Summary Context: Software performance is crucial for ensuring the quality of software products. As one of the non‐functional requirements, the few efforts devoted to software performance have often been neglected until a later phase in the software development life cycle (SDLC). The lack of clarity of what software performance research literature is available prevents researchers from understanding what software performance research fields are available. It also creates difficulty for practitioners to adopt state‐of‐the‐art software performance techniques. Software performance research is not as organized as other established research topics such as software testing. Thus, it is essential to conduct a systematic mapping study as a first step to provide an overview of the latest research literature available in software performance. Objective: The objective of this systematic mapping study is to survey and map software performance research literature into suitable categories and to synthesize the literature data for future access and reference. Method: This systematic mapping study conducts a manual examination by querying research literature in noble journals and proceedings in software engineering in the past decade. We examine each paper manually and identify primary studies for further analysis and synthesis according to the pre‐defined inclusion criteria. Lastly, we map the primary studies based on their corresponding classification category. Results: This systematic mapping study provides a state‐of‐the‐art literature mapping in software performance research. We have carefully examined 222 primary studies out of 2000+ research literature. We have identified six software performance research categories and 15 subcategories. We generate the primary study mapping and report five research findings. Conclusions: Unlike established research fields, it is unclear what types of software performance research categories are available to the community. This work takes the systematic mapping study approach to survey and map the latest software performance research literature. The study results provide an overview of the paper distribution and a reference for researchers to navigate research literature on software performance.

Social media have been used by some companies to support customer co-creation in recent years. However, few academic studies have been done to investigate the use of social media in customer co-creation. To understand the current state-of-the-art and future trends about the use of social media in customer co-creation, we conducted two studies to analyze relevant posts on blogs and social media-based online forums. This study reveals some interesting patterns, themes and future trends in this specific area. Recommendations are given to help managers engage in co-creation activities with customers.

Vehicle-to-Vehicle (V2V) communication in Vehicular Ad hoc Networks (VANETs) is one of the key ingredients in the Intelligent Transportation System (ITS) where vehicles receive relevant traffic information using wireless communications from their peers. Forwarding traffic information to drivers can assist with the tasks of avoiding traffic accidents and related congestion. In this paper, we investigate the effect of association time (a.k.a. connection setup time), relative speed of vehicles, transmission range and message/data size in short range based V2V communications. The analysis is illustrated with the numerical results obtained from simulations.

The advances in cloud computing and internet of things (IoT) have provided a promising opportunity to resolve the challenges caused by the increasing transportation issues. We present a novel multilayered vehicular data cloud platform by using cloud computing and IoT technologies. Two innovative vehicular data cloud services, an intelligent parking cloud service and a vehicular data mining cloud service, for vehicle warranty analysis in the IoT environment are also presented. Two modified data mining models for the vehicular data mining cloud service, a Naïve Bayes model and a Logistic Regression model, are presented in detail. Challenges and directions for future work are also provided.

In vehicular networks, there is a strong correlation between a vehicle's identity and that of the driver. It follows that any effort to protect driver privacy must attempt to make the link between the two harder to detect. One of the most appealing solutions to hiding the identity of a vehicle is the use of pseudonyms, whereby each vehicle is issued one or several temporary identities (i.e., pseudonyms) that it uses to communicate with other vehicles and/or the roadside infrastructure. Due to the large number of vehicles on our roadways and city streets and of the sophistication of possible attacks, privacy protection must be both scalable and robust. The first main contribution of this work is to take a nontrivial step towards providing a scalable and robust solution to privacy protection in vehicular networks. To promote scalability and robustness we employ two strategies. First, we view vehicular networks as consisting of nonoverlapping subnetworks, each local to a geographic area referred to as a cell. Depending on the topology and the nature of the area, these cells may be as large as few city blocks or, indeed, may comprise the entire downtown area of a small town. Each cell has a server that maintains a list of pseudonyms valid for use in the cell. Instead of issuing pseudonyms to vehicles proactively, as virtually all existing schemes do, we issue pseudonyms only to those vehicles that request them. Our second main contribution is to model analytically the time-varying request for pseudonyms in a given cell. This is important for capacity planning purposes since it allows system managers to predict, by taking into account the time-varying attributes of the traffic, the probability that a given number of pseudonyms will be required at a certain time as well as the expected number of pseudonyms in use in a cell at a certain time. Empirical results obtained by detailed simulation confirmed the accuracy of our analytical predictions.

