Existing rate adaptation protocols have advocated training to establish the relationship between channel conditions and the optimal modulation and coding scheme. However, wireless devices for outdoor and vehicular communications frequently enter environments they have not yet encountered and therefore, have insufficient training for rate adaptation decisions. In addition, protocols are often optimally tuned for indoor environments but, when taken outdoors, perform poorly. In both cases, the decision structure formed offline lacks the ability to acclimate to a new situation on the fly. The diverse and ever-changing environments of increasingly mobile wireless devices call for a rate adaption scheme that can quickly adjust accordingly to form a unique environment set established by the user. In this paper, we propose an on-the-fly, in-situ training (FIT) mechanism which addresses the challenges of making rate decisions with unpredictable fluctuation and lack of repeatability of real wireless channels. We design and conduct extensive experiments on emulated and in-field wireless channels to evaluate the in-situ training process, showing that the rate decision structure can be updated as channel conditions change using existing traffic flows.

In this paper, we presented a dynamic channel selection system for vehicular communications that learns from the varying channel congestion levels and automatically selects the least congested channel to maintain link quality. The high mobility of vehicles and a crowded frequency spectrum result in fast-changing channel conditions that make channel selection a challenging problem. Such a system has the potential of supporting future automotive technologies such as vehicle pla-tooning, an emerging technology that could significantly increase road capacity as well as achieve semi-auto driving by grouping individual cars into tight platoons. The key to such applications is accurate and instant coordination among platoon members, which requires reliable low-latency intra-platoon communication links that our channel selection algorithm aims to achieve. We implemented this system integrating radio subsystems based on off-the-shelf networking boards and implemented essential features for achieving dynamic channel access in vehicular environment, including mobility awareness, channel congestion measurement, and channel coordination between mobile nodes. With real-world experiments we showed performance enhancements offered by proposed dynamic channel selection system by avoiding congestion.

Context awareness has received increasing attention with the proliferation of various types of sensors on mobile devices. However, while wireless performance is known to be highly correlated with environmental settings, mobile devices have yet to fully exploit the awareness of context to improve wireless performance. In this paper, we leverage available context information to improve link-level adaptation via decision-tree classifiers and extensively evaluate its performance over emulated channels as well as with in-field trials. We first propose a classification method based on decision trees to select the optimal transmission parameters such as modulation, coding rate and packet size. We then quantify the throughput improvement using the proposed scheme and show that in some scenarios the throughput increases by over 100% compared to traditional SNR-based rate adaptation protocols. Second, we analyze the amount of training to assess the classification scheme. Third, we validate classification-based method by implementation on two different test platforms for extensive experimentation. We reveal the importance of the various contextual attributes used and identify channel type as a key parameter that affects classification performance. Finally, we study and quantify the use of context information across multiple different frequency bands and demonstrate the significant throughput gains that can be obtained.

In this paper, we propose a reinforcement learning-based approach for enabling vehicles to make intelligent channel selection choices across TV whitespace spectrum. In order for vehicle communication networks to dynamically access TV whitespace in a secondary manner, it is imperative that these communication systems be capable of coexisting with other types of secondary wireless networks operating within the same frequency range. Consequently, we first propose a TV whitespace channel sharing scheme that would facilitate the coexistence between WLAN, WRAN, and vehicular communication networks. Using the channel utilization variations observed by a collection of mobile vehicular communication systems, we then devised a reinforcement learning-based adaptive channel selection algorithm that employs channel utilization sensing in order to reinforce the decisions made by the vehicular communication system. Moreover, the parameters of the proposed learning approach are adaptively tuned in order to achieve better adaptation to a particular environment. A computer emulation environment composed of actual real-world sensing measurement data and a simulated TV whitespace network is created in order to accurately model the characteristics of future wireless environment, as well as to test the proposed learning-based channel access approach. Experimental results show a significant performance improvement with respect to vehicle communication.

Future vehicular communications systems are expected to utilize the vacant channels (white spaces) of the spectrum, otherwise allocated for specific designated use. One such candidate of white space comes from the TV broadcast band. In this demonstration, we will first present animated results of a TV spectrum measurement campaign along the entire portion of Interstate I-90 located in the US state of Massachusetts. Next, we will demonstrate a cyber-physical proof-of-concept lab implementation of our previously developed control and data channel assignment schemes for vehicle-to-vehicle communications over (TV) white space. Finally we will show a video of actual vehicle to vehicle communications field tests conducted in Japan using TV white space.

Vehicular networking has significant potential to enable diverse range of applications, including safety and convenience. As the number of vehicles and applications using wireless spectrum grow, one can expect to see a shortage of either spatially or temporally available spectrum. In this paper, we advocate that dynamic spectrum access for vehicles be the first step towards solving the spectrum shortage. For this, vehicles must be able to sense the availability of spectrum before attempting to transmit. The existence of other transmitters should be detected in order not to cause or experience interference. However, spectrum sensing in vehicular environments is a challenging task due to mobility, shadowing and other factors that govern vehicular environments. Therefore, spectrum sensing by a single vehicle may not be able to provide accurate information about the spectrum vacancies. Cooperative spectrum sensing, on the other hand, uses spatial diversity and can be employed to overcome the limitations associated with a single sensor/vehicle. In this paper, we investigate cooperative spectrum sensing performance in a vehicular environment for sensing signals transmitted from i) a roadside infrastructure and ii) radios located on other vehicles, by using energy-based detection of a transmitted pilot tone as an example. Our goal is to characterize the limits on detection speed and reliability of simple hard and soft cooperative energy-based schemes for this environment. We show how cooperation reduces sensing time by a factor of five in an AWGN channel. The cooperative sensing time reduction is far more significant in a vehicular environment with fading and shadowing. Finally, we illustrate how infrastructure-to-vehicle scenario favors soft equal gain combining while vehicle-to-vehicle scenario favors hard fusion OR rule.

Vehicular communication is an emerging technology that has lot of potential to support transportation safety, traffic information and other ITS related applications. Due to its unique challenges and infrastructure requirements it is very difficult to evaluate new communication technologies in real world. A good simulation environment is required to evaluate new technologies in close to real-world situations. It is very difficult to integrate real world scenarios like driving and vehicular mobility in widely used network simulators like NS-2 and Qualnet. This paper discusses these requirements for vehicular communication simulation and provides a new architecture for flexible simulation framework for vehicular networks. Proposed simulation architecture combines network simulation, driving simulation and propagation simulation by using real geographic road network and digital elevation model (DEM) to accurately simulate vehicular communication with realistic mobility, accurate propagation models and precise communication models. Proposed simulation framework provides plug-in type modules to extend the features for a particular technology, whether it is communication protocol or driver safety system and evaluates the results inside complete system. Also presented a simple scenario to show how different modules can be extended based on the simulation requirements

A metasearch engine supports unified access to multiple component search engines. To build a very large-scale metasearch engine that can access up to hundreds of thousands of component search engines, one major challenge is to incorporate large numbers of autonomous search engines in a highly effective manner. To solve this problem, we propose automatic search engine discovery, automatic search engine connection, and automatic search engine result extraction techniques. Experiments indicate that these techniques are highly effective and efficient.