Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing baseline models decreases considerably. Analysis indicates that current diffusion strategies are confronted with two limitations. First, these strategies only rely on short-term observations as conditions. Second, the training objective remains limited to a single denoising loss, which leads to error accumulation and causes grasping deviations. To address these limitations, this paper proposes Foresight-Conditioned Diffusion (ForeDiffusion), by injecting the predicted future view representation into the diffusion process. As a result, the policy is guided to be forward-looking, enabling it to correct trajectory deviations. Following this design, ForeDiffusion employs a dual loss mechanism, combining the traditional denoising loss and the consistency loss of future observations, to achieve the unified optimization. Extensive evaluation on the Adroit suite and the MetaWorld benchmark demonstrates that ForeDiffusion achieves an average success rate of 80% for the overall task, significantly outperforming the existing mainstream diffusion methods by approximately 20% in high difficulty tasks, while maintaining more stable performance across the entire tasks.

To meet the demands of high-capacity and low-delay services, Fifth Generation (5G) Base Stations (BSs) are typically deployed in ultra-dense configurations, especially in urban areas. While this densification enhances coverage and service quality, it also leads to substantially increased energy consumption. However, the dense deployment pattern makes BS workloads more responsive to the spatiotemporal variations in user behavior, offering opportunities for energy-saving strategies that dynamically adjust BS operation states. In this context, we propose a Delay-aware and Energy-efficient Integrated Optimization System (DEIS) based on Deep Reinforcement Learning (DRL), which jointly optimizes energy consumption and network delay while maintaining user satisfaction. DEIS leverages a real-world dataset collected from operational 5G BSs provided by partner network operators, containing both BS deployment data and high-volume user request logs. Extensive simulations demonstrate that DEIS can achieve a 41% reduction in energy consumption while ensuring reliable delay performance.

Computing Power Networks (CPNs) represent an innovative, collaborative architecture that integrates resources via the communication network, optimizing resource allocation to support service demands. Due to the increased need for services powered by artificial intelligence across various domains, CPNs are increasingly required to allocate users efficiently to appropriate servers to meet the low-latency needs of service computing. However, challenges such as users' dynamic mobility, weak communication paths, and high-dimensional solution spaces persist in optimizing user allocation in CPNs. In this context, we propose a diffusion-driven optimization approach for mobility-aware user allocation. To tackle the challenge of users' dynamic mobility, we adopt a user location prediction approach incorporating the users' movement patterns to forecast future movement, calledCAMPE. To tackle the challenge of weak communication paths, we establish the new transmission path by reconfigurable intelligent surface and enhance the quality of the communication link by adjusting the phase configurations. Moreover, faced with the challenge of high-dimensional solution spaces associated with phase adjustment and user allocation decisions, we devise an action-generation strategy based on diffusion models namedDiffUser. This approach motivates the generation of optimal solutions even in complex and dynamic environments. Finally, we conduct extensive simulations in user location prediction and system latency optimization. Compared with other solutions, the superiority of our approach has been demonstrated.

In intelligent education, cognitive diagnostic assessment is a fundamental task for evaluating students’ mastery of knowledge attributes based on their response logs. However, existing cognitive diagnostic models face several limitations. For example, the Q-matrix heavily relies on expert-defined prior knowledge and remains difficult to optimize automatically. In addition, most models assume static knowledge states, limiting their ability to capture the fine-grained dynamics of student cognition. To address these issues, this paper proposes a dynamic cognitive diagnosis model enhanced by genetic evolution (GE-QCDM). Specifically, latent knowledge attributes are discovered through a genetic algorithm, and a refined Q-matrix is generated via discrete-space search to incorporate these potential attributes. A Q-matrix enhancement strategy is further introduced to retain the accuracy of explicit attributes while improving interpretability by uncovering hidden associations. Furthermore, a dynamic attention mechanism is designed to model the interaction between learner states and question characteristics, thereby enabling a more comprehensive evaluation of students’ mastery levels. Experimental results on multiple real-world datasets demonstrate that the proposed model consistently outperforms existing methods in both accuracy and interpretability.

