Smart refueling can reduce costs and lower the possibility of an emergency. Refueling intelligence can only be obtained by mining historical refueling behaviors from big data; however, without devices, such as fuel tank cursors, and cooperation from drivers, these behaviors are hard to detect. Thus, detecting refueling behaviors from big data derived from easy-to-approach trajectories is one of the most efficient retrieve evidences for research of refueling behaviors. In this paper, we describe a complete procedure for detecting refueling behavior in big data derived from freight trajectories. This procedure involves the integration of spatial data mining and machine-learning techniques. The key part of the methodology is a pattern detector that extends the naive Bayes classifier. By drawing on the spatial and temporal characteristics of freight trajectories, refueling behaviors can be identified with high accuracy. Further, we present a refueling prediction and recommendation system to show how our refueling detector can be used practically in big data. Our experiments on real trajectories show that our refueling detector is accurate, and the system performs well.

MapReduce is a programming model for processing large data sets, and Hadoop is the most popular open-source implementation of MapReduce. To achieve high performance, up to 190 Hadoop configuration parameters must be manually tunned. This is not only time-consuming but also error-pron. In this paper, we propose a new performance model based on random forest, a recently developed machine-learning algorithm. The model, called RFMS, is used to predict the performance of a Hadoop system according to the system’s configuration parameters. RFMS is created from 2000 distinct fine-grained performance observations with different Hadoop configurations. We test RFMS against the measured performance of representative workloads from the Hadoop Micro-benchmark suite. The results show that the prediction accuracy of RFMS achieves 95% on average and up to 99%. This new, highly accurate prediction model can be used to automatically optimize the performance of Hadoop systems.

From academia to industry, big data has become a buzzword in information technology. The US Federal Government is paying much attention to the big-data revolution. In 2012, fourteen US government departments allocated funds to 87 big-data projects [1]. Europe has the second largest amount of data [2], and most universities and research institutes have already established big-data research programs. In Asia, especially in China, central and local governments have been setting aside funds for their own big-data programs. The big-data related 973 Projects in China are good examples of this. Industry players have been following in the footsteps of big-data pioneers such as Google, Facebook, Twitter, and Baidu, and more and more companies are rushing into the big-data business. Companies have been analyzing the purchasing behavior of huge numbers of customers and have been devising more attractive plans and policies. Big data is already an important part of the $64 billion database and data analytics market [3]. Indeed, big data will open up commercial opportunities comparable in scale to those created by enterprise software of the late 1980s, the internet of the 1990s, and the social media explosion today.
However, what is big data? It has been defined in many different ways. We prefer to define big data as data sets that are too big for current information technologies to capture, transmit, store, process, or visualize. Although this definition is simple, it encompasses computing complexity theory, computer architecture, operating system, programming model, database technologies, algorithms, and applications. People from different fields have dramatically different understandings of big data, which is why there is so much excitement and conjecture surrounding it.
In this special issue, we present papers that discuss big-data technology from different perspectives. These are not only high-level surveys but also reports on initial results from big-data projects. Communication infrastructure is one of the most important aspects of big data. Yi Zhu and Zhengkun Mi from Nanjing University of Posts and Telecommunications discuss content-centric networking, which is seen as a promising approach to big-data distribution. They propose a networking architecture for processing big data, and this architecture is fundamentally different from TCP/IP. Shengmei Luo et al. from the Cloud Computing & IT Institute of ZTE Corporation present a survey of big-data analytics. They analyze challenges related to storage, data-mining algorithms, and programming models for big data. They also predict opportunities in the big-data era. Although there are many potential business opportunities in big data, security is of the utmost importance for users and cannot be overlooked. Ruixuan Li et al. from Huazhong University of Science and Technology provide an overview of data security and privacy-preservation for cloud storage. They carefully investigate confidentiality, data integrity, and data availability. They also propose a feasible solution to current security problems. Shigang Chen et al. from the University of Florida delve more deeply into data integrity. They propose a novel authenticated data structure called Cloud Merkle B+ tree that supports dynamic operations such as insertion, deletion and modification. CMBT lowers overhead fromO (n ) toO (logn ).
Moving to big data applications, algorithms oriented towards a single machine are not necessarily efficient in big-data platforms because many machines need to run concurrently for the same task. Weisong Shi et al. from Wayne State University design a mechanism called SPBD that reduces the response time of big-data systems. This mechanism is very feasible in practice. Zhendong Bei et al. report their experiences with big-data applications that use MapReduce/Hadoop. They confirm that manually tuning up to 190 Hadoop configuration parameters is extremely time consuming, if at all possible. They then propose an automatic performance prediction scheme based on random forest to determine the best configuration parameter combinations. Their experimental results show that their scheme can predict the performance of Hadoop systems very accurately.
Challenges and opportunities exist together in the big-data era. We believe most of these challenges will be overcome and opportunities will be realized. Big data is a field where dreams will take flight.

