Auflistung nach Schlagwort "Edge computing"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelCatering to Real-Time Requirements of Cloud-Connected Mobile Manipulators(KI - Künstliche Intelligenz: Vol. 33, No. 2, 2019) Walter, Christoph; Scholle, Julian-Benedikt; Elkmann, NorbertIn this contribution, we explore real-time requirements of mobile manipulators, a class of intelligent robots, in the context of the ongoing fast-robotics ( https://de.fast-zwanzig20.de/industrie/fast-robotics/ ) project. The project aims at implementing such robots based on (edge-) cloud-services using wireless communication in order to make them more capable and efficient. Instead of trying to universally achieve hard real-time in such a system, we present a mixed real-time approach with an application centered fault tolerance scheme based on transition points and pre-computed alternate plans. We argue that deliberatively addressing uncertainties in timing is similarly important than handling uncertainties e.g. in perception for future intelligent robots.
- ZeitschriftenartikelNot All Doom and Gloom:ÿHow Energy-Intensive and Temporally Flexible Data Center Applications May Actually Promote Renewable Energy Sources (**encoding or data invalid**)(Business & Information Systems Engineering: Vol. 63, No. 3, 2021) Fridgen, Gilbert; Körner, Marc-Fabian; Walters, Steffen; Weibelzahl, MartinTo achieve a sustainable energy system, a further increase in electricity generation from renewable energy sources (RES) is imperative. However, the development and implementation of RES entail various challenges, e.g., dealing with grid stability issues due to RES? intermittency. Correspondingly, increasingly volatile and even negative electricity prices question the economic viability of RES-plants. To address these challenges, this paper analyzes how the integration of an RES-plant and a computationally intensive, energy-consuming data center (DC) can promote investments in RES-plants. An optimization model is developed that calculates the net present value (NPV) of an integrated energy system (IES) comprising an RES-plant and a DC, where the DC may directly consume electricity from the RES-plant. To gain applicable knowledge, this paper evaluates the developed model by means of two use-cases with real-world data, namely AWS computing instances for training Machine Learning algorithms and Bitcoin mining as relevant DCÿapplications. The results illustrate that for both cases the NPV of the IES compared to a stand-alone RES-plant increases, which may lead to a promotion of RES-plants. The evaluation also finds that the IES may be able to provide significant energy flexibility that can be used to stabilize the electricity grid. Finally, the IES may also help to reduce the carbon-footprint of new energy-intensive DC applications by directly consuming electricity from RES-plants. (**encoding or data invalid**)
- ZeitschriftenartikelA survey on time-sensitive resource allocation in the cloud continuum(it - Information Technology: Vol. 62, No. 5-6, 2020) Ramanathan, Saravanan; Shivaraman, Nitin; Suryasekaran, Seima; Easwaran, Arvind; Borde, Etienne; Steinhorst, SebastianArtificial Intelligence (AI) and Internet of Things (IoT) applications are rapidly growing in today’s world where they are continuously connected to the internet and process, store and exchange information among the devices and the environment. The cloud and edge platform is very crucial to these applications due to their inherent compute-intensive and resource-constrained nature. One of the foremost challenges in cloud and edge resource allocation is the efficient management of computation and communication resources to meet the performance and latency guarantees of the applications. Numerous research studies have been carried out to address this intricate problem. In this paper, the current state-of-the-art resource allocation techniques for the cloud continuum, in particular those that consider time-sensitive applications, are reviewed. Furthermore, we present the key challenges in the resource allocation problem for the cloud continuum, a taxonomy to classify the existing literature and the potential research gaps.