Skip to main content

2014 | Buch

Internet of Vehicles – Technologies and Services

First International Conference, IOV, Beijing, China, September 1-3, 2014. Proceedings

herausgegeben von: Robert C.-H. Hsu, Shangguang Wang

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Computer Science

insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the first International Conference on Internet of Vehicles, IOV 2014, held in Beijing, China, in September 2014. The 41 full papers presented were carefully reviewed and selected from 160 submissions. They focus on the following topics: IOV systems and applications; wireless communications, ad-hoc and sensor networks; security, privacy, IoT and big data intelligence; cloud and services computing.

Inhaltsverzeichnis

Frontmatter

IOV Systems and Applications

A Novel Routing Protocol Based on Mobile Social Networks and Internet of Vehicles

IOV (Internet of Vehicles) has received extensive attention recently as a part of ITS (Intelligent Transportation System). Due to various factors, such as high speed, road condition and traffic flow, the routing protocol becomes one of the important challenging problems in IOV. In this paper, we first present a mobility model at intersection and analysis it by the use of Markov method. On the basis of the mobility model, we propose a novel routing protocol in which the mobile social temporary relationship between vehicles has been considered for the urban transportation environment. Finally, the simulation results show that the packet delivery ratio and the average end-to-end delay of the proposed protocol are better than the traditional protocols.

Hao Wu, Hengliang Tang, Lan Dong
A Link State Aware Hierarchical Road Routing Protocol for 3D Scenario in VANETs

In urban VANETs, nodes on the road appear three-dimensional (3D) distribution. However, the existing protocols only consider the case of planar distribution. It may cause problems in 3D scenarios, like hop count increase and packet delivery ratio decrease. Moreover, most of plane-based protocols determine the road connectivity by collecting the node density information, but it does not accurately reflect the road connectivity. Hence, we propose a novel protocol named Link State aware Hierarchical Road routing (LSHR). LSHR selects the next intersection based on the distance and the road connectivity. Meanwhile, LSHR represents the road connectivity more accurately. In addition, considering the problems of hop count increase and packet delivery ratio decrease, LSHR prior selects the neighbor has the largest transmission range of two hops as the forwarder. Comparing with classic protocols, LSHR is shown to increase the packet delivery ratio and decrease the end-to-end delay and hop count in simulation.

Ying He, Changle Li, Xiaolei Han, Qin Lin
Efficient Profile Routing for Electric Vehicles

This paper introduces a powerful, efficient and generic framework for optimal routing of electric vehicles in the setting of flexible edge cost functions and arbitrary initial states.

More precisely, the introduced state-based routing problem is a consolidated model covering energy-efficiency and time-dependency. Given two vertices and an initial state the routing problem is to find optimal paths yielding minimal final states, while the profile routing problem is to find optimal paths for all initial states. A universal method for applying shortest path techniques to profile routing is developed. To show the genericity and efficiency of this approach it is instantiated for two typical shortest path algorithms, namely for A* and Contraction Hierarchies. Especially using the latter, a highly efficient solution for energy-efficient profile routing is obtained.

René Schönfelder, Martin Leucker, Sebastian Walther
A Message Efficient Intersection Control Algorithm Based on VANETs

Intelligent traffic management via V2V communications in VANETs is attracting more and more attentions from researchers. In this paper, we design a new algorithm to realize intersection control based on coordination among vehicles via VANETs. We basically adopt the concept of mutual exclusion originally proposed for resource management in computer systems. Vehicles at an intersection compete for the privilege of passing by message exchange. The core of such an approach is the algorithms to coordinate vehicles and control the privilege granting. Following our previously proposed intersection control algorithm in [16], we design a new algorithm that can realize intersection control with much less communication cost. The advantage of our new algorithm is validated by simulations using ns-3.

Wei Ni, Weigang Wu
A Histogram-Based Model for Road Traffic Characterization in VANET

This paper presents a new route guidance algorithm and a compact road traffic model that can be easily obtained and transmitted in real-time by individual vehicles while they are travelling on streets or queuing in road cross junctions. The proposed algorithm uses histograms as the network traffic model that captures the arrival rate distribution in VANET. In addition, the paper presents an analysis method that works directly with the histogram model to obtain the queue occupancy distribution at cross-junctions or traffic signals using a finite queue model. A microscopic simulation model is utilized to assess the effectiveness of the traffic model in detecting traffic congestion and directing vehicles to choose better paths. Results show that the proposed road traffic model provides a good prediction of road traffic status, and can be used in conjunction with any standard shortest path algorithms to provide an efficient mechanism for selecting fastest road path.

