Compared with traditional wavelength division optical network, elastic optical network (EON) divides the network spectrum into smaller spectrum slots to improve the spectrum utilization, but the highquality spectrum division also complicates the routing and spectrum allocation (RSA) problem. Various strategies are proposed for reducing the RSA complexity and improving system traffic bearing capacity. However, previous RSA strategies do not consider the changing physical layer impairments that will also impact signal quality and even lead to violation of quality of transmission (QoT), the data cannot be transmitted correctly if the link state is degraded. Therefore, cross-layer optimization is desired, which means that different layer information is taken into account in the RSA strategy. In this paper, we propose a new link state-aware (LSA) RSA strategy to guarantee the QoT requirements under different link states. At first, the link state is evaluated based on chromatic dispersion (CD) and optical signal-to-noise ratio (OSNR), and a LightGBM model is exploited for CD and OSNR estimation. In LSA-RSA strategy, the link state is considered as a metric for qualified routing paths finding, and the link capacity is calculated based on the link state and used in spectrum allocation. Simulation results show that the average CD and OSNR estimation errors of the LightGBM model are 0.28ps/nm and 0.68dB, respectively. Under different link states and traffic loads, the LSA-RSA strategy can reduce traffic failure probability by more than 20%, and traffic load can increase 40Erlang when the bandwidth blocking probability equals 10%.
Building a human-like car-following model that can accurately simulate drivers’ car-following behaviors is helpful to the development of driving assistance systems and autonomous driving. Recent studies have shown the advantages of applying reinforcement learning methods in car-following modeling. However, a problem has remained where it is difficult to manually determine the reward function. This paper proposes a novel car-following model based on generative adversarial imitation learning. The proposed model can learn the strategy from drivers’ demonstrations without specifying the reward. Gated recurrent units was incorporated in the actor-critic network to enable the model to use historical information. Drivers’ car-following data collected by a test vehicle equipped with a millimeter-wave radar and controller area network acquisition card was used. The participants were divided into two driving styles by K-means with time-headway and time-headway when braking used as input features. Adopting five-fold cross-validation for model evaluation, the results show that the proposed model can reproduce drivers’ car-following trajectories and driving styles more accurately than the intelligent driver model and the recurrent neural network-based model, with the lowest average spacing error (19.40%) and speed validation error (5.57%), as well as the lowest Kullback-Leibler divergences of the two indicators used for driving style clustering.
Understanding and reasoning about places and their relationships are critical for many applications. Places are traditionally curated by a small group of people as place gaze eers and are represented by an ID with spatial extent, category, and other descriptions. However, a place context is described to a large extent by movements made from/to other places. Places are linked and related to each other by these movements. is important context is missing from the traditional representation.We present DeepMove, a novel approach for learning latent representations of places. DeepMove advances the current deep learning based place representations by directly model movements between places. We demonstrate DeepMove's latent representations on place categorization and clustering tasks on large place and movement datasets with respect to important parameters. Our results show that DeepMove outperforms state-of-the-art baselines. DeepMove's representations can provide up to 15% higher than competing methods in matching rate of place category and result in up to 39% higher silhoue e coe cient value for place clusters.DeepMove is spatial and temporal context aware. It is scalable. It outperforms competing models using much smaller training dataset (a month or 1/12 of data). ese qualities make it suitable for a broad class of real-world applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.