This study investigates the trade-off between system stability and offloading cost in collaborative edge computing. While collaborative offloading among multiple edge servers enhances resource utilization, existing methods often overlook the role of queue stability in overall system performance. To address this, a multi-hop data transmission model is developed, along with a cost model that captures both energy consumption and delay. A time-varying queue model is then introduced to maintain system stability. Based on Lyapunov optimization, a dynamic offloading algorithm (LDSO) is proposed to minimize offloading cost while ensuring long-term stability. Theoretical analysis and experimental results verify that the proposed LDSO achieves significant improvements in both cost efficiency and system stability compared to the state-of-the-art.

Web 4.0 is characterized by decentralized intelligence and blockchain integration, which introduces significant challenges in congestion management for software-defined networking (SDN). Traditional reinforcement learning (RL)-based approaches encounter inefficiencies due to limited adaptability to decentralized and delayed online learning capabilities. To address these issues, we propose an Active Inference-based Reinforcement Learning (AIRL) framework that integrates generative modelling with RL for enhanced decision-making in congestion control. By leveraging blockchain-enabled secure model trading and predictive intelligence, AIRL ensures adaptive policy optimization while maintaining transparency and trust in decentralized network environments. The proposed method demonstrates substantial improvements in delay reduction, packet loss, and efficient utilization of network resources under various dynamic scenarios.

To address the challenges of small target features being less prominent, susceptibility to background interference, and sample imbalance in road traffic sign detection, which leads to insufficient model detection accuracy, as well as the high complexity of current object detection models that struggle to operate efficiently on resource-constrained edge devices, we propose a traffic sign detection model based on GCA-YOLO. By adding small target detection layers and removing large target detection layers, the model enhances its small target detection capabilities and reduces its parameter size. The introduction of the T-BiFPN (Tiny-BiFPN) structure improves multi-scale feature fusion, while the C2f-CP module increases computational efficiency on edge devices. The GCA (Global Coordinate Attention) mechanism enhances feature extraction, and the Focaler-CIoU loss function enables the model to focus more on difficult samples and accelerate the convergence of bounding boxes. Experimental results show the superiorities of the proposed GCA-YOLO that compared to YOLOv8n, GCA-YOLO improves precision, recall, mAP@50, and mAP@50:95 by 8.6%, 6.1%, 8.7%, and 6.2%, respectively, while reducing the model's parameter count and size by 38.57% and 33.21%, respectively.

Owing to its rapid progress and broad application prospects, few-shot action recognition has attracted considerable interest. However, current methods are predominantly based on limited single-modal data, which does not fully exploit the potential of multimodal information. This paper presents a novel framework that actively identifies reliable modalities for each sample using task-specific contextual cues, thus significantly improving recognition performance. Our framework integrates an Active Sample Inference (ASI) module, which utilizes active inference to predict reliable modalities based on posterior distributions and subsequently organizes them accordingly. Unlike reinforcement learning, active inference replaces rewards with evidence-based preferences, making more stable predictions. Additionally, we introduce an active mutual distillation module that enhances the representation learning of less reliable modalities by transferring knowledge from more reliable ones. Adaptive multimodal inference is employed during the meta-test to assign higher weights to reliable modalities. Extensive experiments across multiple benchmarks demonstrate that our method significantly outperforms existing approaches.

Dense colored point clouds enhance visual perception and are of significant value in various robotic applications. However, existing learning-based point cloud upsampling methods are constrained by computational resources and batch processing strategies, which often require subdividing point clouds into smaller patches, leading to distortions that degrade perceptual quality. To address this challenge, we propose a novel 2D-3D hybrid colored point cloud upsampling framework (GaussianPU) based on 3D Gaussian Splatting (3DGS) for robotic perception. This approach leverages 3DGS to bridge 3D point clouds with their 2D rendered images in robot vision systems. A dual scale rendered image restoration network transforms sparse point cloud renderings into dense representations, which are then input into 3DGS along with precise robot camera poses and interpolated sparse point clouds to reconstruct dense 3D point clouds. We have made a series of enhancements to the vanilla 3DGS, enabling precise control over the number of points and significantly boosting the quality of the upsampled point cloud for robotic scene understanding. Our framework supports processing entire point clouds on a single consumer-grade GPU, eliminating the need for segmentation and thus producing high-quality, dense colored point clouds with millions of points for robot navigation and manipulation tasks. Extensive experimental results on generating million-level point cloud data validate the effectiveness of our method, substantially improving the quality of colored point clouds and demonstrating significant potential for applications involving large-scale point clouds in autonomous robotics and human-robot interaction scenarios.