Hesham El-Sayed, Liren Zhang, Yasser Hawas, Hadeel El Kassabi
Understanding Human Driving Behavior through Computational Cognitive Modeling

As per an article in

The Economist

, someone, somewhere, dies in a road crash every 30 seconds, and about 10 people are seriously injured. Currently, there are about 1.3 million global deaths per year due to road accidents. Most of these deaths and injuries are caused by either factors that are internal to the driver (e.g., driving experience), or due to factors that are external to the driver (e.g., track complexity). However, currently little is known on how these factors influence human driving behavior. In this research, we investigate the role of an external factor (track complexity) on human driving behavior through computational cognitive modeling. Eighteen human participants were asked to drive on two tracks of the same length: simple (4 curves; N=9) and complex (20 curves; N=9). Later, we used two computational models to fit the human steering control data: an existing near-far-point model and a new heuristic model involving tangent and car-axis angles and a position-correction term. Our modeling results show that the fit of the heuristic model to human data on the simple and complex tracks was superior compared to that by the near-far-point model. We highlight the implications of our model results on human driving behavior.

Ajay Kumar, Jai Prakash, Varun Dutt
Vehicular Network Enabling Large-Scale and Real-Time Immersive Participation

This paper presents a system and mechanisms enabling real-time awareness and interaction among vehicles connected via heterogeneous mobile networks. Information obtained by vehicles is considered as the centre in our system. Vehicles are organized dynamically in overlaid clusters. In each cluster, vehicle-related information is pushed in time. As a network node, each vehicle has the function of content abstraction and distribution. Through processing and abstracting the sensed data, various vehicle-related information are organized and denoted in hierarchical names at each node. The data are transmitted and forwarded using protocols accordant with the characteristics of the content. In this way, large-scale and real-time information exchanges among vehicles are realized. Part of our system has been implemented and tested. An open source platform providing standard sensor and actuator API can be provided.

Theo Kanter, Rahim Rahmani, Yuhong Li, Bin Xiao
Internet of Vehicles Service in Dual Channel Supply Chains: Who Should Provide?

Internet of Vehicles is strategic industries in China, which can provide information service for consumer and further increases the market demand for firms. When a manufacturer uses a retailer as a channel for reaching end customers, the IOV strategy takes on an additional dimension: who should provide IOV service to end customers, and what is the equilibrium for providers. We examine the efficacy of IOV service by manufacturer, IOV service by retailer, and overall supply chain in a model of two competing manufacturer-retailer supply chains who sell partially substitutable IOV service that may differ in market size. Findings suggest that that supply chain efficiency is higher with the IOV service by retailer if the service substitutability is low.

Zhang Rong, Liu Bin
Toward Designing Efficient Service Discovery Protocol in Vehicular Networks

Nowadays, it can be seen that there is an increasing interest in the field of vehicular networks due to its important applications. These applications depend mainly on the service discovery protocols which show the need for giving more work and effort to design an efficient VANET service discovery protocol. In fact, little studies have been conducted in this field. Therefore, this paper attempts to highlight some directions that can be considered for designing service discovery solution for VANETs. To explore these directions, the paper provides a literature review for the earlier studies and presents a qualitative analysis of them in order to provide some recommendations for the best design issues. This is can be considered as a step toward designing efficient protocol and may encourage researchers to contribute more in this field.

Lamya Albraheem, Mznah AlRodhan, AbduAllah Aldhlaan
Vehicles Congestion Control in Transport Networks Using an Adaptive Weight Model

This paper proposed an adaptive weight congestion control model in a vehicle transport network. Our focus was to construct a quantitative index series to describe the network congestion distribution, and to shunt vehicles on seriously congested links based on such index sequence. We achieved this goal by combing both feedback and iteration strategy in the congestion control field. First, we developed an agent based model which captured the nonlinear feedback mechanism between the vehicle routing behavior and the road congestion state. Then, the model implemented an adaptive intersection weight adjustment mechanism based on the evolutionary congestion degree of the nearby links, through which to achieve congestion distribution evaluation and network congestion control at the same time. The simulation results verified the validity of our model for congestion control under predefined networks, and proved an applicability of the intersection weight sequence as a measurement for the congestion degree and distribution of road networks.

