In the context of the unmanned aerial vehicle (UAV)-assisted vehicular networking system, more network factors need to be considered to ensure the safe operation of connected vehicles. A large volume of delay-sensitive and computationally demanding tasks necessitate offloading to UAVs or roadside units for processing. And the efficient allocation of various network resources of vehicles, UAVs, and roadside units under constrained conditions determines the efficiency of task offloading. Deep reinforcement learning (DRL) has demonstrated its efficacy as an experienced approach for solving such problems. In this paper, we delve into the utilization of deep reinforcement learning to design an efficient UAV-assisted vehicular edge computing task offloading strategy. Under the constraints of limited network bandwidth and limited UAV power, the trajectory and the task offloading strategy of the UAV are jointly optimized. The primary objective of our proposed strategy is to achieve a notable reduction in the system delay of the edge computing network. Given the dynamic variability of tasks arrival, we employ a long short-term memory (LSTM) network with the attention mechanism and a deep deterministic policy gradient (DDPG) algorithm to effectively model the optimization problem as a Markov decision process. This approach can obtain the optimal policy through interactive learning from the UAV and the vehicle environment. The experiment results illustrate that this strategy outperforms other baseline strategies in terms of convergence speed, network delay, and task offloading ratio.

Unmanned aerial vehicles (UAVs) are considered a promising example of an automatic emergency task in a dynamic marine environment. However, the maritime communication performance between UAVs and offshore platforms has become a severe challenge. Due to the complex marine environment, the task allocation and route planning efficiency of multiple UAVs in an intelligent ocean are not satisfactory. To address these challenges, this paper proposes an intelligent marine task allocation and route planning scheme for multiple UAVs based on improved particle swarm optimization combined with a genetic algorithm (GA-PSO). Based on the simulation of an intelligent marine control system, the traditional particle swarm optimization (PSO) algorithm is improved by introducing partial matching crossover and secondary transposition mutation. The improved GA-PSO is used to solve the random task allocation problem of multiple UAVs and the two-dimensional route planning of a single UAV. The simulation results show that compared with the traditional scheme, the proposed scheme can significantly improve the task allocation efficiency, and the navigation path planned by the proposed scheme is also optimal.

Reducing the energy consumption of Internet services requires knowledge about the specific traffic and energy consumption characteristics, as well as the associated end-to-end topology and the energy consumption of each network segment. Here, we propose a shift from segment-specific to service-specific end-to-end energy-efficiency modeling to align engineering with activity-based accounting principles. We use the model to assess a range of the most popular instant messaging and video play applications to emerging augmented reality and virtual reality applications. We demonstrate how measurements can be conducted and used in service-specific end-to-end energy consumption assessments. Since the energy consumption is dependent on user behavior, we then conduct a sensitivity analysis on different usage patterns and identify the root causes of service-specific energy consumption. Our main findings show that smartphones are the main energy consumers for web browsing and instant messaging applications, whereas the LTE wireless network is the main consumer for heavy data applications such as video play, video chat and virtual reality applications. By using small cell offloading and mobile edge caching, our results show that the energy consumption of popular and emerging applications could potentially be reduced by over 80%.

The vast amounts of mobile communication data collected by mobile operators can provide important insights regarding epidemic transmission or traffic patterns. By analyzing historical data and extracting user location information, various methods can be used to predict the mobility of mobile users. However, existing prediction algorithms are mainly based on the historical data of all users at an aggregated level and ignore the heterogeneity of individual behavior patterns. To improve prediction accuracy, this paper proposes a weighted Markov prediction model based on mobile user classification. The trajectory information of a user is extracted first by analyzing real mobile communication data, where the complexity of a user’s trajectory is measured using the mobile trajectory entropy. Second, classification criteria are proposed based on different user behavior patterns, and all users are classified with machine learning algorithms. Finally, according to the characteristics of each user classification, the step threshold and the weighting coefficients of the weighted Markov prediction model are optimized, and mobility prediction is performed for each user classification. Our results show that the optimized weighting coefficients can improve the performance of the weighted Markov prediction model.

With the development of intelligent agents pursuing humanisation, artificial intelligence must consider emotion, the most basic spiritual need in human interaction. Traditional emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate responses. However, selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the response. We propose a semantic and emotion‐based dual latent variable generation model (Dual‐LVG) for dialogue systems, which is able to generate appropriate emotional responses without an emotional dictionary. Different from previous work, the conditional variational autoencoder (CVAE) adopts the standard transformer structure. Then, Dual‐LVG regularises the CVAE latent space by introducing a dual latent space of semantics and emotion. The content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features respectively. Moreover, the average attention mechanism is adopted to better extract semantic features at the sequence level, and the semi‐supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the model. Experimental results show that Dual‐LVG can successfully achieve the effect of generating different content by controlling emotional factors.

Unmanned aerial vehicle (UAV)-assisted multiaccess edge computing (MEC) technology has garnered significant attention and has been successfully implemented in specific scenarios. The optimization of the network energy consumption in the relevant scenarios is essential for the whole system performance due to the constrained energy capacity of UAVs. However, the dynamic changes in MEC network resources make the energy consumption optimization a challenge. In this paper, a multi-UAV-multiuser MEC model is established to assess the system energy consumption, and the optimization problem of multi-UAV cooperation strategies is formulated base on the model. Then, a multi-agent deep deterministic policy gradient (MADDPG) algorithm based on deep reinforcement learning (DRL) is employed to resolve the above optimization problem. Each UAV is equivalent to a single agent that cooperates with other agents to train actors and critic evaluation networks to accomplish collaborative decision-making. In addition, a prioritized experience replay (PER) scheme is used to improve the convergence of the training process. Simulation results show that the impact of changes in different network resources on the network energy consumption by comparing the performance of different algorithms. The findings presented in this paper serve as a valuable reference for future work on system performance optimization, specifically in terms of energy efficiency.