Land-air bimodal robots (LABR) are gaining attention for autonomous navigation, combining high mobility from aerial vehicles with long endurance from ground vehicles. However, existing LABR navigation methods are limited by suboptimal trajectories from mapping-based approaches and the excessive computational demands of learning-based methods. To address this, we propose a two-stage lightweight framework that integrates global key points prediction with local trajectory refinement to generate efficient and reachable trajectories. In the first stage, the Global Key points Prediction Network (GKPN) was used to generate a hybrid land-air keypoint path. The GKPN includes a Sobel Perception Network (SPN) for improved obstacle detection and a Lightweight Attention Planning Network (LAPN) to improves predictive ability by capturing contextual information. In the second stage, the global path is segmented based on predicted key points and refined using a mapping-based planner to create smooth, collision-free trajectories. Experiments conducted on our LABR platform show that our framework reduces network parameters by 14% and energy consumption during land-air transitions by 35% compared to existing approaches. The framework achieves real-time navigation without GPU acceleration and enables zero-shot transfer from simulation to reality during deployment.

Vehicle Edge Computing (VEC) can effectively improve the efficiency of vehicle task calculation and offloading by integrating edge computing and the Internet of Vehicles. However, current research in VEC mostly focuses on device collaboration within single-hop or two-hop ranges, limiting the additional performance gain and load balancing provided by multi-hop device collaboration. In this study, an Edge Digital Twin assisted Multi-hop Task Offloading Scheme (EDT_MTOS) is proposed to enhance the execution efficiency of vehicle tasks by establishing an edge digital twin layer for virtual mapping of vehicles and edge servers. Firstly, the multi-hop task offloading problem is transformed into a cost optimization problem related to delay and energy consumption under the constraint of load balancing. Secondly, a dynamic collaboration knowledge graph based on digital twin knowledge mapping is introduced to select collaborative device sets for the upload and return links within the multi-hop range. Then, a value iteration algorithm based on the maximum link quality is proposed to realize the dynamic collaboration knowledge graph. Furthermore, a task offloading solution algorithm is proposed based on Dynamic collaboration Knowledge Graph and Double Deep Q-Network (DKG_DDQN). Finally, the simulation results demonstrate that the proposed offloading algorithm can reduce vehicle task processing costs by 33.77% and 26.53% in an idle scenario, and by 27.60% and 26.21% in a busy scenario, compared to state-of-the-art collaborative algorithms such as COOR and DRL-COMV, respectively.

Concept-cognitive learning (CCL) is a paradigm that simulates human concept learning by processing given cues through specific cognitive models. However, existing CCL models face significant limitations, such as weak correlations between attributes and decisions, high redundancy within the concept space, and suboptimal learning performance. To address these issues, this article introduces an Attribute Fluctuation-Based CCL (AFFCCL) model. First, a novel measurement method for attribute fluctuation is proposed, based on the variation range of attribute membership degrees. To mitigate redundancy in the concept space, a fuzzy granular concept space is constructed using the concept contribution degree. Second, the model leverages the semantic richness of concepts by integrating similar fuzzy granular concepts, thereby constructing a clustering space. From this, upper and lower approximation spaces are derived. Finally, extensive experiments conducted on multiple benchmark datasets demonstrate that the proposed AFFCCL model outperforms representative fuzzy CCL models, neural network-based classifiers, and traditional similarity-based approaches in termsof accuracy, interpretability, and robustness.

Mobile Edge Caching (MEC) can potentially alleviate Internet transmission congestion by delivering content at the network edge. However, current MEC solutions suffer from low resource utilization efficiency and often fail to meet user Quality of Experience (QoE), primarily due to dynamic user requests and obsessive pursuit of direct caching hits. Given the prevalence of recommendation systems, users often lack precise requests when using recommendation-based applications like TikTok and Taobao, insted passively enjoying recommended content. In this paper, we introduce a recommendation-enabled MEC architecture to enhance resource utilization and QoE. We develop a recommendation-enabled soft caching model and formulate the optimization problem as maximizing joint system revenue. To address this, we propose an attention-assisted federated learning deep Q-network algorithm. We conduct the simulations by using the real-world MIND dataset. The results demonstrate that our proposed algorithm outperforms existing baselines, demonstrating its effectiveness in improving resource utilization and QoE.

As a robust platform for mobile edge computing, 5G networks, while delivering high data rates and low latency, face a pressing concern with the escalating energy consumption of 5G Base Stations (BSs). To address this issue, we propose an algorithm called the Environmental Protection Prophet (EPP), based on the clustered and geographically inclined user request patterns. The EPP algorithm groups users according to their proximity to BSs and utilizes edge caching to reduce response times for user requests. This clustering strategy optimizes user allocation while minimizing BSs' energy consumption, all while meeting user Quality of Service (QoS) requirements. Simulation experiments illustrate the potential for energy savings and latency reduction, particularly in densely populated urban areas. The findings provide valuable insights for the design of energy-efficient 5G networks, concurrently addressing environmental concerns and meeting user performance expectations.

Underwater acoustic sensor networks (UASNs) have been widely deployed in many areas, such as marine ranching, naval applications, and marine disaster warning systems. The security of UASNs, particularly insider threats, is of growing concern. Internal attacks carried out via compromised normal nodes are more damaging and stealthy than external attacks, such as signal stealing, data decryption, and identity forgery. As a security mechanism for internal threat detection based on interaction data, trust models have proven to enhance the security of UASNs. However, traditional trust models lack sufficient scalability when faced with movable underwater devices, heterogeneous network environments, and variable attack patterns. Therefore, in this paper, a novel trust model based on federated deep reinforcement learning is proposed for UASNs. First, the evidence acquisition mechanism, including communication, energy, and data evidence, is improved based on existing ones to better accommodate the topological dynamics of UASNs. Second, acquired trust evidence is fed into the corresponding deep reinforcement learning-based local trust model to accomplish trust prediction and model training. Finally, a federated learning-based update method periodically aggregates and updates the parameters of the local models. The experimental results prove that the proposed scheme exhibits satisfactory performance in terms of improving trust prediction accuracy and energy efficiency.

The popularity of microservices in industry has sparked much attention in the research community. Despite significant progress in microservice deployment for resource-intensive services and applications at the network edge, the intricate dependencies among microservices are often overlooked, and some studies underestimate the importance of system context extraction in deployment strategies. This paper addresses these issues by formulating the microservice deployment problem as a max-min problem, considering system cost and quality of service (QoS) jointly. We first study the attention-based microservice representation (AMR) method to achieve effective system context extraction. In this way, the contributions of different computing power providers (users, edge servers, or cloud servers) in the networks can be effectively paid attention to. Subsequently, we propose the attention-modified soft actor-critic (ASAC) algorithm to tackle the microservice deployment problem. ASAC leverages attention mechanisms to enhance decision-making and adapt to changing system dynamics. Our simulation results demonstrate ASAC's effectiveness, prioritizing average system cost and reward compared to the other state-of-the-art algorithms.

Mobile edge-cloud computing networks can provide distributed, hierarchical, and fine-grained resources, and have become a major goal for future high-performance computing networks. The key is how to jointly optimize service caching and computation offloading. However, the joint service caching and computation offloading problem faces three significant challenges of dynamic tasks, heterogeneous resources, and coupled decisions. In this paper, we investigate the issue of joint service caching and computation offloading in mobile edge-cloud computing networks. Specifically, we formulate the optimization problem as minimizing the long-term average service latency, which is NP-hard. To solve the problem, we conduct in-depth theoretical analyses and decompose it into two sub-problems: service caching processing and computation offloading processing. We are the first to propose a novel hierarchical deep reinforcement learning algorithm to solve the formulated problem, where multiple edge agents and a cloud agent collaboratively determine the caching-action and offloading-action, respectively. The results obtained through trace-driven simulations reveal that the proposed framework outperforms several prevailing algorithms concerning the average service latency across diverse scenarios. In a complex real scenario, our framework achieves an approximately 33% convergence improvement and a remarkable 39% reduction in the average service latency when compared to reinforcement learning-based algorithms.

Massive device connections in upcoming 6G networks have led to a sharp increase in network traffic volume, posing significant challenges in providing reliable performance guarantees, e.g., low latency. The Computing Power Network (CPN) is a new framework for resource integration involving multiple parties. It integrates the resources of various owners via the network, providing users with efficient and adaptable services. Due to the uncertainty of the signal quality, the majority of existing studies do not adequately organize the topology of user allocation in CPNs when optimizing network resources. Reconfigurable Intelligent Surface (RIS) is a new type of network node for constructing future smart radio environments with high spectral efficiency and nearly zero energy consumption that can offer new access options for user allocation in CPNs. In this paper, we investigate the user access allocation in a RIS-assisted Ad Hoc Edge (RAHE) scenario where the users are with service-intensive demands. To maximize the overall service tasks of the system constrained by a service time threshold, we propose a RIS-assisted interval scheduler strategy (RS3) approach to balancing the whole system service completion and total latency. Specifically, RS3is a graph-theoretic optimization method based on the interval scheduling problem. The numerical simulation results demonstrate that our proposed RS3approach is superior to commonly utilized methods in terms of the number of serves given the service time constraint.

Beyond 5G applications, future 6G services would need to support very large data volumes for emerging industry verticals, such as holographic-type communications, as well as time-sensitive services, e.g., industrial control. Network slicing is the key technology to deliver such customizable services. Slices and their dedicated resources should be provisioned optimally where the services will be run with low network latencies and associated expenses. However, the user dynamics on resource demands within and between slices result in different resource re-allocation triggers, ultimately lead to distinct mobility patterns, e.g., scaling, migration, where sufficient resources must be transferred. Efficient slice mobility requires increasing flexibility in network operation and management to ensure the customized QoS while minimizing the corresponding mobility cost. In this paper, a prediction-based intelligent network analytic is proposed to facilitate the optimized network slice mobility scheme. We will investigate how to utilize the user and network prediction as the auxiliary information to make the slice mobility decision with the objective of maximizing the long-term profits while minimizing the latency and mobility cost. Finally, we evaluate the proposed prediction-based network slice mobility scheme in a simulated environment and compare its performance in terms of system costs, revenues, and profits with two benchmark solutions.

Recently, we have observed an explosion in the intellectual capacity of user equipment, coupled by a meteoric rise in the need for very demanding services and applications. The majority of the work leverages edge computing technologies to accomplish the quick deployment of microservices, but disregards their inter-dependencies. In addition, while constructing the microservice deployment approach, several research disregard the significance of system context extraction. The microservice deployment issue (MSD) is stated as a max-min problem by concurrently evaluating the system cost and service quality. This research first analyzes an attention-based microservice representation approach for extracting system context. The attention-modified soft actor-critic method is proposed to the MSD issue. The simulation results reveal the ASAC algorithm's priorities in terms of average system cost and system reward.

Edge computing (EC) extends the ability of cloud computing to the network edge to support diverse resource-sensitive and performance-sensitive IoT applications. However, due to the limited capacity of edge servers (ESs) and the dynamic computing requirements, the system needs to dynamically update the task allocation policy according to real-time system states. Service migration is essential to ensure service continuity when implementing dynamic task allocation. Therefore, this article investigates the long-term dynamic task allocation and service migration (DTASM) problem in edge-cloud IoT systems where users’ computing requirements and mobility change over time. The DTASM problem is formulated to achieve the long-term performance of minimizing the load forwarded to the cloud while fulfilling the seamless migration constraint and the latency constraint at each time of implementing the DTASM decision. First, the DTASM problem is divided into two subproblems: 1) the user selection problem on each ES and 2) the system task allocation problem. Then, the DTASM problem is formulated as a Markov decision process (MDP) and an approach based on deep reinforcement learning (DRL) is proposed. To tackle the challenge of vast discrete action spaces for DTASM task allocation in the system with a mass of IoT users, a training architecture based on the twin-delayed deep deterministic policy gradient (DDPG) is employed. Meanwhile, each action is divided into a differentiable action for policy training and one mapped action for implementation in the IoT system. Simulation results demonstrate that the proposed DRL-based approach obtains the long-term optimal system performance compared to other benchmarks while satisfying seamless service migration.

