPRO/CTI 2015)
Rijeka: Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2015. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 833398 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Sensors Definitions and Positioning for Load Balancing Algorithms
Autori
Radojević, Branko ; Žagar, Mario ; Golub, Ivana
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 38th International Convention for Information and Communication Technology, Electronics and Microelectronics (MIPRO/CTI 2015)
/ - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2015
Skup
38th International Convention for Information and Communication Technology, Electronics and Microelectronics (MIPRO/CTI 2015)
Mjesto i datum
Opatija, Hrvatska, 25.05.2015. - 29.05.2015
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
load balancing; sensors; definitions; positioning
Sažetak
Building a complex load balancing mechanism requires good knowledge of network and networking metrics, all parts of computer systems that participate in the service, and especially sensors and sensor metrics that are providing important inputs to the mechanism algorithm. It is essential to identify potential sensors that can be used together with their specific metrics, and to understand on what degree those sensors and metrics can and may influence decisions of load balancing algorithms. The analysis of potential candidates, expected, and observed data that those sensors are returning together with their correlations with final decisions will be presented in this paper. To have the right data, and to understand the crucial correlations is essential in building a new advanced load balancing algorithm that can proactively influence load balancing decisions or reactively change decision in handling critical situations.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb