Suffering from environmental distress like carbon emissions, traffic restrictions have been enforced extensively in distribution logistics. Reasonable arrangement of urban freight transportation can effectively improve distribution efficiency, reduce distribution costs, and alleviate the impact of traffic restrictions in distribution logistics. In response to increasingly stringent traffic restrictions, we establish a multi-objective optimization model, including the minimum distributions and the minimum carbon emissions. Given that the limits of battery capacity and cargo capacity, we build a green vehicle routing problem with soft time windows (GVRPTW) model with heterogenous fleets. In this study, three different factors, that is restricted area, travel time of vehicles, and carbon tax prices, are discussed in details. In order to solve the NP-hard model, we propose an improved ant colony optimization algorithm (IACO) by optimizing the state transition probability, and verifies the worth of the algorithm. The experimental results can explore the impacts of traffic restriction policies on the formulation of distribution scheme and offer reference opinions for the government to formulate reasonable restriction policies and better guide logistics enterprises to reduce carbon emissions.

Given the transport efficiency of large vehicles in urban environments, an increasing number of enterprises are adopting the factory-warehouse-store transportation model. To address the limitations of previous models in practical transport operations, this study formulates a Two-Echelon Vehicle Routing Problem with Simultaneous Pickup and Delivery for Multi-Commodity. Furthermore, the model uniquely emphasizes certain considerations, such as prioritizing product distribution based on production batches and allowing vehicles to engage in flexible product redistribution. Considering the computational challenges arising from the substantial data involved in real-world problem instances, a hybrid heuristic algorithm is proposed. Initially, a hybrid Fuzzy C-Means is employed to decompose the problem by clustering chain stores, effectively reducing the solution space. Subsequently, an enhanced Multi-Population Genetic Algorithm, integrated with Variable Neighborhood Search, is introduced to solve the decomposed sub-problems. Experimental validation conducted with a food enterprise located in Zhengzhou, China, provides empirical support for the efficacy of the proposed model. Multiple test scenarios further illustrate the superior performance of the proposed algorithm. This study holds significant practical and theoretical implications, offering insights to aid decision-makers in reducing transportation costs and advancing the development and application of Vehicle Routing Problem models.

The implementation of Vehicle-to-Grid technology enables bidirectional communication and power flow in the Internet of Electric Vehicles (IoEV) context, facilitating the extensive application of electric vehicles in the logistics industry. In response to escalating urban traffic congestion, simultaneously, many cities have implemented widespread traffic restriction policies. Scientifically optimizing the charging strategies for electric logistics fleets and formulating rational distribution plans are pivotal pathways for developing more efficient and intelligent IoEV. To address the problem, an Electric Vehicle Routing Problem of heterogeneous fleet with time window under traffic constraints is formulated, featuring strategies for demand-driven charging within the IoEV and staggered traffic restriction periods. Given the intricate nature of this mathematical model, it is divided into two subproblems, from which two integer programming models are derived. To tackle this model, a two-tier optimization approach is employed, and an improved Ant Colony Optimization algorithm integrated with Variable Neighborhood Search is proposed. Experimental results show that the proposed model reduces the cost by 9.80%-15.68%, confirming the effectiveness of the proposed charging and staggered traffic restriction strategies, as well as the influence of different traffic restriction factors. This research holds practical and theoretical significance in aiding local governments in formulating rational traffic restriction policies, assisting businesses in effectively reducing the costs of electric logistics fleets, and advancing the development of IoEVs.

To reduce carbon footprint, a hybrid energy powered cellular network (HybE-Net) in the Internet of Things (IoT) environment is widely sought after. Different from cellular network powered on-grid energy, the base station (BS) wake-up in HybE-Net needs to consider the solar energy of the BS and the traffic load in the network. Thus, in this paper, a fuzzy logic based wake-up strategy is proposed, which comprehensively considers the energy wake-up level and the available network resource ratio. Then, the solar energy states are analysed mathematically by using the diffusion approximation method. Finally, to prevent BSs from switching frequently between the sleeping and nonsleeping model, the awakening threshold is optimized by the penalty function method. The simulation results demonstrate that in the proposed wake-up strategy, the wake-up threshold based on the energy state is used to avoid the phenomenon of frequent handoff of the BSs, resulting in fewer handoffs. The proposed BS wake-up strategy can be further applied to both the current and sixth-generation (6G) mobile communication networks, which will be powered by other forms of renewable energy and on-grid energy in the future.

With the advance of artificial intelligence and communication technology in smart city, various location-based data of users can be collected via location-based social networks. How to make full use of these data for accurate point of interest (POI) recommendation is challenging because POI selection is influenced by various factors. In this paper, we propose a network representation learning enhanced multi-source information fusion model for POI recommendation in the context of location-based social networks. The proposed model jointly considers various factors, including user preference, geographical influence, and social influence for recommendation. Specifically, the social influence is modeled by performing network representation learning methods on the constructed co-visiting user networks so that the hidden complex social relationships among users can be measuring automatically. Moreover, considering the significance of user preference and geographical influence, a fusion model is design to jointly consider user preference, social influence, and geographical influence for POI recommendation. Our method is evaluated based on two publicly available datasets and extensive experimental results demonstrate that the proposed multi-source information fusion model outperforms several state-of-the-art algorithms for POI recommendation in terms of precision, recall, and F1.

In smart city, the internet of vehicles provides technical support and innovative power for the development of municipal solid waste management system by virtue of the deep integration of information technology and vehicles. The vehicle routing problem based on waste classification for collection and transportation (C&T) has garnered increasing attention as a typical issue within this system. Given the diverse nature of waste types and the need to organize multiple vehicles to service collection points, congestion often arises due to simultaneous vehicle operations or queuing, posing a significant challenge. To address this, our study introduces asynchronous constraints on vehicle operations to mitigate congestion. Furthermore, building upon the separate loading and unified loading waste C&T models, a combined C&T model grounded in waste classification is devised. We propose an enhanced ant colony optimization algorithm to solve this intricate problem and validate its efficacy. Experimental findings reveal that, compared to both separate and unified schemes, the proposed combined model yields respective reductions of 5.38% and 2.75% in C&T costs. Meanwhile, the comprehensiveness of the combined model has been demonstrated through other experiments, providing a reference for the improvement and optimization of garbage classification C&T schemes.