Processing high-speed big data streams is one of the most challenging tasks in machine learning nowadays. To deal withthese unbounded and massive amounts of data, highly efficient methods that continuously update the...
详细信息
ISBN:
(纸本)9781785616525
Processing high-speed big data streams is one of the most challenging tasks in machine learning nowadays. To deal withthese unbounded and massive amounts of data, highly efficient methods that continuously update their structure are required. this paper aims at presenting a new incremental and distributed lazy classifier, and a distributed instance selection technique that efficiently process real-world data streams. Both algorithms have been implemented in a single system by using the Apache Spark platform. thanks to this original design, the high computational requirements of standard lazy classifiers have been alleviated. A thorough experimental framework has been conducted on a set of big datasets, both artificial and real. Our study show the usefulness of our solutions and show that casebased reasoning can perform as a competitive option in largescale streaming environments.
Elastic scaling of event stream processing systems has gained significant attention recently due to the prevalence of cloud computing technologies. We investigate on the complexities associated with elastic scaling of...
详细信息
ISBN:
(纸本)9781450344043
Elastic scaling of event stream processing systems has gained significant attention recently due to the prevalence of cloud computing technologies. We investigate on the complexities associated with elastic scaling of an event processing system in a private/public cloud scenario. We develop an Elastic Switching Mechanism (ESM) which reduces the overall average latency of event processing jobs by significant amount considering the cost of operating the system. ESM is augmented with adaptive compressing of upstream data. the ESM conducts one of the two types of switching where either part of the data is sent to the public cloud (data switching) or a selected query is sent to the public cloud (query switching) based on the characteristics of the query. We model the operation of the ESM as the function of two binary switching functions. We show that our elastic switching mechanism with compression is capable of handling out-of-order events more efficiently compared to techniques which does not involve compression. We used two application benchmarks called EmailProcessor and a Social networking Benchmark (SNB2016) to conduct multiple experiments to evaluate the effectiveness of our approach. In a single query deployment with EmailProcessor benchmark we observed that our elastic switching mechanism provides 1.24 seconds average latency improvement per processed event which is 16.70% improvement compared to private cloud only deployment. When presented the option of scaling EmailProcessor with four public cloud VMs ESM further reduced the average latency by 37.55% compared to the single public cloud VM. In a multi-query deployment with both EmailProcessor and SNB2016 we obtained a reduction of average latency of boththe queries by 39.61 seconds which is a decrease of 7% of overall latency. these performance figures indicate that our elastic switching mechanism with compressed data streams can effectively reduce the average elapsed time of stream processing happening in pr
Withthe growing demand for real-time data originating from myriads of Internet-connected devices, the number of requests hitting today's computing infrastructures goes beyond what is manageable for operations and...
详细信息
ISBN:
(纸本)9781450348997
Withthe growing demand for real-time data originating from myriads of Internet-connected devices, the number of requests hitting today's computing infrastructures goes beyond what is manageable for operations and affordable for management. Coping withthese challenges requires a modernization of the application architectures and the underlying infrastructures. the mobile nature inherent to modern communications and interactions requires a radical shift towards new computing paradigms that reflect the fully decentralized perspective of the emerging execution environment. To this end, the trend is to switch thinking from assembling components into systems to dynamically composing autonomous systems into systems-of-systems. Indeed, systems-of-systems possibly emerge dynamically as an opportunistic aggregation of systems available at a given time. Since these systems operate under highly dynamic conditions where boththe entities and their interconnections are subject to continuous change, the traditional stability assumptions made on distributed systems' design are no longer valid. Indeed, the dynamic operating conditions introduce uncertainty, which may harm the dependability of the system. In order to guarantee the provision of dependable functionality in such an unknown, ever-changing execution environment, systems should be fluid and able to self-adapt their structure depending on the changing situation. this talk examines a set of principles and techniques facilitating the design and development of fully decentralized systems that leverage on self-adaptivity to mitigate run-time uncertainty. Specifically, the key objective is to efficiently and effectively provide engineers with proper abstractions to develop self-adaptive systems capable of being at the same time fluid, as well as dependable.
Data encryption is gaining much attention these days from the research community and industry for transmitting secure information over access networks, i.e. `fiber-to-the-home (FTth)' networks and data centers. It...