With the advancement of the user application service demands, the IoT system tends to offload the tasks to the edge server for execution. Most of the current studies on edge computation offloading ignore the dependencies between components of the application. The few pieces of research on edge computing offloading which focus on the topology of application are primarily applied in single-user scenarios. Unlike previous work, our work mainly solves dependent task offloading with edge computing in multiuser scenarios, which is more in line with reality. In this article, the dependent task offloading problem is modeled as a Markov decision process (MDP) first. Then, we propose an actor–critic mechanism with two embedding layers for directed acyclic graphs (DAGs)-based multiple dependent tasks computation offloading, namely, ACED, by jointly considering the topology of the application and the channel interference between several users. Finally, the results of simulations also show the priorities of the proposed ACED algorithm.

With the development of network technology and the surge in demand, the speed and throughput of data and applications are leading to the skyrocketing increase in traffic. The communication and collaboration between heterogeneous edge servers are indispensable. In this scenario with heterogeneous edges, there is a common understanding on the fact that an effective edge caching algorithm could play the role of enabler to reduce the network resource consumption and content fetch delay. However, most of the existing studies on multi-agent caching methods focus more on the overall situation, while ignoring the mutual influence between different agents. In this context, we model the edge caching content replacement problem as a Markov process and deploy attention mechanism based on the Actor-Attention-Critic algorithm to realize a neighboring-aware edge caching (NAEC) strategy. The proposed method makes full use of the communication between base stations to exchange neighboring information, so that we can reduce the pressure on the backbone and further improve user satisfaction. The simulation results have verified the feasibility and effectiveness of the proposed algorithm.

Recently, integrated with the advanced communication technologies (e.g., 5G) and artificial intelligence (AI), mobile-edge intelligence (MEI) is regarded as the promising method to deal with the emerging challenges. Specifically, Device-to-Device (D2D) communications have been put forward to reduce the traffic pressure while extending cellular network capacity. However, the stability of the social network is important for the design of efficient and reliable traffic offloading strategy, which is often absent from the related work. Besides, most existing studies merely model the relation between a node pair as a binary or continuous value, neglecting the rich information between users. Moreover, many traditional models are conducted based on small-scale data sets or online Internet services, severely confining their applications in the D2D scenario. Thus, it is necessary to understand the network structure and select the key users to address the aforementioned challenges. In this article, we first propose a network representation model, named MPPT, to regard the multidimensional relations as a probability in a third-order (3-D) tensor space. Then, a mobile D2D social community is derived by integrating an edge base station (BS) and the nearby D2D users, and develop an anchored user selection algorithm to maintain the stability of multiple D2D social communities by choosing and retaining critical users adaptively under the limited network resources. Finally, we devise a probability-based onion layers anchored$(k,r)$-core (P-OLAK) algorithm to identify the anchor users. The large-scale data sets-based experimental results show the superiorities of the proposed methods.

In order to meet the growing demands for multimedia service access and release the pressure of the core network, edge caching and device-to-device (D2D) communication have been regarded as two promising techniques in next generation mobile networks and beyond. However, most existing related studies lack consideration of effective cooperation and adaptability to the dynamic network environments. In this article, based on the flexible trilateral cooperation among user equipment, edge base stations and a cloud server, we propose a D2D-assisted heterogeneous collaborative edge caching framework by jointly optimizing the node selection and cache replacement in mobile networks. We formulate the joint optimization problem as a Markov decision process, and use a deep Q-learning network to solve the long-term mixed integer linear programming problem. We further design an attention-weighted federated deep reinforcement learning (AWFDRL) model that uses federated learning to improve the training efficiency of the Q-learning network by considering the limited computing and storage capacity, and incorporates an attention mechanism to optimize the aggregation weights to avoid the imbalance of local model quality. We prove the convergence of the corresponding algorithm, and present simulation results to show the effectiveness of the proposed AWFDRL framework in reducing average delay of content access, improving hit rate and offloading traffic.

