ABSTRACT
Computing has undergone a significant transformation over the past two decades, shifting from a machine-based approach to a human-centric, virtually invisible service known as ubiquitous or pervasive computing. This change has been achieved by incorporating small embedded devices into a larger computational system, connected through networking and referred to as edge devices. When these devices are also connected to the Internet, they are generally named Internet-of-Thing (IoT) devices. Developing Machine Learning (ML) algorithms on these types of devices allows them to provide Artificial Intelligence (AI) inference functions such as computer vision, pattern recognition, etc. However, this capability is severely limited by the device's resource scarcity. Embedded devices have limited computational and power resources available while they must maintain a high degree of autonomy. While there are several published studies that address the computational weakness of these small systems-mostly through optimization and compression of neural networks- they often neglect the power consumption and efficiency implications of these techniques. This study presents power efficiency experimental results from the application of well-known and proven optimization methods using a set of well-known ML models. The results are presented in a meaningful manner considering the "real world" functionality of devices and the provided results are compared with the basic "idle" power consumption of each of the selected systems. Two different systems with completely different architectures and capabilities were used providing us with results that led to interesting conclusions related to the power efficiency of each architecture.
ABSTRACT
The provision of high data rate services to mobile users combined with improved quality of experience (i.e., zero latency multimedia content) drives technological evolution towards the design and implementation of fifth generation (5G) broadband wireless networks. To this end, a dynamic network design approach is adopted whereby network topology is configured according to service demands. In parallel, many private companies are interested in developing their own 5G networks, also referred to as non-public networks (NPNs), since this deployment is expected to leverage holistic production monitoring and support critical applications. In this context, this paper introduces a 5G NPN architectural approach, supporting among others various key enabling technologies, such as cell densification, disaggregated RAN with open interfaces, edge computing, and AI/ML-based network optimization. In the same framework, potential applications of our proposed approach in real world scenarios (e.g., support of mission critical services and computer vision analytics for emergencies) are described. Finally, scalability issues are also highlighted since a deployment framework of our architectural design in an additional real-world scenario related to Industry 4.0 (smart manufacturing) is also analyzed.
Subject(s)
Social Networking , Wireless Technology , Multimedia , TechnologyABSTRACT
The digitization of manufacturing industry has led to leaner and more efficient production, under the Industry 4.0 concept. Nowadays, datasets collected from shop floor assets and information technology (IT) systems are used in data-driven analytics efforts to support more informed business intelligence decisions. However, these results are currently only used in isolated and dispersed parts of the production process. At the same time, full integration of artificial intelligence (AI) in all parts of manufacturing systems is currently lacking. In this context, the goal of this manuscript is to present a more holistic integration of AI by promoting collaboration. To this end, collaboration is understood as a multi-dimensional conceptual term that covers all important enablers for AI adoption in manufacturing contexts and is promoted in terms of business intelligence optimization, human-in-the-loop and secure federation across manufacturing sites. To address these challenges, the proposed architectural approach builds on three technical pillars: (1) components that extend the functionality of the existing layers in the Reference Architectural Model for Industry 4.0; (2) definition of new layers for collaboration by means of human-in-the-loop and federation; (3) security concerns with AI-powered mechanisms. In addition, system implementation aspects are discussed and potential applications in industrial environments, as well as business impacts, are presented.