Bin Jiang, Xiao Xu, Chao Yang, Renfa Li, Takao Terano
Enhancing GNSS-Based Vehicle Positioning Using DSRC and a Nonlinear Robust Filter under the Connected Vehicles Environment

The concept of IOV (Internet of Vehicles) is capable of ensuring the safety and efficiency in road transportation by using wireless communication among the vehicles and the infrastructure facilities. Precise and real-time positioning of vehicles in the road net is of great significance for many intelligent functions and applications. In this paper, we expand the capability of Dedicated Short Range Communication (DSRC) devices to enhance the GNSS (Global Navigation Satellite System) for vehicle positioning. By utilizing the Huber-based M-estimation technique, an improved robust cubature filter is proposed with a novel approach for real-timely updating the measurement covariance, and a strategy for tuning the filter parameter is designed to improve the adaptability. Simulation results with specific tools show that the robustness and estimation precision of information fusion for positioning can be improved under the uncertain measurement and operating conditions.

Liu Jiang, Cai Bai-gen, Wang Jian
OPUVRE: Overall Performance for Urban Vehicle Routing Environments

In recent years, with the great development in assisted driving, traffic monitoring and vehicle entertainment applications, vehicle networking (VANET) attracted a large number of academic research. Because of the vehicle mobility, wireless transmission ranges limit and the loss of wireless channel characteristics in VANET, providing a reliable multi-hop routing protocol in VANET is a significant challenge. This paper proposed a VANET routing protocol OPUVRE (Overall Performance for Urban Vehicular Routing Environments). OPUVRE is an overlay link state routing protocol .It uses traffic density, distribution uniformity and road length to calculate the score of each road, then uses the Dijkstra algorithm to select the best routing path. We evaluate OPUVRE against the traditional geographic routing protocols GSR and LOUVRE. The result shows that OPUVRE provides a higher performance in average packet delivery radio (PDR) and average latency.

Mengchao Song, Wenbin Yao
Implementation and Demonstration of WAVE Networking Services for Intelligent Transportation Systems

Intelligent Transportation System has been a hot topic during the past decades. The Wireless Access in Vehicular Environments (WAVE) system is a radio communication system which is capable of providing safety, efficiency and sustainability. Major researches have been done to evaluate the performance of IEEE 802.11p which concerns PHY and MAC layer. However, the networking services provided by IEEE 1609.3 are essential contributors to the low-latency and low-overhead characteristics, which deserves its attentions. In this paper, after a detailed description of both Data Plane and Management Plane functions of the IEEE 1609.3, we implement this particular standard based on Linux system and develop a GUI program to demonstrate three safety related application scenarios.

Minpeng Miao, Qiang Zheng, Kan Zheng, Zhiwei Zeng
A Receiver-Based Routing Algorithm Using Competing Parameter for VANET in Urban Scenarios

This paper proposes an AODV-based routing algorithm for Vehicular Ad Hoc Network (VANET).This routing algorithm uses a routing metric, which includes the length of each hop as well as the link remaining lifetime. In addition, it can effectively reduce routing overhead by the use of receiver-based method. Furthermore, we design a new urban road scenario and a new mobility model for vehicles to describe the movement of cars. The simulation results we provide confirm the superiority of the proposed algorithm. These simulation comparisons of different ratios between both link-length and link stability also show improvements.

Lujie Wang, Yiming Wang, Cheng Wu

Wireless Communications, Ad-Hoc and Sensor Networks

Path Accumulation Extensions for the LOADng Routing Protocol in Sensor Networks

The “Light-weight On-demand Ad-hoc Distance-vector Routing Protocol – Next Generation” (LOADng) is a simple, yet efficient and flexible routing protocol, specifically designed for use in lossy networks with constrained devices. A reactive protocol, LOADng – as a basic mode of operation – offers discovery and maintenance of hop-by-hop routes and imposes a state in intermediate routers proportional to the number of traffic paths served by that intermediate router.

This paper offers an extension to LOADng, denoted LOADng-PA (Path Accumulation). LOADng-PA is designed with the motivation of requiring even less state in each intermediate router, and with that state being independent on the number of concurrent traffic flows carried. Another motivation the design of LOADng-PA is one of monitoring and managing networks: providing more detailed topological visibility of traffic paths through the network, for either traffic or network engineering purposes.