Cognitive radio networking is emerging paradigm for future generation wireless networks in which cognitive radio users (also known as secondary users) dynamically access the RF spectrum opportunistically without creating harmful interference to primary users. In this paper, the waiting probability of secondary users in the cognitive radio network is analyzed. We consider a cognitive radio network where multiple secondary users (SUs) contend for spectrum access using time division multiple access over idle primary user (PU) channels. Using queue dynamics as Poisson driven stochastic process, we characterize the waiting probability of secondary users. Generally speaking, in practical systems, secondary users of cognitive radio network would have no knowledge of activities of other users, thus the probability of being idle or contention probabilities of SUs' in cognitive radio network have to be assigned according to the available local information. Our focus is on SUs waiting probability analysis, for which a systematic understanding is lacking. Simulation results show that the use of multiple channels and/or multiple slots leads to significant delay reduction and transmission fairness.

In a series of recent papers, Prof. Olariu and his co-workers have promoted the vision of vehicular clouds (VCs), a nontrivial extension, along several dimensions, of conventional cloud computing. In a VC, underutilized vehicular resources including computing power, storage, and Internet connectivity can be shared between drivers or rented out over the Internet to various customers. Clearly, if the VC concept is to see a wide adoption and to have significant societal impact, security and privacy issues need to be addressed. The main contribution of this work is to identify and analyze a number of security challenges and potential privacy threats in VCs. Although security issues have received attention in cloud computing and vehicular networks, we identify security challenges that are specific to VCs, e.g., challenges of authentication of high-mobility vehicles, scalability and single interface, tangled identities and locations, and the complexity of establishing trust relationships among multiple players caused by intermittent short-range communications. Additionally, we provide a security scheme that addresses several of the challenges discussed.

The past decade has witnessed a growing interest in vehicular networking and its panoply of potential applications among vehicles. Olariu and his co-workers [1, 2, 3] have put forth the vision of a new type of cloud, Vehicular Cloud Computing (VCC). It is clear that the VCC concept raise exceptional security and privacy challenges. It is also clear that if the VCC concept is to see a wide adoption and to have a significant societal impact, security and privacy issues need to be addressed. In this paper we are interested to analyze the security challenges and potential privacy threats in VCC. We address some major design issues that will affect the future implementation of VCC and provide a set of security and privacy-protecting protocols. To the best of our knowledge, this is the first paper that deals with security problems in VCC. But we state that few VCC security issues are fundamentally new. Many of the security challenges have received attentions in related fields such as cloud computing and VANETs. On the other hand, we address relatively unique security challenges resulted by features of VCC, e.g. the challenges of authentication of high-mobility vehicles and the complexity of trust relationships among multi-players caused by intermittent short-range communication.

Recently, Olariu et al. [3], [7], [18], [19], [20] proposed to refer to a dynamic group of vehicles whose excess computing, sensing, communication, and storage resources can be coordinated and dynamically allocated to authorized users, as a vehicular cloud. One of the characteristics that distinguishes vehicular clouds from conventional clouds is the dynamically changing amount of available resources that, in some cases, may fluctuate rather abruptly. In this work, we envision a vehicular cloud involving cars in the long-term parking lot of a typical international airport. The patrons of such a parking lot are typically on travel for several days, providing a pool of cars that can serve as the basis for a datacenter at the airport. We anticipate a park and plug scenario where the cars that participate in the vehicular cloud are plugged into a standard power outlet and are provided Ethernet connection to a central server at the airport. In order to be able to schedule resources and to assign computational tasks to the various cars in the vehicular cloud, a fundamental prerequisite is to have an accurate picture of the number of vehicles that are expected to be present in the parking lot as a function of time. What makes the problem difficult is the time-varying nature of the arrival and departure rates. In this work, we concern ourselves with predicting the parking occupancy given time-varying arrival and departure rates. Our main contribution is to provide closed forms for the probability distribution of the parking lot occupancy as a function of time, for the expected number of cars in the parking lot and its variance, and for the limiting behavior of these parameters as time increases. In addition to analytical results, we have obtained a series of empirical results that confirm the accuracy of our analytical predictions.

Future development of Intelligent Transportation Systems (ITS) depends on Vehicular Ad-hoc Networks (VANETs) in which communications will help to improve traffic safety and efficiency through exchanging information among vehicles. As each vehicle cannot be a source of all messages in VANET, most communications depend on the information received from other vehicles. To protect VANET from malicious action, each vehicle must be able to evaluate, decide and react locally on information received from other vehicles. Message verification is more challenging in VANETs since the security and privacy of the participating vehicles, in general, and of the drivers and passengers specifically is of major concern. Each vehicle needs to verify the accuracy of the message and needs to verify that the received message is from a legitimate vehicle. In this paper, we propose a new algorithm to secure vehicular communication with the help of trust measured for the given period using a probabilistic approach. The proposed algorithm secures VANETs against the untrustworthy drivers. The proposed algorithm is illustrated through numerical results obtained from simulations.

