In vehicular networks, the interference is brought about by the rapid growth of various services due to the scarcity of radio resources, which poses great challenges for the network connectivity. Unlike the connectivity that is solely determined by the signal strength or the distance between pairwise vehicles, the connectivity considered in this paper is influenced by the interference among multiple links. To improve the network connectivity by interference mitigation, a connectivity optimization problem based on resource allocation is modeled using graph theory. First, the definitions of the connectivity metrics affected by interference in the vehicular networks are given. Second, the number of resources that guarantee the network connectivity is analyzed. Finally, a resource allocation algorithm based on the minimum spanning tree is proposed to improve the network connectivity that is constrained by limited resources. The simulation results confirm that the proposed algorithm approximates the optimal performance and improves the connectivity better than similar algorithms.

The stochastic properties of vehicles’ arrival process and the high-speed mobility of vehicles lead to dynamic changes in the topology of vehicular networks, affecting the data download experience of users, especially for large files. In this paper, a novel elastic-segment-based vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) cooperative strategy (ESCS) is proposed to reduce the impact of the density of vehicles on achievable throughput. The achievable throughput and optimal parameters of the proposed system are analyzed. The strategy takes the impact of the density of vehicles on the data download process as the key element for consideration. The density of vehicles has a great influence on the distance between vehicles, and further affects the transmission data rate. To solve the problem of low transmission data rate induced by the density of vehicles, the sizes of the elastic-segments are optimized according to the distance between the vehicles. Owing to the stochastic process of the distance between vehicles, it is particularly challenging to derive a closed-form expression for the achievable throughput. To tackle this problem, we develop a new V2I/V2V cooperative model to adapt to the general two-way lanes, analyze the distribution and mobility of vehicles, and derive a closed-form expression for the achievable throughput, as a function of V2I effective transmission range, the V2V effective transmission range, and other system parameters. We then optimize V2V effective connection range and the vehicle density to maximize the achievable throughput. Simulation results show that the proposed strategy significantly improves the throughput compared with the existing cooperative strategy, especially in the scenario of high vehicle density.

Vehicular networks are becoming increasingly dense due to expanding wireless services and platooning has been regarded as a promising technology to improve road capacity and on-road safety. Constrained by limited resources, not all communication links in platoons can be allocated to the resources without suffering interference. To guarantee the quality of service, it is required to determine the set of served services at which the scale of demand exceeds the capability of the network. To increase the number of guaranteed services, the resource allocation has to be adjusted to adapt to the dynamic environment of the vehicular network. However, resource re-allocation results in additional costs, including signal overhead and latency. To increase the number of guaranteed services at a low-cost in a resource-limited vehicular network, we propose a time dynamic optimization method that constrains the network re-allocation rate. To decrease the computational complexity, the time dynamic optimization problem is converted into a deterministic optimization problem using the Lyapunov optimization theory. The simulation indicates that the analytical results do approximate the reality, and that the proposed scheme results in a higher number of guaranteed services as compared to the results of a similar algorithm.

Semantic segmentation is one of the most critical modules in road scene understanding. In this paper, we focus on the challenging task of pedestrian’s relative location perception in the semantic graph of complex driving scenes. Prevalent research on semantic segmentation mainly concentrate on improving the segmentation accuracy with less attention paid to computational efficiency. Furthermore, little effort has been made in pedestrian location perception in complex driving scenes. For example, current semantic segmentation methods classify all pedestrians as a mono category, regardless of whether the pedestrians are penetrating into the vehicular lane or standing still in the safe sidewalk area. We propose a pedestrian location perception network (P-LPN). P-LPN can produce real-time semantic segmentation while simultaneously providing location inference for each pedestrian in semantic maps. This enables autonomous driving system to categorize pedestrians into different safety levels. We comprehensively evaluated P-LPN on CityScapes benchmark through comparative studies. Our proposal achieved competitive performance in both accuracy and efficiency. It yields quality inference with real-time speed at ~22 fps.

In underwater sensor networks (UWSNs), the unique characteristics of acoustic channels have posed great challenges for the design of medium access control (MAC) protocols. The long propagation delay problem has been widely explored in recent literature. However, the long preamble problem with acoustic modems revealed in real experiments brings new challenges to underwater MAC design. The overhead of control messages in handshaking-based protocols becomes significant due to the long preamble in underwater acoustic modems. To address this problem, we advocate the receiver-initiated handshaking method with parallel reservation to improve the handshaking efficiency. Despite some existing works along this direction, the data polling problem is still an open issue. Without knowing the status of senders, the receiver faces two challenges for efficient data polling: when to poll data from the sender and how much data to request. In this paper, we propose a traffic estimation-based receiver-initiated MAC (TERI-MAC) to solve this problem with an adaptive approach. Data polling in TERI-MAC depends on an online approximation of traffic distribution. It estimates the energy efficiency and network latency and starts the data request only when the preferred performance can be achieved. TERI-MAC can achieve a stable energy efficiency with arbitrary network traffic patterns. For traffic estimation, we employ a resampling technique to keep a small computation and memory overhead. The performance of TERI-MAC in terms of energy efficiency, channel utilization, and communication latency is verified in simulations. Our results show that, compared with existing receiver-initiated-based underwater MAC protocols, TERI-MAC can achieve higher energy efficiency at the price of a delay penalty. This confirms the strength of TERI-MAC for delay-tolerant applications.

Short-term load forecasting is very important for power systems. The load is related to many factors which compose tensors. However, tensors cannot be input directly into most traditional forecasting models. This paper proposes a tensor partial least squares-neural network model (TPN) to forecast the power load. The model contains a tensor decomposition outer model and a nonlinear inner model. The outer model extracts common latent variables of tensor input and vector output and makes the residuals less than the threshold by iteration. The inner model determines the relationship between the latent variable matrix and the output by using a neural network. This model structure can preserve the information of tensors and the nonlinear features of the system. Three classical models, partial least squares (PLS), least squares support vector machine (LSSVM) and neural network (NN), are selected to compare the forecasting results. The results show that the proposed model is efficient for short-term load and daily load peak forecasting. Compared to PLS, LSSVM and NN, the TPN has the best forecasting accuracy.