Thomas Clausen, Jiazi Yi
Fusion of Decisions in Multi-hop Wireless Sensor Networks with Three-Level Censoring Scheme

This paper examines the impact of the three-level censoring scheme on the performance of decision fusion in multi-hop wireless sensor networks (WSNs). In performing the decision fusion process, an optimal fusion rule is derived for the model of the Rayleigh fading channel. However, the optimal fusion rule requires the instantaneous channel state information which may be too costly for resource constrained sensor networks. Hence, considering the approximation of the optimal fusion rule, a sub-optimal alternative with the knowledge of channel statistics is proposed. Simulation results show that the optimal fusion performance can be obtained via adjusting the censoring probability. It implies that with the three-level censoring scheme, the goal of energy saving and performance improvement can be achieved. In addition, the sub-optimal fusion rule exhibits only slight performance degradation compared with the optimal fusion rule which needs much more system resource.

Shoujun Liu, Kezhong Liu, Wei Chen
A Multi-Channel Frame-Slot Assignment Algorithm for Real-Time MACs in Wireless Sensor Networks

In this paper, we propose a multi-channel frame-slot assignment algorithm to reduce the total number of slots required for data packet transmissions and enable a slot reuse against the irregular interference caused by the gradual signal fading. This becomes possible thanks to the efficient scheduling scheme of multiple channels. In our approach, each node determines a sending channel and a receiving channel based on the channel selection rule in a totally distributed manner. The channels are scheduled to the nodes at different depths such that any vertically two-hop away nodes can use the same slot without causing any inference. We evaluate the performance of the proposed algorithm by resorting to simulation. The simulation results show that our proposed approach significantly improves network throughput, packet latency and superframe size.

Van Vinh Phan, Hoon Oh
Maximizing Lifetime Data Aggregation in Multi-sink Wireless Sensor Networks with Unreliable Vehicle Communications

In this paper, we study the problem of maximizing lifetime data aggregation in multi-sink wireless sensor networks with unreliable vehicle communication environment. Firstly, we analyze the communication between adjacent nodes, and present the optimal emission radius that can guarantee the minimum expected energy consumption. Secondly, we discuss the problem that how sensor nodes choose the sink node to send message. Thirdly, we propose the Tree-based topology Data Aggregation algorithm (TDA) based on the energy consumption balancing and the Directed Acyclic Graph based Data Aggregation algorithm (DAGDA) to improve the data acceptance probability. The simulation results show that our algorithms can extend network lifetime effectively.

Zhihuang Su, Yongzao Chen, Hongju Cheng, Naixue Xiong
The Study of OFDM Synchronization Based on the Particle Swarm Optimization Algorithm

The OFDM technology has been widely applied for the effective information transmission in the Internet of Vehicles. In order to solve the problem that synchronization process is complex and the amount of calculation is very large by using the current synchronization algorithm of OFDM system, we propose a synchronization method based on the particle swarm optimization algorithm in the paper. Through being taken the symbol timing and frequency offset of the OFDM system as a two-dimensional particle, the estimations of the symbol timing and frequency offset value are implemented simultaneously by the particle swarm optimization algorithm. Thus the synchronization of OFDM system is achieved by compensating the time and frequency. The computer simulation results show that the proposed algorithm has the better performance, the simpler implementation, and the lower complexity than the existing synchronization algorithms.

Guihua Kang, Hongbo Kang, Jingbo Meng
Crossroads Optimal Geographic Routing for Vehicular Ad Hoc Networks in City Scenario

As it is a big challenge to adapt routing protocol to different applications and dynamic network topology in Mobile Ad Hoc Networks, geographic routing protocols such as Greedy Perimeter Stateless Routing protocol (GPSR) have attracted significant attention. However, unintelligent routing path selecting strategy and outdated neighbor information lead to unwanted performance decline. In this paper, we propose a routing protocol called Crossroads Optimal Geographic Routing protocol (COGR) for vehicular ad hoc networks (VANET) in city scenario, which features on intelligent routing path planning, efficient recovery strategy from dead holes and feasible neighbor position distribution protocol without map information ahead. Through simulation experiments, we prove that COGR does substantially improve performance such as packet delivery ratio, delay and throughput in highly dynamic network environment as VANET in city scenario.

