Researchers and IT companies have proposed in recent years the use of new hybrid edge/cloud solutions to efficiently process the huge amounts of data produced by IoT devices. In fact, edge combined with cloud computing is used in different application scenarios, such as that of autonomous vehicles, which often require low latency, energy saving, privacy protection, and scalable services. Specifically, edge computing is useful in managing tasks that require real-time analysis and low response times, such as driving assistance, collision avoidance and road sign recognition. Instead, the use of the cloud is convenient for tasks that require a lot of resources and access to large data sets, such as diagnostic data collection and analysis, routing, and targeted advertising. Designing and testing edge/cloud architectures to support autonomous vehicles are still open issues due to their large-scale, heterogeneity, and complexity. In this chapter, we analyze how edge/cloud solutions can be exploited for efficiently managing tasks related to autonomous vehicle driving. In particular, through a simulation-based approach, we demonstrate that these solutions are capable of providing great performance benefits in support of autonomous vehicle systems, especially as the number of vehicles and computing nodes increase.
Hybrid edge/cloud solutions for supporting autonomous vehicles
Belcastro L.;Marozzo F.;Orsino A.
2023-01-01
Abstract
Researchers and IT companies have proposed in recent years the use of new hybrid edge/cloud solutions to efficiently process the huge amounts of data produced by IoT devices. In fact, edge combined with cloud computing is used in different application scenarios, such as that of autonomous vehicles, which often require low latency, energy saving, privacy protection, and scalable services. Specifically, edge computing is useful in managing tasks that require real-time analysis and low response times, such as driving assistance, collision avoidance and road sign recognition. Instead, the use of the cloud is convenient for tasks that require a lot of resources and access to large data sets, such as diagnostic data collection and analysis, routing, and targeted advertising. Designing and testing edge/cloud architectures to support autonomous vehicles are still open issues due to their large-scale, heterogeneity, and complexity. In this chapter, we analyze how edge/cloud solutions can be exploited for efficiently managing tasks related to autonomous vehicle driving. In particular, through a simulation-based approach, we demonstrate that these solutions are capable of providing great performance benefits in support of autonomous vehicle systems, especially as the number of vehicles and computing nodes increase.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.