Real-Time Reliability Monitoring on Edge Computing: a Systematic Mapping

Scenario: System reliability monitoring focuses on determining the level at which the system works as expected (under certain conditions and over time) based on requirements. The edge computing environment is heterogeneous and distributed. It may lack central control due to the scope, number, and vo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Informatika i avtomatizaciâ (Online) 2023-11, Vol.22 (6), p.1243-1295
Hauptverfasser: Diván, Mario José, Shchemelinin, Dmitry, Carranza, Marcos E., Martinez-Spessot, Cesar Ignacio, Buinevich, Mikhail
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Scenario: System reliability monitoring focuses on determining the level at which the system works as expected (under certain conditions and over time) based on requirements. The edge computing environment is heterogeneous and distributed. It may lack central control due to the scope, number, and volume of stakeholders. Objective: To identify and characterize the Real-time System Reliability Monitoring strategies that have considered Artificial Intelligence models for supporting decision-making processes. Methodology: An analysis based on the Systematic Mapping Study was performed on December 14, 2022. The IEEE and Scopus databases were considered in the exploration. Results: 50 articles addressing the subject between 2013 and 2022 with growing interest. The core use of this technology is related to networking and health areas, articulating Body sensor networks or data policies management (collecting, routing, transmission, and workload management) with edge computing. Conclusions: Real-time Reliability Monitoring in edge computing is ongoing and still nascent. It lacks standards but has taken importance and interest in the last two years. Most articles focused on Push-based data collection methods for supporting centralized decision-making strategies. Additionally, to networking and health, it concentrated and deployed on industrial and environmental monitoring. However, there are multiple opportunities and paths to walk to improve it. E.g., data interoperability, federated and collaborative decision-making models, formalization of the experimental design for measurement process, data sovereignty, organizational memory to capitalize previous knowledge (and experiences), calibration and recalibration strategies for data sources.
ISSN:2713-3192
2713-3206
DOI:10.15622/ia.22.6.1