Machine learning (ML)-enabled systems like autonomous driving systems (ADSs) face challenges meeting safety and performance requirements in diverse environments, especially in resource-constrained, latency-sensitive edge-cloud settings. These challenges often arise from the ML models’ limitations, including poor generalization to unseen conditions. Static ML models often struggle to generalize to unseen scenarios, particularly under the latency and resource constraints of edge-cloud infrastructure. Adaptive algorithms using ML system switching have been proposed, but existing approaches frequently lack generalizability, support for common black-box systems, and effective use of distributed edge-cloud resources. This paper presents a novel adaptive ML-enabled edge-cloud system framework to address these shortcomings. Our framework combines cloud-based pre-runtime analysis, which leverages simulation for behavioral understanding and scenario-to-system mapping, with collaborative edge-cloud runtime adaptation featuring dynamic ML model switching. It supports black-box systems and aims to balance safety and efficiency by utilizing appropriate edge and cloud resources situationally. Preliminary CARLA-based evaluation of the edge runtime component suggests our framework can potentially improve the safety-efficiency trade-off compared to single-model ADSs in some scenarios. Moreover, extensive experiments using the MetaDrive simulator with 100,000 randomized driving scenarios demonstrate that the adaptive system improves safety by 2.6% while doubling computational efficiency compared to a single-model baseline. These results validate the framework’s scalability and the feasibility of data-driven scenario–system mapping for adaptive ML-enabled autonomous systems operating across edge and cloud environments.

With the increasing number of Web of Things devices, the network and processing delays in the cloud have also increased. As a solution, fog computing has emerged, placing computational resources closer to the user to lower the communication overhead and congestion in the cloud. In fog computing systems, microservices are deployed as containers, which require an orchestration tool like Kubernetes to support service discovery, placement, and recovery. A key challenge in the orchestration of microservices is automatically scaling the microservices in case of an unpredictable burst of load. In cloud computing, a centralized autoscaler can monitor the deployed microservice instances and make scaling actions based on the monitored metric values. However, monitoring an increasing number of microservices in fog computing can cause excessive network overhead and thereby delay the time to scaling action. We propose DESA, a fully DEcentralized Self-adaptive Autoscaler through which microservice instances make their own scaling decisions, cloning or terminating themselves through self-monitoring. We evaluate DESA in a simulated fog computing environment with different numbers of fog nodes. Furthermore, we conduct a case study with the 1998 World Cup website access log, examining DESA’s performance in a realistic scenario. The results show that DESA successfully reduces the scaling reaction time in large-scale fog computing systems compared to the centralized approach. Moreover, DESA resulted in a similar maximum number of instances and lower average CPU utilization during bursts of load.

Abstract Proactive adaptation, in which the adaptation for a system’s reliable goal achievement is performed by predicting changes in the environment, is considered as an effective alternative to reactive adaptation, in which adaptation is performed after observing changes. When predicting the environmental changes, the prediction may be uncertain, so it is necessary to verify and confirm an adaptation’s consequences before execution. To resolve the uncertainty, probabilistic model checking (PMC) has been utilized for verification of adaptation tactics’ effects on the goal of a self-adaptive system (SAS). However, PMC-based approaches have limitations on the state-explosion problem of complex SAS model verification and the modeling languages supported by the model checkers. In this paper, to overcome the limitations of the PMC-based approaches, we propose an efficient Proactive Adaptation approach based on STAtistical model checking (PASTA). Our approach allows SASs to mitigate the uncertainty of the future environment, faster than the PMC-based approach, by producing statistically sufficient samples for verification of adaptation tactics based on statistical model checking (SMC) algorithms. We provide algorithmic processes, a reference architecture, and an open-source implementation skeleton of PASTA for engineers to apply it for SAS development. We evaluate PASTA on two SASs using actual data and show that PASTA is efficient comparing to the PMC-based approach. We also provide a comparative analysis of the advantages and disadvantages of PMC- and SMC-based proactive adaptation to guide engineers’ decision-making for SAS development.