Zhipeng Gao, Kan Chen, Jingchen Zheng, Yuwen Hao, Yang Yang, Xuesong Qiu
Indoor Coverage Performance Comparison between IEEE 802.11g and IEEE 802.11 ah of Wireless Nodes in M2M Network

This paper mainly presents the indoor coverage performance and time delay comparison between IEEE 802.11g and IEEE 802.11 ah of wireless sensor node in Machine to Machine(M2M)network. Firstly, three key problems about the development of M2M network are proposed in order to bring out why IEEE chooses to release IEEE 802.11ah standard and its current situation and tendency. And also, we simply introduce the standard of IEEE 802.11g. Secondly, the paper illustrates the indoor coverage performance and time delay comparison of wireless sensor nodes according to different indoor path loss models respectively for Sub 1GHz and 2.4GHz ISM band. And numeral simulation results and simulation results are respectively offered to depict sensor nodes’ coverage and the time delay.

Mingming Li, Dongxu Wang

Security, Privacy, IoT and Big Data Intelligence

SCHAP: The Aggregate SignCryption Based Hybrid Authentication Protocol for VANET

To secure the message transmission in vehicular ad hoc networks (VANET), the hybrid authentication protocol was proposed. The aggregated signcryption scheme was used to authenticate the private vehicular while protect them from being leak the identities. The aggregated signature was used to authenticate the public vehicular. And the batch-verification was employed to reduce the overheads also. Compared with the existed schemes, the proposal reduced the message overhead 15% at least, and speedup 50% in signing operation. Besides, the simulation experiment also shows that it has the lower communication delay and smaller message loss ratio than others.

Yiliang Han, Dingyi Fang, Zelun Yue, Jian Zhang
tNote: A Social Network of Vehicles under Internet of Things

The main vision of Internet of Things (IoT) is to equip real life physical objects with computing and communication power so that they can interact with each other for social good. As one of the important members of Internet of Things (IoT), vehicles have seen steep advancement in communication technology. In this paper we instantiate IoT to define a social network of vehicles,

tNote

, where vehicles can share transport related safety, efficiency, and comfort notes with each other. We leverage the infrastructure laid down by Vehicular Ad-Hoc Networks (VANETs) to propose an architecture for social network of vehicles in the paradigm of Social Internet of Things (SIoT). We have identified the social structures of vehicles, their relationship types, interactions and the components to manage the system. We also define the

tNote

message structure following the Dedicated Short Range Communication (DSRC) standard. The paper ends with prototype implementation details of the

tNote

message and the proposed system architecture along with experimental results.

Kazi Masudul Alam, Mukesh Saini, Abdulmotaleb El Saddik
Impervious Surface Detection from Multispectral Images Using Surf

Detection of different regions like impervious surfaces, vegetation and water from a multispectral satellite image is a complex task. This paper introduces a novel idea for impervious surface detection from multispectral images using SURF descriptors. To determine the efficiency of the proposed system, a comparative evaluation is done with other two techniques, namely histogram based and spectral-value-based technique. The result shows that the proposed system outperforms the other two techniques in detecting impervious surfaces like buildings and vehicles with an accuracy of 80.48%. The histogram-based technique and spectral-value-based clustering obtained an accuracy of 61.89% and 68.29% respectively. However, in classifying vegetation the other two techniques outperforms SURF descriptors. The histogram based technique gives an accuracy of 86.46% and an accuracy of 94.35% is obtained by using the spectral-value-based clustering. Whereas SURF based technique gives only an accuracy of 50.71%.

Anu Paulose, Sreeraj M., Harikrishnan V.
The Paradigm of Big Data for Augmenting Internet of Vehicle into the Intelligent Cloud Computing Systems

Big Data for IoV development is about turning imperfect, complex, often unstructured data into actionable information, which implies leveraging advanced computational tools to visualize trends and correlations within and across large IoV data sets that would otherwise remain undiscovered. The current research on IoV and cloud system is focusing on data in terms of its complexity and the connections to share it, in consideration of costs and efficiency. However, in few years after, there will be IoV populated and heterogeneous networked embedded devices, which are generating large-scale data in an explosion fashion. The intelligent IoV system should be also capable of learn, think and understand the physical systems by themselves. Therefore, in this paper, we investigate and introduced a paradigm augmenting big data for IoV intelligent system to optimize massive data exploration in the field. The paradigm of big data augmentation is a systematic approach to development raises great expectations and concern to the analytical value of large-scale data that address IoV in the natural progression of intelligent IoV and cloud computing. The intelligent IoV technology is transforming to cloud system to satisfy a variety of IoV applications and user needs, which provide analytic and access of massive data.

