arXiv subjects

Yehia Elkhatib

Publications and source records attributed to Yehia Elkhatib.

31 records · Page 2Linked to original sources

arXiv2018

Cloud Brokerage: A Systematic Survey

Background: The proliferation of cloud providers and provisioning levels has opened a space for cloud brokerage services. Brokers intermediate between cloud customers and providers to assist the customer in selecting the most suitable cloud service, helping to manage the dimensionality, heterogeneity, and uncertainty associated with cloud services. Objective: This paper identifies and classifies approaches to realise cloud brokerage. By doing so, this paper presents an understanding of the state of the art and a novel taxonomy to characterise cloud brokers. Method: We conducted a systematic literature survey to compile studies related to cloud brokerage and explore how cloud brokers are engineered. We analysed the studies from multiple perspectives, such as motivation, functionality, engineering approach, and evaluation methodology. Results: The survey resulted in a knowledge base of current proposals for realising cloud brokers. The survey identified surprising differences between the studies' implementations, with engineering efforts directed at combinations of market-based solutions, middlewares, toolkits, algorithms, semantic frameworks, and conceptual frameworks. Conclusion: Our comprehensive meta-analysis shows that cloud brokerage is still a formative field. There is no doubt that progress has been achieved in the field but considerable challenges remain to be addressed. This survey identifies such challenges and directions for future research.

cs.DC↗

arXiv2018

Adaptive Selection of Deep Learning Models on Embedded Systems

The recent ground-breaking advances in deep learning networks ( DNNs ) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the computation into the cloud is often infeasible due to privacy concerns, high latency, or the lack of connectivity. As such, there is a critical need to find a way to effectively execute the DNN models locally on the devices. This paper presents an adaptive scheme to determine which DNN model to use for a given input, by considering the desired accuracy and inference time. Our approach employs machine learning to develop a predictive model to quickly select a pre-trained DNN to use for a given input and the optimization constraint. We achieve this by first training off-line a predictive model, and then use the learnt model to select a DNN model to use for new, unseen inputs. We apply our approach to the image classification task and evaluate it on a Jetson TX2 embedded deep learning platform using the ImageNet ILSVRC 2012 validation dataset. We consider a range of influential DNN models. Experimental results show that our approach achieves a 7.52% improvement in inference accuracy, and a 1.8x reduction in inference time over the most-capable single DNN model.

cs.PF↗

arXiv2018

Price and Performance of Cloud-hosted Virtual Network Functions: Analysis and Future Challenges

The concept of Network Function Virtualization (NFV) has been introduced as a new paradigm in the recent few years. NFV offers a number of benefits including significantly increased maintainability and reduced deployment overhead. Several works have been done to optimize deployment (also called embedding) of virtual network functions (VNFs). However, no work to date has looked into optimizing the selection of cloud instances for a given VNF and its specific requirements. In this paper, we evaluate the performance of VNFs when embedded on different Amazon EC2 cloud instances. Specifically, we evaluate three VNFs (firewall, IDS, and NAT) in terms of arrival packet rate, resources utilization, and packet loss. Our results indicate that performance varies across instance types, departing from the intuition of "you get what you pay for" with cloud instances. We also find out that CPU is the critical resource for the tested VNFs, although their peak packet processing capacities differ considerably from each other. Finally, based on the obtained results, we identify key research challenges related to VNF instance selection and service chain provisioning.

cs.NI↗

arXiv2018

Same Same, but Different: A Descriptive Differentiation of Intra-cloud Iaas Services

Users of cloud computing are overwhelmed with choice, even within the services offered by one provider. As such, many users select cloud services based on description alone. We investigate the degree to which such strategy is optimal. In this quantitative study, we investigate the services of 2 of major IaaS providers. We use 2 representative applications to obtain longitudinal observations over 7 days of the week and over different times of the day, totalling over 14,000 executions. We give evidence of significant variations of performance offered within IaaS services, calling for brokers to use automated and adaptive decision making processes with means for incorporating expressive user constraints.

cs.DC↗

arXiv2017

Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges

While machine learning and artificial intelligence have long been applied in networking research, the bulk of such works has focused on supervised learning. Recently there has been a rising trend of employing unsupervised machine learning using unstructured raw network data to improve network performance and provide services such as traffic engineering, anomaly detection, Internet traffic classification, and quality of service optimization. The interest in applying unsupervised learning techniques in networking emerges from their great success in other fields such as computer vision, natural language processing, speech recognition, and optimal control (e.g., for developing autonomous self-driving cars). Unsupervised learning is interesting since it can unconstrain us from the need of labeled data and manual handcrafted feature engineering thereby facilitating flexible, general, and automated methods of machine learning. The focus of this survey paper is to provide an overview of the applications of unsupervised learning in the domain of networking. We provide a comprehensive survey highlighting the recent advancements in unsupervised learning techniques and describe their applications for various learning tasks in the context of networking. We also provide a discussion on future directions and open research issues, while also identifying potential pitfalls. While a few survey papers focusing on the applications of machine learning in networking have previously been published, a survey of similar scope and breadth is missing in literature. Through this paper, we advance the state of knowledge by carefully synthesizing the insights from these survey papers while also providing contemporary coverage of recent advances.

