Architectural Aspects of Self-Aware and Self-Expressive Computing Systems: From Psychology to Engineering

Abstract

A dvanced computing systems generally contain many heterogeneous subsystems, each with a local perspective and goal set, which interconnect in changing network topologies. The subsystems must interact with each other and with humans in ways that are difficult to understand and predict while robustly maintaining performance, reliability, and security even with unforeseen dynamics, such as system failures or changing goals.To meet these stringent requirements, computational systemsranging from robot swarms and personal music devices to Web services and sensor networks-must achieve sophisticated autonomous behavior by adapting themselves at runtime and through learning processes that enable ongoing self-change. Managing tradeoffs among conflicting local and global goals at runtime requires considerable awareness of both the system's current state and its environment. Yet researchers have only recently begun to understand the implications of selfawareness principles and how to translate them into system engineering. Consequently, there is no general methodology for architecting self-aware systems or for comparing their self-awareness capabilities.To address this need, we examined how human selfawareness can serve as a source of inspiration for a new notion of computational self-awareness and associated self-expression, and we developed a general framework for describing a computing system's self-awareness properties. As part of this work, we created a reference architecture, which we used to derive architectural patterns for RESEARCH FEATURE

A Review of Future and Ethical Perspectives of Robotics and AI

“…It could also be advantageous for multiple robots to share parts of their internally modeled behavior with each other (Winfield, 2017). Self-awareness regards either knowledge about one's self-private self-awareness-or the surrounding environment-public self-awareness (Lewis et al, 2015)-and is applicable across a number of different application areas (Lewis et al, 2016). The models can be organized in a hierarchical and distributed manner (Demiris and Khadhouri, 2006).…”

A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems

“…Such knowledge permits better reasoning about the system's adaptive behaviors. Consequently, self-awareness is often seen as the lowest level of abstraction of selfadaptivity [128], and thus it can improve the basic perceptions and self-adaptivity of a system [54,102,101,53]. Inspired from the psychology domain, Becker et al [34] have classified self-awareness of a computing system into the following general capabilities (they have used node to represent any conceptual part of a system being managed):…”

“…This means that, in the remaining 67% of the work, it is more difficult to capture more complex and advanced levels of knowledge, as evident by the fact that most work does not go beyond the basic stimulus-awareness. Indeed, studies in References [34,54,102,101,53] have found that, for self-aware and self-adaptive software systems in general, the absence of explicit consideration for the fine-grained representation of the knowledge in the architecture can result in, e.g., improper inclusion of unnecessary knowledge and/or missing important knowledge that can improve adaptation quality when developing autoscaling systems; 67% of studies that do not discuss knowledge at the architecture level implies that such an issue is often overlooked and remains unresolved in the SSCAS context, urging the need for further investigation. The challenge here lies in how we can systematically distinguish different levels of knowledge and how they can be built into SSCAS in a principal way.…”

An architecture for the autonomic curation of crowdsourced knowledge

“…It provides a well structured procedure to evaluate an architecture's fitness taking into account a set of non-dominant quality attributes (in the sense that improving one attribute will implicitly worsen another). ATAM has been successfully used for analysing software architectures in cloud computing [30], with a special focus on the security aspect [13], for investigating the design of service-oriented systems for serious games [8] as well as a starting point for bespoke approaches considering the impact of uncertainty on software requirements and architectures [29], the importance of enterprise information systems availability [33] or the sustainability of software architectures [50]. When applied to the Aviator domain, ATAM enabled the identification and management of the following factors.…”