The 'Compute Continuum' (CC), which encom-passes and harmonizes the Edge, Fog, and Cloud computing paradigms, emerges as an opportunity for an efficient deployment and adoption of innovative services ranging from eHealth to virtual reality. However, the effective management of services all along the CC presents the challenge of service deployment in relatively resource scarce or poorly connected locations. We argue that CC environments call for novel resource management strategies with a holistic perspective of the whole computing ecosystem, that also consider the QoS reconfiguration and tuning of services in the resource reallocation process. Tackling these challenges, we introduce VOICE, a cutting-edge platform designed for service management in CC ecosystems. Thanks to a Value of Information (Vol)-based technique that emphasizes the significance of data filtering, VOICE supports dynamic service components allocation throughout the CC. To evaluate the choice of VoI as enabling-technology for VOICE, we leverage computational intelligence (CI) approaches and compare it with more traditional strategies (e.g. maximization of satisfied requests or latency minimization). Final results show how VoI can be a valuable proposal to optimize the usage of resource scarcity that characterizes CC environments.
VOICE: Value-of-Information for Compute Continuum Ecosystems
Zaccarini, Mattia;Fazio, Maria;Poltronieri, Filippo;Stefanelli, Cesare;Tortonesi, Mauro
2024
Abstract
The 'Compute Continuum' (CC), which encom-passes and harmonizes the Edge, Fog, and Cloud computing paradigms, emerges as an opportunity for an efficient deployment and adoption of innovative services ranging from eHealth to virtual reality. However, the effective management of services all along the CC presents the challenge of service deployment in relatively resource scarce or poorly connected locations. We argue that CC environments call for novel resource management strategies with a holistic perspective of the whole computing ecosystem, that also consider the QoS reconfiguration and tuning of services in the resource reallocation process. Tackling these challenges, we introduce VOICE, a cutting-edge platform designed for service management in CC ecosystems. Thanks to a Value of Information (Vol)-based technique that emphasizes the significance of data filtering, VOICE supports dynamic service components allocation throughout the CC. To evaluate the choice of VoI as enabling-technology for VOICE, we leverage computational intelligence (CI) approaches and compare it with more traditional strategies (e.g. maximization of satisfied requests or latency minimization). Final results show how VoI can be a valuable proposal to optimize the usage of resource scarcity that characterizes CC environments.I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