Gebeyehu Belay Gebremeskel, Yi Chai, Zhimin Yang
Crowdsourcing Leakage of Personally Identifiable Information via Sina Microblog

Since Edward Snowden’s leaks about the scale and scope of US electronic surveillance, it has become apparent that security services are just as fascinating as what they might learn from our data exhaust. At the time, cybercrime is becoming a global threat now. Cybercriminals may engage in criminal activities with personal privacy data from microblog. Identity theft is probably an example. In this paper we examine the characteristics of privacy leakage in microblog and its potential threats to the Internet community. Research found that a large number of privacy information in social network space was leaked unintentionally. Users often share too much significant personal information. Our study found that the accumulated privacy information may bring huge spam into Internet space. We examined over 20 million nodes profile information and extracted the name, location, gender, and email from these nodes profiles. After basic analysis and processing, we shown that all these personal information is enough to launch spam storm or other criminal activities. The result suggests that each node in the microblog should protect its privacy information carefully.

Chen Fu, Zhan Shaobin, Shi Guangjun, Guan Mengyuan

Cloud and Services Computing

SepStore: Data Storage Accelerator for Distributed File Systems by Separating Small Files from Large Files

Distributed file systems often rely on disk file systems for storing data on disks. Disk file systems can do a relative good performance on large files than small files as sequential access patterns often exhibit for large files. This paper improves the performance of data servers for distributed file systems by improving the performance for small files. A LSM structure based

key-value

store is used for storing the data for small files for transforming the random access to sequential access as well as reducing the metadata of disk file systems. The

key-value

store is also used as the index for accessing small files. Experimental results showed that our method could improve the throughput up to 78% as well as 37% improvement on IOPS.

Zhenzhao Wang, Kang Chen, Yongwei Wu, Weimin Zheng
A Mathematic Mobile Cloud Computing System

In this paper, we propose a mathematical mobile cloud computing system called M2C. This cloud system allows users to execute MATLAB instructions on their Android-based mobile devices, and take advantage of diverse resources including CPUs and GPUs available in clouds to speed up the execution of their MATLAB applications. On the other hand, M2C supports time sharing on license codes to reduce the waiting time of users, and optimizes resource configurations for maximizing the performance of user applications, and automatically recover system services from faults. Consequently, M2C provides a reliable and efficient service for mobile users to perform data-intensive mathematic computation anytime and anywhere.

Tyng-Yeu Liang, You-Jie Li, Ga-Jin He, Jian-Cheng Liao
SafeBrowsingCloud: Detecting Drive-by-Downloads Attack Using Cloud Computing Environment

Drive-by downloads attack has become the primary attack vehicle for malware distribution in recent years. One existing method of detecting drive-by download attacks is using static analysis technique. However, static detection methods are vulnerable to sophisticated obfuscation and cloaking. Dynamic detection methods are proposed to overcome the shortcomings of static analysis techniques and can get a higher detection rate. But dynamic anomaly detection methods are typically resource intensive and introduce high time overhead. To improve performance of dynamic detection techniques, we designed SafeBrowingCloud, a system based on apache S4, a distributed computing platform. And the system is deployed at edge router. SafeBrowingCloud analyzes network traffic, executes webpages in firefox with modified javascript engine, abstracts javascript strings and detects shellcode with three shellcode detection methods to find malicious web pages. Experimental results show efficiency of the proposed system with the high-speed network traffic.

Haibo Zhang, Chaoshun Zuo, Shanqing Guo, Lizhen Cui, Jun Chen
A Dynamic Requests Scheduling Model Based on Prediction in Multi-core Web Server

Traditional requests scheduling algorithms in multi-core web server couldn’t fully exploit the performance of multi-core CPUs. To solve this problem, we proposed the requests scheduling algorithm in the previous paper. But the algorithm couldn’t keep load balance between cores in long time period. In this paper, we proposed a new model to solve this problem. Simulation experiments have been done to evaluate the new model. The experiment results show that the proposed model could better keep load balance between processing cores in long time period.

Guohua You, Xuejing Wang, Ying Zhao
Cloud Services for Deploying Client-Server Applications to SaaS

The Software as a Service (SaaS) model of cloud computing is becoming the trend of the new generation of software development due to its low investment, flexibility, and accessibility. Nowadays there are many well used conventional software applications, especially client-server applications. Reuse these application in cloud platforms will benefit both enterprises and the customers. This paper proposes a service framework for easily deploying conventional client-server applications to cloud running as SaaS. The service framework consists of four services: tenant awareness services, tenant management service, application auto-deployment service, and cloud resources management service. The proposed service framework has been implemented and verified on the Amazon AWS cloud engine.