In 2010, cloud computing gained momentum. Cloud computing is a model for real-time, on-demand, pay-for-use network access to a shared pool of configurable computing and storage resources. It has matured from a promising business concept to a working reality in both the private and public IT sectors. The U.S. government, for example, has requested all its agencies to evaluate cloud computing alternatives as part of their budget submissions for new IT investment.

In recent years we have also witnessed the rapid growth of mobile applications due to the increasing popularity of smartphones and ubiquity of wireless access. Cloud computing fuels innovation in mobile computing and opens new pathways between mobile devices (where an application is launched) and the infrastructure (where data is stored and processed). Because mobile devices have intrinsic storage, processing, and battery power constraints, mobile applications often hit a performance wall. Unlimited computing and storage resources offered by cloud computing can help break through this wall and turn the problem into a vast opportunity for the growth of mobile computing. According to the latest study from Juniper Research, the market for cloud-based mobile applications is expected to grow 88% annually and reach $9.5 billion by 2014.

To a typical mobile user, a mobile application driven by the cloud should look and feel just like any native mobile applications installed and run in their mobile device. There are already some well-known cloud-based mobile applications; for example, Google’s Gmail for iPhone and Cisco’s WebEx on iPad. These are largely run as Software-as-a-Service (SaaS), in which a cloud provider’s applications are deployed and run in the cloud and can be accessed by users. In general, cloud computing goes beyond the SaaS model by offering computing and storage Infrastructure as a Service (IaaS) or application development Platform as a Service (PaaS). Each cloud service model has proved efficacious in desktop computing. However, the benefits of IaaS and PaaS in mobile cloud computing have not been fully exploited.

This special issue of ZTE Communications discusses related issues in mobile cloud computing. The purpose is to provide an overview of this cutting edge field and to describe its development, trends, challenges, and current practices. Papers have been included that cover a broad spectrum of interesting topics, including mobile cloud computing architectures, mobile search and data management, energy management and sustainability, privacy and security, mobile social networks, and novel cloud-assisted smartphone applications.

In the paper,“A Survey of Mobile Cloud Computing,”Fan et al. classify mobile cloud computing systems. Two representative systems, Hyrax and Cloudlet, are discussed in detail. In their paper“Mirroring Smartphones for Good: A Feasibility Study,”Zhao et al. propose a framework that keeps a mirror for each smartphone on a computing infrastructure in the telecom network. In this framework, some computational workload is offloaded from a smartphone to its mirror. They demonstrate the efficacy of the framework in data caching applications and antivirus scanning services.

“A Cloud-Based Virtualized Execution Environment for Mobile Applications,”by Hung et al. presents a cloud-based virtualized execution environment framework for mobile applications, with a focus on schemes for migrating applications and synchronizing data between execution environments. Performance and power saving issues involved in application migration are also discussed. In“Building a Platform to Bridge Low End Mobile Phones and Cloud Computing Services,”Tso et al. propose a Thumb-in-Cloud platform to break the performance wall in low-end mobile phones. The platform consists of virtual machines that are deployed in low-end phones for execution of mobile applications. It also consists of Thumb gateways that tailor cloud services by reformatting and compressing the service content to fit into the phone’s profile.

Zhang et al. in“WiFace: A Secure Geosocial Networking System Using Wi-Fi Based Multihop MANET,”present a geosocial networking system running on a Wi-Fi based multihop ad hoc network platform for personal mobile devices. The system allows users to access cloud services in environments with or without networking infrastructure or GPS modules. In“A Case for Cloud-Based Mobile Search,”Gao et al. design an Internet search case for cloud-based mobile applications. Searches launched in a mobile device invoke a cloud-based search engine to fulfill the tasks. Key enabling technologies are discussed.

“An On-Demand Security Mechanism for Cloud-Based Telecommunications Services,”by Lin et al. investigates the security issues in cloud computing and a security model is proposed based on a security domain division concept. This helps provide dynamic, on-demand, and differentiated protection for services.

I am grateful to the authors who submitted for this special issue and to the reviewers who spent their valuable time to provide constructive feedback. I hope that you find this special issue interesting and useful.

Emerging Vehicular Ad-Hoc Networks (VANET) have the potential to improve the safety and efficiency of future highways. This paper reviews recent advances in wireless communication technologies with regard to their applications in vehicular environments. Four basic demands of future VANET applications are identified, and the research challenges in different protocol layers are summarized. Information dissemination is one of the most important aspects of VANET research. This paper also discusses the primary issues in information dissemination from an information-centric perspective, and provides two case studies. Finally, future research directions and possible starting points for new solutions are considered.