Luis Sequeira

Luis Sequeira, Toktam Mahmoodi

In this paper, we study the role that machine learning can play in cooperative driving. Given the increasing rate of connectivity in modern vehicles, and road infrastructure, cooperative driving is a promising first step in automated driving. The example scenario we explored in this paper, is coordinated lane merge, with data collection, test and evaluation all conducted in an automotive test track. The assumption is that vehicles are a mix of those equipped with communication units on board, i.e. connected vehicles, and those that are not connected. However, roadside cameras are connected and can capture all vehicles including those without connectivity. We develop a Traffic Orchestrator that suggests trajectories based on these two sources of information, i.e. connected vehicles, and connected roadside cameras. Recommended trajectories are built, which are then communicated back to the connected vehicles. We explore the use of different machine learning techniques in accurately and timely prediction of trajectories.

Omar Nassef, Luis Sequeira, Elias Salam et al.

In this paper, a framework for lane merge coordination is presented utilising a centralised system, for connected vehicles. The delivery of trajectory recommendations to the connected vehicles on the road is based on a Traffic Orchestrator and a Data Fusion as the main components. Deep Reinforcement Learning and data analysis is used to predict trajectory recommendations for connected vehicles, taking into account unconnected vehicles for those suggestions. The results highlight the adaptability of the Traffic Orchestrator, when employing Dueling Deep Q-Network in an unseen real world merging scenario. A performance comparison of different reinforcement learning models and evaluation against Key Performance Indicator (KPI) are also presented.

Luis Sequeira, Adam Szefer, Jamie Slome et al.

Cooperative driving using connectivity services has been a promising avenue for autonomous vehicles, with the low latency and further reliability support provided by 5th Generation Mobile Network (5G). In this paper, we present an application for lane merge coordination based on a centralised system, for connected cars. This application delivers trajectory recommendations to the connected vehicles on the road. The application comprises of a Traffic Orchestrator as the main component. We apply machine learning and data analysis to predict whether a connected vehicle can successfully complete the cooperative manoeuvre of a lane merge. Furthermore, the acceleration and heading parameters that are necessary for the completion of a safe merge are elaborated. The results demonstrate the performance of several existing algorithms and how their main parameters were selected to avoid over-fitting.

Jose Saldana, Mirko Suznjevic, Luis Sequeira et al.

We study TCP flows coexistence between Massive Multiplayer Online Role Playing Games (MMORPGs) and other TCP applications, by taking World of Warcraft (WoW) and a file transfer application based on File Transfer Protocol (FTP) as an example. Our focus is on the effects of the sender buffer size and FTP cross-traffic on the queuing delay experienced by the (MMORPG) game traffic. A network scenario corresponding to a real life situation in an ADSL access network has been simulated by using NS2. Three TCP variants, namely TCP SACK, TCP New Reno, and TCP Vegas, have been considered for cross-traffic. The results show that TCP Vegas is able to maintain a constant rate while competing with the game traffic, since it prevents packet loss and high queuing delays by not increasing the sender window size. TCP SACK and TCP New Reno, on the other hand, tend to continuously increase the sender window size, thus potentially allowing higher packet loss and causing undesired delays for the game traffic. In terms of buffer size, we have established that smaller buffers are better for MMORPG applications, while larger buffers contribute to a higher overall delay.

Jose Saldana, Luis Sequeira, Julian Fernandez-Navajas et al.

This paper studies the use of a traffic optimization technique named TCM (Tunneling, Compressing and Multiplexing) to reduce the bandwidth of MMORPGs (Massively Multiplayer Online Role-Playing Games), which employ TCP to provide a soft real-time service. In order to optimize the traffic and to improve bandwidth efficiency, TCM can be applied when the packets of a number of players share the same link, which occurs in some scenarios, as e.g. the traffic between proxies and servers of game-supporting infrastructures. First, TCP/IP headers are compressed using standard algorithms that avoid sending repeated fields; next, a number of packets are blended into a bigger one and finally, they are sent using a tunnel. The expected compressed header size has been obtained using traffic traces of a real game. Next, simulations using a traffic model of a popular MMORPG have been performed in order to estimate the expected bandwidth savings and the reduction in packets per second. The obtained bandwidth saving is about 60 percent. Packets per second are also significantly reduced. In addition, the added delays are shown to be small enough so as not to impair layers' experienced quality.

Idelkys Quintana, Jose Saldana, Jose Ruiz Mas et al.

This work presents a study of the behaviour of the router buffer when managing the traffic of P2P-TV applications, where a number of peers exchange video content. First, a summary of the characteristics of SOPCast is presented. Then, the results obtained in simulation tests using different buffer policies are presented. Real traces of the application, obtained from a research project, have been used for the tests, sharing the Internet access with different amounts of background traffic. The results show that a similar buffer behaviour for all the access technologies. In addition, the big amount of small packets generated may impair the video traffic, thus avoiding the retransmission of the contents by the application.

Jose Saldana, Julian Fernandez Navajas, Jose Ruiz Mas et al.

This paper compares two policies which can be used for multiplexing the traffic of a number of players of a First Person Shooter game. A network scenario in which a number of players share an access network has been simulated, in order to compare the policies in terms of a subjective quality estimator. The first policy, namely timeout, achieves higher bandwidth savings, while the second one, period, introduces less delay and jitter. The results show that the difference in terms of QoE is only significant when the number of players is small. Thus, in order to make the correct decision, the concrete network scenario and the characteristics of the router would have to be considered in each case, taking into account the estimation of the subjective quality that can be expected.