Jianbo Zheng, Weichang Du
An Event Driven Model for Highly Scalable Clustering for Both on Premise and Cloud Based Systems

Computer clustering has emerged as the paradigm of choice in distributed systems and cloud computing. Multicast based approaches are dominant in the computer clustering domain and many clustering systems are built on top of IP multicast based message passing systems. However, most cloud based systems not provide proper support for multicasting because of the dynamic nature of IP’s, which complicates the configuration and maintenance of such an approach on the cloud.This paper presents an event driven approach for computer clustering, that can effectively handle dynamic IP’s and other issues present in computer clustering and cloud environments. We discuss a clustering implementation based on this event driven approach for an Apache Axis2 cloud deployment. We then compare this event driven clustering implementation with an existing multicast based clustering implementation for a cloud deployed Apache Axis2. The comparisons reveal significantly higher performance in the event driven approach, in addition to solving some of the challenges present in cloud environments.

P. S. Wickramasinghe, L. D. A. Madusanka, H. P. M. Tissera, D. C. S. Weerasinghe, Shahani Markus Weerawarana, Afkham Azeez
A BLE-Based Mobile Cloud Architecture for Longer Smart Mobile Device Battery Life

Smart mobile devices offer increasingly powerful applications for entertainment and work. Compared with the rapid growth of their computing power, the battery capacity can hardly catch up. One way to address the power consumption problem is to offload some workload to the cloud. Different offloading approaches have been proposed. However, they all have their own limitations. In this paper, we review the proposed approaches and present a BLE-based mobile cloud architecture for workload offloading.

James Mao, K. H. Yeung
Human Readable Scenario Specification for Automated Creation of Simulations on CloudSim

Cloud Computing is a widely used computing model which enables customers to deliver services to their end users, with reduced IT management and costs. However, the deployment of applications for the cloud may require the design of the needed environment. CloudSim is a very well-known simulation tool to project these cloud scenarios. However, each scenario creation requires programming efforts that are time-consuming, error prone, not necessarily reusable and commonly only feasible for experienced programmers. This paper presents a tool to define cloud scenarios using YAML files and automates the creation of simulations at CloudSim. The use of human readable YAML data format allows the entire split of the scenario specification and the simulation execution and allows non-programmers to clear and directly define the simulation scenarios, facilitating the scenarios sharing, extension and reuse.

Manoel C. Silva Filho, Joel José P. C. Rodrigues
A Cloud Computing Framework for On-Demand Forecasting Services

This paper presents the Forecast-as-a-Service (FaaS) framework, a cloud-based framework that provides on-demand customer-defined forecasting services. Based on the principles of service-oriented architecture (SOA), the FaaS enables the use of different types of data from different sources to generate different kinds of forecasts at different levels of detail for different prices. The FaaS framework has been developed to provide on-demand forecasts of solar or wind power. Forecasts can be long-term forecasts useful for prospecting or planning by potential investors, or short-term forecasts suitable for operational decision making by operators of existing facilities. FaaS provides a more flexible and affordable alternative to the subscription model provided by current forecast service vendors. By improving the flexibility and economics of renewable energy forecasting services with SOA and cloud computing, FaaS achieves the goal of Services Computing.

Kwa-Sur Tam, Rakesh Sehgal
Security and Efficiency Analysis on a Simple Keyword Search Scheme over Encrypted Data in Cloud Storage Services

With the growing popularity of cloud computing, cloud storage service becomes an essential part of cloud services and numerous researches have been widely studied in recent years. Recently, Hsu et al. proposed an ElGamal-based simple keyword search scheme over encrypted data in cloud storage services. They claimed that a secure cloud storage service needs to achieve five security requirements, including: consistency, ciphertext indistinguishability, trapdoor indistinguishability, outside keyword guessing attack and inside keyword guessing attacks. However, in this paper, we observe that Hsu et al.’s scheme not only cannot prevent inside keyword guessing attack but also cannot prevent denial of service attack and has low efficiency problem in computing algorithms.