With the proliferation of mobile device users, the Device-to-Device (D2D) communication has ascended to the spotlight in social network for users to share and exchange enormous data. Different from classic online social network (OSN) like Twitter and Facebook, each single data file to be shared in the D2D social network is often very large in data size, e.g., video, image or document. Sometimes, a small number of interesting data files may dominate the network traffic, and lead to heavy network congestion. To reduce the traffic congestion and design effective caching strategy, it is highly desirable to investigate how the data files are propagated in offline D2D social network and derive the diffusion model that fits to the new form of social network. However, existing works mainly concern about link prediction, which cannot predict the overall diffusion path when network topology is unknown. In this article, we propose D2D-LSTM based on Long Short-Term Memory (LSTM), which aims to predict complete content propagation paths in D2D social network. Taking the current user's time, geography and category preference into account, historical features of the previous path can be captured as well. It utilizes prototype users for prediction so as to achieve a better generalization ability. To the best of our knowledge, it is the first attempt to use real world large-scale dataset of mobile social network (MSN) to predict propagation path trees in a top-down order. Experimental results corroborate that the proposed algorithm can achieve superior prediction performance than state-of-the-art approaches. Furthermore, D2D-LSTM can achieve 95% average precision for terminal class and 17% accuracy for tree path hit.

Duplicated download has been a big problem that affects the users' quality of service/experience (QoS/QoE) of current mobile networks. Edge caching and Device-to-Device communication are two promising technologies to release the pressure of repeated traffic downloading from the cloud. There are many researches about the edge caching policy. However, these researches have some limitations in the real scenarios. Traditional methods are lacking the self-adaptive ability in the dynamic environment and privacy issues will occur in centralized learning methods. In this paper, based on the virtue of Deep Q-Network (DQN), we propose a weighted distributed DQN model (WDDQN) to solve the cache replacement problem. Our model enables collaboratively to learn a shared predictive model. Trace-driven simulation results show that our proposed model outperforms some classical and state-of-the-art schemes.

Edge caching is an emerging technology for addressing massive content access in mobile networks to support rapidly growing Internet-of-Things (IoT) services and applications. However, most current optimization-based methods lack a self-adaptive ability in dynamic environments. To tackle these challenges, current learning-based approaches are generally proposed in a centralized way. However, network resources may be overconsumed during the training and data transmission process. To address the complex and dynamic control issues, we propose a federated deep-reinforcement-learning-based cooperative edge caching (FADE) framework. FADE enables base stations (BSs) to cooperatively learn a shared predictive model by considering the first-round training parameters of the BSs as the initial input of the local training, and then uploads near-optimal local parameters to the BSs to participate in the next round of global training. Furthermore, we prove the expectation convergence of FADE. Trace-driven simulation results demonstrate the effectiveness of the proposed FADE framework on reducing the performance loss and average delay, offloading backhaul traffic, and improving the hit rate.

In recent years, due to the rapid development of mobile multimedia services integrated with online social networks, how to select influential users (seed users) to promote multimedia content propagation has attracted more and more attention. However, little work has been done for large-scale offline face-to-face (Device-to-Device, D2D) content propagation. Previous studies have much limitations in this scenario due to their small-scale or synthetic data sets. In this paper, we propose the algorithm of Weighted LeaderRank with Neighbors (WLRN) to select seed users in D2D mobile social networks with accuracy to promote offline multimedia content propagation. We consider the importance of users' 2-hop neighbors. The evaluation of our algorithm is carried out on a realistic large-scale D2D data set based on the high performance computing platform of Apache Spark. The experiment results show the efficiency of the algorithm both in terms of content propagation coverage and time cost.

