No abstract

Few real-world applications of mobile ad hoc networks have been developed or deployed outside the military environment, and no traces of actual node movement in a real ad hoc network have been available. In this paper, we propose a novel commercial application of ad hoc networking, we describe and evaluate a multitier ad hoc network architecture and routing protocol for this system, and we document a new source of real mobility traces to support detailed simulation of ad hoc network applications on a large scale. The proposed system, which we call Ad Hoc City, is a multitier wireless ad hoc network routing architecture for generalpurpose wide-area communication. The backbone network in this architecture is itself also a mobile multihop network, composed of wireless devices mounted on mobile fleets such as city buses or delivery vehicles. We evaluate our proposed design through simulation based on traces of the actual movement of the fleet of city buses in the Seattle, Washington metropolitan area, on their normal routes providing passenger bus service throughout the city.

With the increasing size of wind farms, the impact of the wake effect on wind farm energy yields become more and more evident. The arrangement of locations of the wind turbines (WTs) will influence the capital investment and contribute to the wake losses, which incur the reduction of energy production. As a consequence, the optimized placement of the WTs may be done by considering the wake effect as well as the components cost within the wind farm. In this paper, a mathematical model which includes the variation of both wind direction and wake deficit is proposed. The problem is formulated by using levelized production cost (LPC) as the objective function. The optimization procedure is performed by a particle swarm optimization (PSO) algorithm with the purpose of maximizing the energy yields while minimizing the total investment. The simulation results indicate that the proposed method is effective to find the optimized layout, which minimizes the LPC. The optimization procedure is applicable for optimized placement of WTs within wind farms and extendible for different wind conditions and capacity of wind farms.Index Terms-Energy yields, levelized production cost (LPC), optimized placement, particle swarm optimization (PSO), wake effect, wake model.

No abstract

With the growing integration of distributed energy resources (DERs), flexible loads, and other emerging technologies, there are increasing complexities and uncertainties for modern power and energy systems. This brings great challenges to the operation and control. Besides, with the deployment of advanced sensor and smart meters, a large number of data are generated, which brings opportunities for novel data-driven methods to deal with complicated operation and control issues. Among them, reinforcement learning (RL) is one of the most widely promoted methods for control and optimization problems. This paper provides a comprehensive literature review of RL in terms of basic ideas, various types of algorithms, and their applications in power and energy systems. The challenges and further works are also discussed.

Deep convolutional neural networks have promoted significant progress in building extraction from high-resolution remote sensing imagery. Although most of such work focuses on modifying existing image segmentation networks in computer vision, we propose a new network in this paper, Deep Encoding Network (DE-Net), that is designed for the very problem based on many lately introduced techniques in image segmentation. Four modules are used to construct DE-Net: the inceptionstyle downsampling modules combining a striding convolution layer and a max-pooling layer, the encoding modules comprising six linear residual blocks with a scaled exponential linear unit (SELU) activation function, the compressing modules reducing the feature channels, and a densely upsampling module that enables the network to encode spatial information inside feature maps. Thus, DE-Net achieves stateoftheart performance on the WHU Building Dataset in recall, F1-Score, and intersection over union (IoU) metrics without pretraining. It also outperformed several segmentation networks in our self-built Suzhou Satellite Building Dataset. The experimental results validate the effectiveness of DE-Net on building extraction from aerial imagery and satellite imagery. It also suggests that given enough training data, designing and training a network from scratch may excel fine-tuning models pre-trained on datasets unrelated to building extraction.

No abstract

No abstract