The past decade has witnessed a phenomenal market penetration of wireless communications and a steady increase in the number of mobile users. Unlike wired networks, where communication links are inherently stable, in wireless networks, the lifetime of a link is a random variable whose probability distribution depends on mobility, transmission range, and various impairments of radio communications. Because of the very dynamic nature of Vehicular Ad hoc NETworks (VANETs) and the short transmission range mandated by the Federal Communications Commission (FCC), individual communication links come into existence and vanish unpredictably, making the task of establishing and maintaining routing paths between fast-moving vehicles very challenging. The main contribution of this work is to investigate the probability distribution of the lifetime of individual links in a VANET under the combined assumptions of a realistic radio transmission model and a realistic probability distribution model of intervehicle headway distance. Our analytical results were validated and confirmed by extensive simulation.

In this paper, we present a new scheme for dynamic adaptation of transmission power and contention window (CW) size to enhance performance of information dissemination in Vehicular Ad-hoc Networks (VANETs). The proposed scheme incorporates the Enhanced Distributed Channel Access (EDCA) mechanism of 802.11e and uses a joint approach to adapt transmission power at the physical (PHY) layer and quality-of-service (QoS) parameters at the medium access control (MAC) layer. In our scheme, transmission power is adapted based on the estimated local vehicle density to change the transmission range dynamically, while the CW size is adapted according to the instantaneous collision rate to enable service differentiation. In the interest of promoting timely propagation of information, VANET advisories are prioritized according to their urgency and the EDCA mechanism is employed for their dissemination. The performance of the proposed joint adaptation scheme was evaluated using the ns-2 simulator with added EDCA support. Extensive simulations have demonstrated that our scheme features significantly better throughput and lower average end-to-end delay compared with a similar scheme with static parameters.

Location is important information in Vehicular Adhoc Network because most, if not all, applications will depend on accurate location information. In reality, the dynamics of vehicles makes the location information consistently changing. The existence of malicious attackers even makes the task of estimating accurate location more difficult. In this paper, we describe an efficient statistic method for estimating accurate location of vehicles in a noisy environment including malicious attackers and measurement errors. Given such noisy input, the algorithm estimates the high resolution location of a vehicle by filtering the malicious location input and by refining low resolution location input. We show results of simulations and evaluate the quality of location estimation as well.

Location, fundamental information, plays a critical role in many applications and network routings in Vehicular Adhoc NETworks (VANETs). Therefore, it is of importance to validate the location information. We propose a cross-layer design to achieve location validation. We assume vehicles are installed with radar, GPS and transceiver. On physical layer, radar detection can validate GPS coordinates. On network layer, an agreement of a location can be achieved. On application layer, location information as a set of measurements can be filtered and refined by using a proposed data fusion method. We also present results of simulations and evaluate the location validation methods.

The past decade has witnessed the confluence of Intelligent Transportation Systems (ITS) and Vehicular Ad hoc Networks (VANET) that promises to revolutionize incident detection and the timely dissemination of traffic-related information to the various interested parties. One of the key components is expected to be a Cooperative Collision Warning System (CCWS). Our main contribution is to derive analytical expressions for key CCWS metrics that rely on mobility information exchanged by various players. The feasibility of CCWS has been demonstrated in previous work; this paper analyzes the mobility parameters and derives the conditional probability of a collision. We begin by proposing a set of fundamental parameters for CCWS: conditional probability of collision, headway distance, driver reaction time, relative velocity and acceleration. Preliminary simulation results have demonstrated the effectiveness of our analytical derivations.

Positioning or tracking in VANET is currently based on GPS. However, GPS is known to be prone to failure in case of emergencies. In addition, the current market penetration rate of GPS devices is low. Vehicles with built-in cellular communication capability are expected to be a part of the near future. Therefore, it is reasonable to assume that any vehicle possesses the functionality of a mobile unit (MU). The principal contribution of this paper is the proposed novel concept that employs the existing cellular RSS measurements as the basis for position estimation in VANET in situations where GPS services are unavailable. The proposed localization technique involves sampling the signal beacons received from three base stations surrounding the mobile unit for a very small time duration. Each of the RSS samples are then mapped to a sample of distance estimates based on shadowing radio propagation model. The medians of the generated distance sets are then used by a state of the art technique to produce a final location estimate. One of the important contributions of this work is justifying the selection of median over mean. An extremely small sampling duration negates the impact of mobile unit movement while the median selection neutralizes the deviation caused by time varying radio channel characteristics. All computation is restricted to mobile unit, thereby ensuring privacy. Simulation results demonstrate the efficiency of the proposed algorithm.

Acquiring and securing position information is of fundamental importance in vehicular ad hoc networks and their applications. Recently, it has been shown that securing position information can be achieved by enlisting the help of on-board radar devices that have seen a phenomenal penetration of the vehicular market. However, most on-board radar devices have a static range and this can cause a number of insecurities and can add to communication delay. The main contribution of this work is a novel low-cost radar model which can dynamically tune its range by changing the signal sample size. As it turns out, the dynamically-tunable radar considerably enhances position security.