To satisfy rapidly increasing multimedia service requests from mobile users, content caching at the network edges (e.g., base stations) has been regarded as a promising technique in future mobile networks. In this paper, by virtue of Deep Reinforcement Learning (DRL) with respect to solving complicated control problems, we propose a framework on Double Deep Q-Network for cooperative edge caching in mobile networks. Particularly, we aim at minimizing the long-term average content fetching delay of mobile users without requiring any priori knowledge of content popularity distribution. Trace-driven simulation results show that our proposed framework outperforms some existing caching algorithms, including Least Recently Used (LRU), Least Frequently Used (LFU) and First-In First-Out (FIFO) caching strategies by 7%, 11% and 9% improvements, respectively. Besides, our proposed work is further shown that only average 4% performance loss exists compared to an omniscient oracle algorithm.

Edge caching is a promising method to deal with the traffic explosion problem towards future network. In order to satisfy the demands of user requests, the contents can be proactively cached locally at the proximity to users (e.g., base stations or user device). Recently, some learning-based edge caching optimizations are discussed. However, most of the previous studies explore the influence of dynamic and constant expanding action and caching space, leading to unpracticality and low efficiency. In this paper, we study the edge caching optimization problem by utilizing the Double Deep Q-network (Double DQN) learning framework to maximize the hit rate of user requests. Firstly, we obtain the Device-to-Device (D2D) sharing model by considering both online and offline factors and then we formulate the optimization problem, which is proved as NP-hard. Then the edge caching replacement problem is derived by Markov decision process (MDP). Finally, an edge caching strategy based on Double DQN is proposed. The experimental results based on large-scale actual traces show the effectiveness of the proposed framework.

Content transmission over Mobile Opportunistic Networks is in the manner of “store-carry-forward” due to opportunistic contacts between node pairs. Most of the existing works focus on the “forward” process rather than how to “store” content in the network. Moving contents to the edge of network can significantly offload network traffic while satisfying content requests from mobile users locally. In this paper, considering the preference of nodes for different content items, we propose Fetcher Selection Greedy Algorithm (FSGA), a novel strategy to select a subset of nodes for cooperative caching scheme by evaluating each node utility in the network. To improve the cooperative caching opportunity and reduce the traffic pressure of core network, we introduce the Heterogeneous Mobile Opportunistic Networks (HMONs)architecture by deploying an Access Point (AP)which is acting as a bridge to connect the core network and mobile nodes. The mobile nodes in HMONs are segmented into two kinds, one is called$Fetchers$which are responsible for caching content from AP then forwarding them to the other ones, and the other mobile nodes are$Regulars$. We formulate and analyze the average content transmission delay in different transmission conditions. Finally, our experiment results indicate that the cooperative caching scheme improves the network performance.

Caching at the edge of mobile networks can significantly offload network traffic while satisfying content requests from mobile users locally. The contents can be requested from the proximity users via Device-to-device (D2D) communications while proactive caching the popular content to local users. However, the assumptions that content popularity is equal to user preference in several existing studies, which are invalid and not rigorous due to the fact that content popularity is calculated by the statistic of user requests within a certain period while user preference reflects the probability of a content requested by the individual user. Motivated by this, in this paper, we study the edge caching optimization of hierarchical wireless networks. Our aiming is to maximize the size of content offload by D2D communications. In particular, the edge caching policy with D2D sharing model based on the analysis of user mobility and social relationship is derived. We first prove the problem is NP-hard and then formulate it as a Markov Decision Process (MDP) problem, finally a Q-learning based distributed content replacement strategy is proposed. The large-scale real trace based experiment results show the effectiveness of our proposed framework.

Mobile opportunistic network (MON) is a new paradigm which exploits node contacts to forward data, enabling numerous and impressive applications. The data copy spraying scheme is a challenging problem in MON, due to the mobility of nodes and lack of global knowledge, it hence captures great interests from research communities. Traditional algorithms allocate data copies with node's statistical information and neglect the temporal contact feature, resulting in a poor delivery performance. We propose AS, an adaptive data copy spraying scheme in MON. AS adjusts the number of copies dynamically based on the temporal contact feature among nodes. Theoretical analysis verifies that AS achieves a lower mean delivery delay than SprayWait, one of the state-of-the-art works. Simulation results show that AS improves the packet delivery ratio simultaneously.