This page has only limited features, please log in for full access.
Artificial intelligence (AI) has taken us by storm, helping us to make decisions in everything we do, even in finding our “true love” and the “significant other”. While 5G promises us high-speed mobile internet, 6G pledges to support ubiquitous AI services through next-generation softwarization, heterogeneity, and configurability of networks. The work on 6G is in its infancy and requires the community to conceptualize and develop its design, implementation, deployment, and use cases. Towards this end, this paper proposes a framework for Distributed AI as a Service (DAIaaS) provisioning for Internet of Everything (IoE) and 6G environments. The AI service is “distributed” because the actual training and inference computations are divided into smaller, concurrent, computations suited to the level and capacity of resources available with cloud, fog, and edge layers. Multiple DAIaaS provisioning configurations for distributed training and inference are proposed to investigate the design choices and performance bottlenecks of DAIaaS. Specifically, we have developed three case studies (e.g., smart airport) with eight scenarios (e.g., federated learning) comprising nine applications and AI delivery models (smart surveillance, etc.) and 50 distinct sensor and software modules (e.g., object tracker). The evaluation of the case studies and the DAIaaS framework is reported in terms of end-to-end delay, network usage, energy consumption, and financial savings with recommendations to achieve higher performance. DAIaaS will facilitate standardization of distributed AI provisioning, allow developers to focus on the domain-specific details without worrying about distributed training and inference, and help systemize the mass-production of technologies for smarter environments.
Nourah Janbi; Iyad Katib; Aiiad Albeshri; Rashid Mehmood. Distributed Artificial Intelligence-as-a-Service (DAIaaS) for Smarter IoE and 6G Environments. Sensors 2020, 20, 5796 .
AMA StyleNourah Janbi, Iyad Katib, Aiiad Albeshri, Rashid Mehmood. Distributed Artificial Intelligence-as-a-Service (DAIaaS) for Smarter IoE and 6G Environments. Sensors. 2020; 20 (20):5796.
Chicago/Turabian StyleNourah Janbi; Iyad Katib; Aiiad Albeshri; Rashid Mehmood. 2020. "Distributed Artificial Intelligence-as-a-Service (DAIaaS) for Smarter IoE and 6G Environments." Sensors 20, no. 20: 5796.
The increasing demand of the cloud services and with the emergence of many could service providers, the need for cloud federation is inevitable. In cloud federation, many could services providers are collaborating with each other to improve the resources usage, cost, quality of service they provide. To form this federation a management framework is required to facilitate the communication between these providers. This framework can be centralized or distributed, distributed Peer to Peer cloud federation improve extensibility, scalability and fault-tolerant. On the other hand, it is challenging in term of complexity, security and manageability of the federation. In this paper we propose a fully distributed P2P Cloud Federation (PPCF) architecture. PPCF provide a way to connect heterogenous cloud providers to share resources and improve the cloud elasticity. The architecture combines different software technologies to fulfil the cloud federation requirements.
Nourah Janbi. Peer to Peer Cloud Providers Federation. journal of King Abdulaziz University Computing and Information Technology Sciences 2019, 8, 59 -69.
AMA StyleNourah Janbi. Peer to Peer Cloud Providers Federation. journal of King Abdulaziz University Computing and Information Technology Sciences. 2019; 8 (1):59-69.
Chicago/Turabian StyleNourah Janbi. 2019. "Peer to Peer Cloud Providers Federation." journal of King Abdulaziz University Computing and Information Technology Sciences 8, no. 1: 59-69.
Peer-to-peer (P2P) file sharing networks are widely used by Internet users but due to their anonymity and self-organizational nature, they are often targeted by malicious users. Therefore, reputation systems are used to distinguish between good and malicious peers. Many reputation systems propose the use of the Bayesian model and it has proved to be effective for reputation calculation in a small, fully distributed system. This paper focuses on the distributed rank-based reputation system (DRank), one of the latest systems applying the Bayesian model in P2P streaming. DRank developers evaluated it on a small network with a maximum 200 nodes. In this paper, DRank is examined in a P2P file sharing system and on larger networks. This examination showed a drop in reputation propagation and a rise in the number of polluted files downloaded. Therefore, we propose a number of optimizations to DRank, such as unstructured reputation propagation, and two mechanisms of peer selection: (1) the first peer in the rank, and (2) randomly from a set of top ranked peers. For evaluation purposes, a simulator is built using a P2P simulator and DRank is examined with and without our proposed improvements. The experiments showed that our proposals improve DRank performance in preventing malicious peers from obtaining high reputation values.
Nourah Janbi; Milena Radenkovic. An enhanced Bayesian-based reputation system for P2P file sharing. 2017 Computing Conference 2017, 1247 -1252.
AMA StyleNourah Janbi, Milena Radenkovic. An enhanced Bayesian-based reputation system for P2P file sharing. 2017 Computing Conference. 2017; ():1247-1252.
Chicago/Turabian StyleNourah Janbi; Milena Radenkovic. 2017. "An enhanced Bayesian-based reputation system for P2P file sharing." 2017 Computing Conference , no. : 1247-1252.