详细信息
Data encryption is gaining much attention these days from the research community and industry for transmitting secure information over access networks, i.e. `fiber-to-the-home (FTth)' networks and data centers. It is important that the newly designed encrypted networks are fully functional, reconfigurable, compatible, flexible and scalable withthe existing deployed optical fiber networks around the globe. the prime benefit of having FTth networks is the optical end-to-end data encryption that can best be implemented by quantum-keydistribution (QKD) protocols using state-of-the-art telecommunication components, i.e. continuous-variable quantum key distribution (CV-QKD). In this paper, we numerically investigate the quadrature phase shift keying (QPSK) based CV-QKD network that is compatible withthe next generation (NG) services such as point-to-point (P2P) transmission and multicast overlay (MCO) traffic for audio/video signalling. We have further investigated the performance of quantum signals on multi-user fibers by emulating 7-, 12- and 19-core multi-core fibers (MCF). 100 Mbits/s secure key rates (SKRs) can be generated for inter-core crosstalk (XT) values of
Cloud computing has becoming the hotspot in the area of information technology. However, when indulging into its convenience and strong ability of the data processing, we also find that the great challenges also appea...
详细信息
ISBN:
(纸本)9781509041237
Cloud computing has becoming the hotspot in the area of information technology. However, when indulging into its convenience and strong ability of the data processing, we also find that the great challenges also appear in terms of data security and privacy information protection. In this paper, on the one hand, the summary on the current security and privacy information challenges have been surveyed. Second, the current security measurements are summarized as well.
the Internet of things (IoT) has recently become mainstream, different from the incomplete realization of ubiquitous computing, sensor networks, and others in past that commonly shared the notion of visionary hyper-co...
详细信息
ISBN:
(纸本)9781509014453
the Internet of things (IoT) has recently become mainstream, different from the incomplete realization of ubiquitous computing, sensor networks, and others in past that commonly shared the notion of visionary hyper-connectivity, i. e., everything is connected. Among many, one significant reason for this achievement of IoT is the nowadays availability of cloud computing which can cost effectively deal withthe sheer number of globally distributed devices and data generated from those devices. In this paper, we address the issue of IoT scalability in cloud environments by proposing the unique integration scheme between pub/sub systems and Named Data networking (NDN). While the pub/sub architecture has been applied in modern IoT cloud platforms, its implementation and deployment practice have not been fully studied for large scale IoT applications. Our approach concentrates on how to leverage the essential scalability of NDN for building pub/sub systems, thereby achieving scalable IoT cloud services.
this work presents a platform for decentralized distributedcomputing called Resilient Information Architecture for the Smart Grid (RIAPS) through a transactional energy and a traffic application.
ISBN:
(纸本)9781450349659
this work presents a platform for decentralized distributedcomputing called Resilient Information Architecture for the Smart Grid (RIAPS) through a transactional energy and a traffic application.
As a new information service mode and a storing and processing method for mass data, cloud computing brings changes to the age of the Internet service computing;this paper conducts study on the dynamic trust managemen...
详细信息
As a new information service mode and a storing and processing method for mass data, cloud computing brings changes to the age of the Internet service computing;this paper conducts study on the dynamic trust management and evaluation model in the distributed environment based on cloud computing environment.
the rapid progress of cloud technology has attracted a growing number of video providers to deploy their streaming services onto multiple distributed datacenters for more cost-effective performance. the emerging Softw...
详细信息
ISBN:
(纸本)9781509017812
the rapid progress of cloud technology has attracted a growing number of video providers to deploy their streaming services onto multiple distributed datacenters for more cost-effective performance. the emerging Software-Defined networking (SDN) technology overcomes the limitation of the existing network and provides a promising solution to manage the underlying network. In this paper, we introduce an SDN-enabled cloud video distribution architecture and propose a joint resource allocation and traffic management mechanism to improve user experience and reduce the system operational cost. We use a delay utility function to represent user experience and formulate the joint optimization problem as a convex optimization problem. We conduct simulations to evaluate the performance of our algorithm and the results show that our strategy can effectively cut down the total cost and guarantee user experience.
distributed applications deployed in multi-datacenter environments need to deal with network connections of varying quality, including high bandwidth and low latency within a datacenter and, more recently, high bandwi...
详细信息
ISBN:
(纸本)9781538617939
distributed applications deployed in multi-datacenter environments need to deal with network connections of varying quality, including high bandwidth and low latency within a datacenter and, more recently, high bandwidth and high latency between datacentres. In principle, for a given network connection, each message should be sent over the best available network protocol, but existing middlewares do not provide this functionality. In this paper, we present KompicsMessaging, a messaging middleware that allows for fine-grained control of the network protocol used on a per-message basis. Rather than always requiring application developers to specify the appropriate protocol for each message, we also provide an online reinforcement learner that optimises the selection of the network protocol for the current network environment. In experiments, we show how connection properties, such as the varying round-trip time, influence the performance of the application and we show how throughput and latency can be improved by picking the right protocol at the right time.
暂无评论