Chun-Ta Li, Jau-Ji Shen, Chin-Wen Lee
A Cloud Server Selection System – Recommendation, Modeling and Evaluation

The popularity of cloud computing has increasing rapidly across various sectors. The model that cloud computing offered has drawn attention of the enterprise such as pay as you go model, auto scaling, etc. With those kinds of advantages, it will help enterprise to save their cost while running their business. The benefit of cloud computing leads lots of cloud server providers offering their cloud server for rent in the internet. Each cloud server provider has his advantages and disadvantages. Enterprise needs more time to find a suitable could server provider and it also might not know the differences among cloud server providers. This research presents a search model for searching cloud server providers, and uses enterprise location (context aware method) for recommending the cloud server providers which are nearby the enterprise in order to improve bandwidth and reduce latency problem. Furthermore, this paper implements the search model, recommendation system, and evaluation standard in the system for users using their requirements and locations. Implementation result shows that cloud server which is near to enterprise will improve bandwidth and reduce the latency.

Yao-Chung Chang, Sheng-Lung Peng, Ruay-Shiung Chang, Hery Hermanto
Non-local Denoising in Encrypted Images

Signal processing in the encrypted domain becomes a desired technique to protect privacy of outsourced data in cloud. In this paper we propose a double-cipher scheme to implement non-local means denoising in encrypted images. In this scheme, one ciphertext is generated by Paillier scheme which enables the mean-filter, and the other is obtained by a privacy-preserving transform which enables the non-local searching. By the privacy-preserving transform, the cloud can search the similar pixel blocks in the ciphertexts with the same speed as in the plaintexts, so the proposed method can be fast executed. The experimental results show that the quality of denoised images in the encrypted domain is comparable to that obtained in plain domain.

Xianjun Hu, Weiming Zhang, Honggang Hu, Nenghai Yu
An Adaptive Pre-copy Strategy for Virtual Machine Live Migration

Live migration technology for virtual machines provides greater flexibility when scheduling tasks in a cloud environment. This flexibility helps increase the utilization of resources within the cloud. A key component of live migration technology is the pre-copy strategy. The pre-copy strategy allows virtual machine to perform live migration without interruption of service. However, in order for live migration to be efficient, it is imperative that virtual machines’ memories are not limited by bandwidth and that the downtime of the virtual machines involved is minimal.

This paper presents an adaptive pre-copy strategy for virtual machine live migration called Multi-Phase Pre-Copy (MPP). In iterative pre-copy stage MPP transmits memory pages only when a predefined threshold is met. This strategy significantly reduces unnecessary migration of memory pages.

Ching-Hsien Hsu, Sheng-Ju Peng, Tzu-Yi Chan, Kenn Slagter, Yeh-Ching Chung
Life Support System by Motion Sensor-Based Behavior Monitoring and SNS-Based Information Sharing

Behavior monitoring is an important method for life support of elderly persons. However, current behavior monitoring system is hard to be applied into our lives whether from user side or from supporter side. In this paper, we propose a sensor-based input system that can detect daily activities automatically and provide necessary information to remote supporters. The system adopts a wearable device to obtain activity data and for activity recognize and analysis. Moreover, we develop a rule-based algorithm and employ AHP method for information mining and filtering of daily activities. The filtered information is shared to supporters through cloud to reflect users’ behavior and health situations. The system is evaluated by 10 subjects and the result indicates its feasibility and effectiveness.

Yinghui Zhou, Yoshio Asano, Lei Jing, Zixue Cheng
Compression Accelerator for Hadoop Appliance

In this paper, we propose an accelerator for Hadoop appliances. Data servers receive significant data traffic because of several services based on networks. Processing such big data requires sufficient communication bandwidth for big data management. In order to increase communication bandwidth, compression algorithms are adopted in Hadoop appliances, although additional computation overhead is required. Our accelerator compresses data from a PCIe (Peripheral Component Interconnect Express) interface, thus reducing the size of data that should be transmitted through a network. As a result, computation overhead of the main processor in a server is decreased and communication bandwidth is increased.

Sang Don Kim, Seong Mo Lee, Sang Muk Lee, Ji Hoon Jang, Jae-Gi Son, Young Hwan Kim, Seung Eun Lee
Backmatter
Metadaten
Titel
Internet of Vehicles – Technologies and Services
herausgegeben von
Robert C.-H. Hsu
Shangguang Wang
Copyright-Jahr
2014
Verlag
Springer International Publishing
Electronic ISBN
978-3-319-11167-4
Print ISBN
978-3-319-11166-7
DOI
https://doi.org/10.1007/978-3-319-11167-4