Agent-based computing remains an active field of research with the goal of building (semi-)autonomous software for dynamic ecosystems. Today, this task should be realized using dedicated, specialized frameworks. Over almost 40 years, multiple agent platforms have been developed. While many of them have been “abandoned”, others remain active, and new ones are constantly being released. This contribution presents a historical perspective on the domain and an up-to-date review of the existing agent platforms. It aims to serve as a reference point for anyone interested in developing agent systems. Therefore, the main characteristics of the included agent platforms are summarized, and selected links to projects where they have been used are provided. Furthermore, the described platforms are divided into general-purpose platforms and those targeting specific application domains. The focus of the contribution is on platforms that can be judged as being under active development. Information about “historical platforms” and platforms with an unclear status is included in a dedicated website accompanying this work.

Modern systems often employ decentralised and distributed approaches. This can be attributed, among others, to the increasing complexity of system processes, which go beyond the capabilities of singular components. Additionally, with the growth in demand for system automation and high-level coordination, solutions belonging to the decentralised Artificial Intelligence and collaborative decision-making are often applied. It can be observed that these concerns fall within the domain of multi-agent systems. However, even though MAS concepts emerged more than 40 years ago, despite their obvious advantages and continuous efforts of the scientific community, agents remain rarely used in industrial-grade applications. In this context, the goal of this contribution is to analyse the reasons for the lack of adoption of agent solutions in the real world. During the analysis, all pertinent aspects of the modern software development life cycle are examined and compared to what is currently available in the agent system domain. Specifically, the study focuses on identifying gaps that are often overlooked when it comes to scientific applications of MAS, but are critical in terms of potential for large-scale system development in practice.

The increasing complexity of the Edge–Cloud Continuum (ECC), driven by the rapid expansion of the Internet of Things (IoT) and data-intensive applications, necessitates implementing innovative methods for automated and efficient system management. In this context, recent studies focused on the utilization of self-* capabilities that can be used to enhance system autonomy and increase operational proactiveness. Separately, anomaly detection and adaptive sampling techniques have been explored to optimize data transmission and improve systems’ reliability. The integration of those techniques within a single, lightweight, and extendable self-optimization module is the main subject of this contribution. The module was designed to be well suited for distributed systems, composed of highly resource-constrained operational devices (e.g., wearable health monitors, IoT sensors in vehicles, etc.), where it can be utilized to self-adjust data monitoring and enhance the resilience of critical processes. The focus is put on the implementation of two core mechanisms, derived from the current state-of-the-art: (1) density-based anomaly detection in real-time resource utilization data streams, and (2) a dynamic adaptive sampling technique, which employs Probabilistic Exponential Weighted Moving Average. The performance of the proposed module was validated using both synthetic and real-world datasets, which included a sample collected from the target infrastructure. The main goal of the experiments was to showcase the effectiveness of the implemented techniques in different, close to real-life scenarios. Moreover, the results of the performed experiments were compared with other state-of-the-art algorithms in order to examine their advantages and inherent limitations. With the emphasis put on frugality and real-time operation, this contribution offers a novel perspective on resource-aware autonomic optimization for next-generation ECC.

Cloud infrastructures operate in highly dynamic environments, and today, energy-focused optimization become crucial. Moreover, the concept of extended cloud infrastructure, which, among others, uses green energy, started to gain traction. This introduces a new level of dynamicity to the ecosystem, as “processing components” may “disappear” and “come back”, specifically in scenarios where the lack/return of green energy leads to shutting down/booting back servers at a given location. Considered use cases may involve introducing new types of resources (e.g., adding containers with server racks with “next-generation processors”). All such situations require the dynamic adaptation of “system knowledge”, i.e., runtime system adaptation. In this context, an agent-based digital twin of the extended green cloud infrastructure is proposed. Here, knowledge management is facilitated with an explainable Rule-Based Expert System, combined with Expression Languages. The tests were run using Extended Green Cloud Simulator, which allows the modelling of cloud infrastructures powered (partially) by renewable energy sources. Specifically, the work describes scenarios in which: (1) a new hardware resource is introduced in the system; (2) the system component changes its resource; and (3) system user changes energy-related preferences. The case study demonstrates how rules can facilitate control of energy efficiency with an example of an adaptable compromise between pricing and energy consumption.