cs.NI↗

arXiv2017

Fake it till you make it: Fishing for Catfishes

Many adult content websites incorporate social networking features. Although these are popular, they raise significant challenges, including the potential for users to "catfish", i.e., to create fake profiles to deceive other users. This paper takes an initial step towards automated catfish detection. We explore the characteristics of the different age and gender groups, identifying a number of distinctions. Through this, we train models based on user profiles and comments, via the ground truth of specially verified profiles. Applying our models for age and gender estimation of unverified profiles, we identify 38% of profiles who are likely lying about their age, and 25% who are likely lying about their gender. We find that women have a greater propensity to catfish than men. Further, whereas women catfish select from a wide age range, men consistently lie about being younger. Our work has notable implications on operators of such online social networks, as well as users who may worry about interacting with catfishes.

cs.SI↗

arXiv2017

On Using Micro-Clouds to Deliver the Fog

Cloud computing has demonstrated itself to be a scalable and cost-efficient solution for many real-world applications. However, its modus operandi is not ideally suited to resource-constrained environments that are characterized by limited network bandwidth and high latencies. With the increasing proliferation and sophistication of edge devices, the idea of fog computing proposes to offload some of the computation to the edge. To this end, micro-clouds---which are modular and portable assemblies of small single-board computers---have started to gain attention as infrastructures to support fog computing by offering isolated resource provisioning at the edge in a cost-effective way. We investigate the feasibility and readiness of micro-clouds for delivering the vision of fog computing. Through a number of experiments, we showcase the potential of micro-clouds formed by collections of Raspberry Pi computers to host a range of fog-related applications, particularly for locations where there is limited network bandwidths and long latencies.

cs.DC↗

arXiv2016

Charting an Intent Driven Network

The current strong divide between applications and the network control plane is desirable for many reasons; but a downside is that the network is kept in the dark regarding the ultimate purposes and intentions of applications and, as a result, is unable to optimize for these. An alternative approach, explored in this paper, is for applications to declare to the network their abstract intents and assumptions; e.g. "this is a Tweet", or "this application will run within a local domain". Such an enriched semantic has the potential to enable the network better to fulfill application intent, while also helping optimize network resource usage across applications. We refer to this approach as 'intent driven networking' (IDN), and we sketch an incrementally-deployable design to serve as a stepping stone towards a practical realization of the IDN concept within today's Internet.

cs.NI↗

arXiv2016

Defining Cross-Cloud Systems

Recent years have seen an increasing number of cross-cloud architectures, i.e. systems that span across cloud provisioning boundaries. However, the cloud computing world still lacks any standards in terms of programming interfaces, which has a knock-on effect on the costs associated with interoperability and severely limits the flexibility and portability of applications and virtual infrastructures. This paper outlines the different types of cross-cloud systems, and the associated design decisions.

cs.DC↗

arXiv2016

Daleel: Simplifying Cloud Instance Selection Using Machine Learning

Decision making in cloud environments is quite challenging due to the diversity in service offerings and pricing models, especially considering that the cloud market is an incredibly fast moving one. In addition, there are no hard and fast rules, each customer has a specific set of constraints (e.g. budget) and application requirements (e.g. minimum computational resources). Machine learning can help address some of the complicated decisions by carrying out customer-specific analytics to determine the most suitable instance type(s) and the most opportune time for starting or migrating instances. We employ machine learning techniques to develop an adaptive deployment policy, providing an optimal match between the customer demands and the available cloud service offerings. We provide an experimental study based on extensive set of job executions over a major public cloud infrastructure.

cs.DC↗

arXiv2015

Does the Internet deserve everybody?

There has been a long standing tradition amongst developed nations of influencing, both directly and indirectly, the activities of developing economies. Behind this is one of a range of aims: building/improving living standards, bettering the social status of recipient communities, etc. In some cases, this has resulted in prosperous relations, yet often this has been seen as the exploitation of a power position or a veneer for other activities (e.g. to tap into new emerging markets). In this paper, we explore whether initiatives to improve Internet connectivity in developing regions are always ethical. We draw a list of issues that would aid in formulating Internet initiatives that are ethical, effective, and sustainable.

cs.CY↗

arXiv2014

The Effect of Network and Infrastructural Variables on SPDY's Performance

HTTP is a successful Internet technology on top of which a lot of the web resides. However, limitations with its current specification, i.e. HTTP/1.1, have encouraged some to look for the next generation of HTTP. In SPDY, Google has come up with such a proposal that has growing community acceptance, especially after being adopted by the IETF HTTPbis-WG as the basis for HTTP/2.0. SPDY has the potential to greatly improve web experience with little deployment overhead. However, we still lack an understanding of its true potential in different environments. This paper seeks to resolve these issues, offering a comprehensive evaluation of SPDY's performance using extensive experiments. We identify the impact of network characteristics and website infrastructure on SPDY's potential page loading benefits, finding that these factors are decisive for SPDY and its optimal deployment strategy. Through this, we feed into the wider debate regarding HTTP/2.0, exploring the key aspects that impact the performance of this future protocol.

cs.NI↗

arXiv2013

Experiences of Using a Hybrid Cloud to Construct an Environmental Virtual Observatory

Environmental science is often fragmented: data is collected using mismatched formats and conventions, and models are misaligned and run in isolation. Cloud computing offers a lot of potential in the way of resolving such issues by supporting data from different sources and at various scales, by facilitating the integration of models to create more sophisticated software services, and by providing a sustainable source of suitable computational and storage resources. In this paper, we highlight some of our experiences in building the Environmental Virtual Observatory pilot (EVOp), a tailored cloud-based infrastructure and associated web-based tools designed to enable users from different backgrounds to access data concerning different environmental issues. We review our architecture design, the current deployment and prototypes. We also reflect on lessons learned. We believe that such experiences are of benefit to other scientific communities looking to assemble virtual observatories or similar virtual research environments.

cs.DC↗