ACM Transactions on Autonomous and Adaptive Systems最新文献

Approaches that support the decision-making of self-adaptive and autonomous systems (SAS) often consider an idealized situation where (i) the system’s state is treated as fully observable by the monitoring infrastructure, and (ii) adaptation actions are assumed to have known, deterministic effects over the system. However, in practice, the system’s state may not be fully observable, and the adaptation actions may produce unexpected effects due to uncertain factors. This paper presents a novel probabilistic approach to quantify the uncertainty associated with the effects of adaptation actions on the state of a SAS. Supported by Bayesian inference and POMDPs (Partially-Observable Markov Decision Processes), these effects are translated into the satisfaction levels of the non-functional requirements (NFRs) to, therefore, drive the decision-making. The approach has been applied to two substantial case studies from the networking and Internet of Things (IoT) domains, using two different POMDP solvers. The results show that the approach delivers statistically significant improvements in supporting decision-making for SAS.

Various methods have been proposed in the literature for identifying subgoals in discrete reinforcement learning (RL) tasks. Once subgoals are discovered, task decomposition methods can be employed to improve the learning performance of agents. In this study, we classify prominent subgoal identification methods for discrete RL tasks in the literature into the following three categories: graph-based, statistics-based, and multi-instance learning (MIL)-based. As contributions, firstly, we introduce a new MIL-based subgoal identification algorithm called EMDD-RL and experimentally compare it with a previous MIL-based method. The previous approach adapts MIL’s Diverse Density (DD) algorithm, whereas our method considers Expected-Maximization Diverse Density (EMDD). The advantage of EMDD over DD is that it can yield more accurate results with less computation demand thanks to the expectation-maximization algorithm. EMDD-RL modifies some of the algorithmic steps of EMDD to identify subgoals in discrete RL problems. Secondly, we evaluate the methods in several RL tasks for the hyperparameter tuning overhead they incur. Thirdly, we propose a new RL problem called key-room and compare the methods for their subgoal identification performances in this new task. Experiment results show that MIL-based subgoal identification methods could be preferred to the algorithms of the other two categories in practice.

Self-governing hybrid societies are multi-agent systems where humans and machines interact by adapting to each other’s behaviour. Advancements in Artificial Intelligence (AI) have brought an increasing hybridisation of our societies, where one particular type of behaviour has become more and more prevalent, namely deception. Deceptive behaviour as the propagation of disinformation can have negative effects on a society’s ability to govern itself. However, self-governing societies have the ability to respond to various phenomena. In this paper we explore how they respond to the phenomenon of deception from an evolutionary perspective considering that agents have limited adaptation skills. Will hybrid societies fail to govern deceptive behaviour and reach a Tragedy of The Digital Commons? Or will they manage to avoid it through cooperation? How resilient are they against large-scale deceptive attacks? We provide a tentative answer to some of these questions through the lens of evolutionary agent-based modelling, based on the scientific literature on deceptive AI and public goods games.

Recently, machine learning (ML) has become a popular approach to support self-adaptation. ML has been used to deal with several problems in self-adaptation, such as maintaining an up-to-date runtime model under uncertainty and scalable decision-making. Yet, exploiting ML comes with inherent challenges. In this paper, we focus on a particularly important challenge for learning-based self-adaptive systems: drift in adaptation spaces. With adaptation space, we refer to the set of adaptation options a self-adaptive system can select from to adapt at a given time based on the estimated quality properties of the adaptation options. A drift of adaptation spaces originates from uncertainties, affecting the quality properties of the adaptation options. Such drift may imply that the quality of the system may deteriorate, eventually, no adaptation option may satisfy the initial set of adaptation goals, or adaptation options may emerge that allow enhancing the adaptation goals. In ML, such a shift corresponds to a novel class appearance, a type of concept drift in target data that common ML techniques have problems dealing with. To tackle this problem, we present a novel approach to self-adaptation that enhances learning-based self-adaptive systems with a lifelong ML layer. We refer to this approach as lifelong self-adaptation. The lifelong ML layer tracks the system and its environment, associates this knowledge with the current learning tasks, identifies new tasks based on differences, and updates the learning models of the self-adaptive system accordingly. A human stakeholder may be involved to support the learning process and adjust the learning and goal models. We present a general architecture for lifelong self-adaptation and apply it to the case of drift of adaptation spaces that affects the decision-making in self-adaptation. We validate the approach for a series of scenarios with a drift of adaptation spaces using the DeltaIoT exemplar.

Applications that are constrained by low-latency requirements can hardly be executed on cloud infrastructures, given the high network delay required to reach remote servers. Multi-access Edge Computing (MEC) is the reference architecture for executing applications on nodes that are located close to users (i.e., at the edge of the network). This way, the network overhead is reduced but new challenges emerge. The resources available on edge nodes are limited, workloads fluctuate since users can rapidly change location, and complex tasks are becoming widespread (e.g., machine learning inference). To address these issues, this article presents NEPTUNE, a serverless-based framework that automates the management of large-scale MEC infrastructures. In particular, NEPTUNE provides i) the placement of serverless functions on MEC nodes according to users’ location, ii) the resolution of resource contention scenarios by avoiding that single nodes be saturated, and iii) the dynamic allocation of CPUs and GPUs to meet foreseen execution times. To assess NEPTUNE, we built a prototype based on K3S, an edge-dedicated version of Kubernetes, and executed a comprehensive set of experiments. Results show that NEPTUNE obtains a significant reduction in terms of response time, network overhead, and resource consumption compared to five state-of-the-art solutions.