Mobile edge computing (MEC) has been recently proposed to bring computing capabilities closer to mobile endpoints, with the aim of providing low latency and real-time access to network information via applications and services. Several attempts have been made to integrate MEC in intelligent transportation systems (ITS), including new architectures, communication frameworks, deployment strategies and applications. In this paper, we explore existing architecture proposals for integrating MEC in vehicular environments, which would allow the evolution of the next generation ITS in smart cities. Moreover, we classify the desired applications into four major categories. We rely on a MEC architecture with three layers to propose a data dissemination protocol, which can be utilized by traffic safety and travel convenience applications in vehicular networks. Furthermore, we provide a simulation-based prototype to evaluate the performance of our protocol. Simulation results show that our proposed protocol can significantly improve the performance of data dissemination in terms of data delivery, communication overhead and delay. In addition, we highlight challenges and open issues to integrate MEC in vehicular networking environments for further research.

Vehicular traffic congestion is a significant problem that arises in many cities. This is due to the increasing number of vehicles that are driving on city roads of limited capacity. The vehicular congestion significantly impacts travel distance, travel time, fuel consumption and air pollution. Avoidance of traffic congestion and providing drivers with optimal paths are not trivial tasks. The key contribution of this work consists of the developed approach for dynamic calculation of optimal traffic routes. Two attributes (the average travel speed of the traffic and the roads’ length) are utilized by the proposed method to find the optimal paths. The average travel speed values can be obtained from the sensors deployed in smart cities and communicated to vehicles via the Internet of Vehicles and roadside communication units. The performance of the proposed algorithm is compared to three other algorithms: the simulated annealing weighted sum, the simulated annealing technique for order preference by similarity to the ideal solution and the Dijkstra algorithm. The weighted sum and technique for order preference by similarity to the ideal solution methods are used to formulate different attributes in the simulated annealing cost function. According to the Sheffield scenario, simulation results show that the improved simulated annealing technique for order preference by similarity to the ideal solution method improves the traffic performance in the presence of congestion by an overall average of 19.22% in terms of travel time, fuel consumption and CO₂ emissions as compared to other algorithms; also, similar performance patterns were achieved for the Birmingham test scenario.

Vehicular communication systems play an important role in the context of smart cities. Different applications are being proposed and evaluated to improve our daily driving in terms of safety and convenience. These applications require efficient data dissemination that guarantees full coverage with minimum overhead and delay. Existing data dissemination protocols often rely on extra communication to gather knowledge about the neighborhood and set the dissemination criteria accordingly. This extra communication poses serious overhead issues that affect the scalability of data dissemination, which is an essential criterion under high density scenarios. In this paper, we propose and evaluate an Efficient multi-directional Data Dissemination Protocol (EDDP), which considers the requirements of an urban vehicular environment without requiring the extra communication overhead. We rely only on simple local data to indicate the road condition for better dissemination performance. In this paper, the design considerations of urban layout include message format, broadcast suppression mechanism, and delay control. The EDDP utilizes the properties of the received messages along with positioning information to make decisions on suppressing broadcasts, with the objective of improving coverage in different directions without unnecessary transmissions. Simulation results show that the EDDP can effectively disseminate traffic data with a high data delivery ratio and a minimized overhead.

The increasing complexity of JavaScript (JS) in modern mobile web pages has become a performance bottleneck for low-end mobile phone users, especially in developing regions. In this paper we propose SlimWeb, a novel approach that automatically derives lightweight versions of mobile web pages on-the-fly by eliminating non-essential JavaScript that does not impact the core page content and interactive functionality. SlimWeb consists of a JavaScript classification service powered by a supervised Machine Learning (ML) model that provides insights into each JavaScript element embedded in a web page. SlimWeb aims to improve the web browsing experience by predicting the class of each element, such that essential elements are preserved and non-essential elements are blocked by the browsers using the service. We motivate SlimWeb’s core design via a preference survey where 306 users overwhelmingly preferred having faster page load times over fetching various categories of non-essential JavaScript. We evaluate SlimWeb across 500 popular web pages in a developing region on real cellular networks, along with a user experience study with 20 real-world users and a usage willingness survey of 588 users. Evaluation results show that SlimWeb achieves 50% reduction in page load time compared to the original pages, and more than 30% reduction compared to competing solutions, while achieving high similarity scores to the original pages measured via a qualitative evaluation study with 62 users. SlimWeb improves the overall user experience metric (defined by Google Lighthouse combining first contentful paint, time to interactive, speed index) by more than 60% compared to the original pages, while maintaining 90-100% of the visual and functional components of most pages.

The amount of JavaScript used in web pages has substantially grown in the past decade, leading to large and complex pages that are computationally intensive for handheld mobile devices. Due to the increasing usage of these devices to access today’s web, and to accommodate the needs of a large number of mobile web users who solely rely on low-end devices, we propose “JSAnalyzer,” an easy-to-use tool that enables web developers to quickly optimize JavaScript usage in their pages and to generate simpler versions of these pages for mobile web users. JSAnalyzer is motivated by the widespread use of non-critical JavaScript elements, i.e., those that have negligible (if any) impact on the page’s visual content and interactive functionality. JSAnalyzer allows the developer to selectively enable or disable JavaScript elements in any given page while visually observing their impact on the page to (1) accurately identify any non-critical JavaScript elements and (2) create a simplified page with these elements removed. Our quantitative evaluation shows that, given a low-end mobile phone, JSAnalyzer achieves an increase of nearly 90% in Google’s lighthouse performance score while reducing the page load time by 30%. A qualitative study of 22 users shows that the lighter pages produced by JSAnalyzer maintain more than 90% visual similarity compared to the original pages. Moreover, JSAnalyzer was evaluated by 69 developers, showing that it scores nearly 90% in terms of usefulness and usability while retaining the page’s content and functionality. Finally, we show that JSAnalyzer outperforms state-of-the-art solutions in terms of timing speedups and resource savings.