Alessandro Tundo

Alessandro Tundo, Marco Mobilio, Shashikant Ilager et al.

The advent of edge devices dedicated to machine learning tasks enabled the execution of AI-based applications that efficiently process and classify the data acquired by the resource-constrained devices populating the Internet of Things. The proliferation of such applications (e.g., critical monitoring in smart cities) demands new strategies to make these systems also sustainable from an energetic point of view. In this paper, we present an energy-aware approach for the design and deployment of self-adaptive AI-based applications that can balance application objectives (e.g., accuracy in object detection and frames processing rate) with energy consumption. We address the problem of determining the set of configurations that can be used to self-adapt the system with a meta-heuristic search procedure that only needs a small number of empirical samples. The final set of configurations are selected using weighted gray relational analysis, and mapped to the operation modes of the self-adaptive application. We validate our approach on an AI-based application for pedestrian detection. Results show that our self-adaptive application can outperform non-adaptive baseline configurations by saving up to 81\% of energy while loosing only between 2% and 6% in accuracy.

Daniel May, Alessandro Tundo, Shashikant Ilager et al.

The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge and cloud devices, identifying the most suitable split layer and hardware configurations is a non-trivial task. This process is in fact hindered by the large configuration space, the non-linear dependencies between software and hardware parameters, the heterogeneous hardware and energy characteristics, and the dynamic workload conditions. To overcome this challenge, we propose DynaSplit, a two-phase framework that dynamically configures parameters across both software (i.e., split layer) and hardware (e.g., accelerator usage, CPU frequency). During the Offline Phase, we solve a multi-objective optimization problem with a meta-heuristic approach to discover optimal settings. During the Online Phase, a scheduling algorithm identifies the most suitable settings for an incoming inference request and configures the system accordingly. We evaluate DynaSplit using popular pre-trained NNs on a real-world testbed. Experimental results show a reduction in energy consumption up to 72% compared to cloud-only computation, while meeting ~90% of user request's latency threshold compared to baselines.

Oliviero Riganelli, Paolo Saltarel, Alessandro Tundo et al.

Hierarchical Temporal Memory (HTM) is an unsupervised learning algorithm inspired by the features of the neocortex that can be used to continuously process stream data and detect anomalies, without requiring a large amount of data for training nor requiring labeled data. HTM is also able to continuously learn from samples, providing a model that is always up-to-date with respect to observations. These characteristics make HTM particularly suitable for supporting online failure prediction in cloud systems, which are systems with a dynamically changing behavior that must be monitored to anticipate problems. This paper presents the first systematic study that assesses HTM in the context of failure prediction. The results that we obtained considering 72 configurations of HTM applied to 12 different types of faults introduced in the Clearwater cloud system show that HTM can help to predict failures with sufficient effectiveness (F-measure = 0.76), representing an interesting practical alternative to (semi-)supervised algorithms.

Alessandro Tundo, Chiara Castelnovo, Marco Mobilio et al.

Systems of systems are highly dynamic software systems that require flexible monitoring solutions to be observed and controlled. Indeed, operators have to frequently adapt the set of collected indicators according to changing circumstances, to visualize the behavior of the monitored systems and timely take actions, if needed. Unfortunately, dashboard systems are still quite cumbersome to configure and adapt to a changing set of indicators that must be visualized. This paper reports our initial effort towards the definition of an automatic dashboard generation process that exploits metamodel layouts to create a full dashboard from a set of indicators selected by operators.

Marco Mobilio, Matteo Orrù, Oliviero Riganelli et al.

Cloud systems are complex, large, and dynamic systems whose behavior must be continuously analyzed to timely detect misbehaviors and failures. Although there are solutions to flexibly monitor cloud systems, cost-effectively controlling the anomaly detection logic is still a challenge. In particular, cloud operators may need to quickly change the types of detected anomalies and the scope of anomaly detection, for instance based on observations. This kind of intervention still consists of a largely manual and inefficient ad-hoc effort. In this paper, we present Anomaly Detection as-a-Service (ADaaS), which uses the same as-a-service paradigm often exploited in cloud systems to declarative control the anomaly detection logic. Operators can use ADaaS to specify the set of indicators that must be analyzed and the types of anomalies that must be detected, without having to address any operational aspect. Early results with lightweight detectors show that the presented approach is a promising solution to deliver better control of the anomaly detection logic.

Matteo Orrù, Marco Mobilio, Anas Shatnawi et al.

Smart Cities are future urban aggregations, where a multitude of heterogeneous systems and IoT devices interact to provide a safer, more efficient, and greener environment. The vision of smart cities is adapting accordingly to the evolution of software and IoT based services. The current trend is not to have a big comprehensive system, but a plethora of small, well integrated systems that interact one with each other. Monitoring these kinds of systems is challenging for a number of reasons.