The diffusion of time-critical information, like traffic alert messages, is critical and challenging in Vehicle Ad hoc Networks (VANETs). It is critical because lives of people on the road are at stake and is challenging due to a combination of highly dynamic mobility patterns, which result in rapidly changing network topologies, combined with the fast movement of vehicles and highly dynamic traffic patterns. Flooding-based alert diffusion among vehicles has a strong similarity with diffusion of a new product among people. Applying a diffusion model to alert messages enables the dissemination modeling of the alert messages among vehicles, and thus opening an opportunity to adopt appropriate strategies to recovery from the traffic accidents. In this paper, a diffusion model is developed for a flooding-based alert message diffusion algorithm and the diffusion speed is explored. The fact that information value (or importance) is decreasing with time and distance, is also considered in the proposed model. We analytically investigate the impact parameters on time-critical information diffusion by mapping to the classic BASS diffusion model [1, 2]. The analytical model allows the evaluation at runtime and enables vehicles to dynamically adapt their diffusion strategies depending on the local node density.

We introduce a real-time weather notification system in which drivers are notified with any bad weather conditions on the road including icy conditions or foggy conditions. Different type of bad weather requires different type of detection. We combine all cases by placing sensors uniformly to the road with an intelligent vehicles that communicate with the surrounding vehicles and the road itself. Our system depends on the spread sensors placed uniformly on the highway to monitor the road traffic. Cat eye's on the road which has been used for years as a reflectors to help drivers over night or at bad weather conditions can be more smart or intelligent by adding sensing capabilities. Intelligent vehicles can help in detecting some types of bad weather conditions and with the help of the sensors over the road using a combination of vehicle-to-vehicle communication and vehicle-to-infrastructure communication, we can reach a system that gives real-time notice for the drivers. Embedded processors are built inside the sensor over the road to allow the node to process these information.

In vehicular adhoc network (VANET), applications are involved with sensitive and secret information. We address a location-based encryption method that not only ensures messages confidentiality but also authenticates identity and location of communication peers. The authentication of location means that a message can only decrypted by the receiver which is ldquophysicallyrdquo present inside a decryption region that is specified by location, time and speed. A practical mapping function which converts location, time and speed into a unique lock key is proposed. The determination of the decryption region is addressed in two steps: predicting and updating. The proposed method evaluated by simulations is efficient and secure.

One of the notoriously difficult problems in vehicular ad-hoc networks is to ensure that established paths do not break before the end of data transmission. This is a difficult problem because the network topology is changing constantly and the routing links are inherently unstable. Inspired by ticket based probing, we propose a scheme to selects a stable routing path in vehicular network environment. On the basis of stability preference, an optimal path (low-cost, low-delay and high-stability) is considered. Our algorithms consider not only the efficiency of path searching but also the balance of stability, delay, and cost metrics to find the optimal routing path. Several possible paths are searched at the same time. The path selection is based on three types of control packets probing routing paths satisfying stability, delay and cost requirements. Extensive simulations show that the proposed algorithm can tolerate the constantly-changing topology in vehicular ad-hoc networks.

The key attribute that distinguishes Vehicular Ad hoc Networks (VANET) from Mobile Ad hoc Networks (MANET) is scale. To wit, while MANET involve up to one hundred nodes and are short lived, being deployed in support of special-purpose operations, VANET networks involve millions of vehicles on thousands of kilometers of highways and city streets. Also, being mission-driven, MANET mobility is inherently limited by the application at hand. Indeed, in a search-and-rescue mission a search party is deployed to look, say, for children lost in the woods. It stands to reason that in such a context the mobility of individual nodes is not arbitrary, but rather restricted by the search strategy implemented. In most MANET applications, such as the one just mentioned, mobility occurs at low speed. By contrast, VANET networks involve vehicles that move at high speed, often well beyond what is reasonable or legally stipulated.

In this paper, we propose an algorithm for joint adaptation of transmission power and contention window to improve the performance of vehicular network in a cross layer approach. The high mobility of vehicles in vehicular communication results in the change in topology of the Vehicular Ad-hoc Network (VANET) dynamically, and the communication link between two vehicles might remain active only for short duration of time. In order for VANET to make a connection for long time and to mitigate adverse effects due to high and fixed transmission power, the proposed algorithm adapts transmission power dynamically based on estimated local traffic density. In addition to that, the prioritization of messages according to their urgency is performed for timely propagation of high priority messages to the destination region. In this paper, we incorporate the contention based MAC protocol 802.11e enhanced distributed channel access (EDCA) mechanism to implement a priority-based vehicle-to-vehicle (V2V) communication. Simulation results show that the proposed algorithm is successful in getting better throughput with lower average end-to-end delay than the algorithm with static/default parameters.