Mobile video has become one of the most valuable services in next-generation heterogeneous networks, and users? quality of experience (QoE) is recognized as its important performance metric. In this paper, we propose an adaptive bitrate (ABR) algorithm to achieve improvement of the timevarying QoE determinants during mobile video playback. Since watching video will bring mobile data charges to the users, the traffic consumed by video downloads should be customized to a user-specified amount. To this end, we first analyze the realworld traces, and find the key factors to formulate a continuous QoE model. Then, we introduce a traffic-aware rate adaptation strategy (TARA). Given that users are aware of their realtime capabilities when watching mobile video, TARA tries to make the ABR process get smarter with what users really want with traffic constraints. Third, a centralized reinforcement learning (RL) approach is proposed for the joint optimization of TARA, which aims to maximize the designed QoE metric and deliver the expected viewing experience to users. Results of experiments driven by both the simulated and real-world network traces reveal the efficiency of the proposed TARA strategy and demonstrate its significant performance improvement as compared to the state-of-the-art ABR algorithms.

Border Gateway Protocol (BGP) is a standard inter-domain routing protocol for the Internet that conveys network layer reachability information and establishes routes to different destinations. The BGP protocol exhibits security design defects, such as an unconditional trust mechanism and the default acceptance of BGP route announcements from peers by BGP neighboring nodes, easily triggering prefix hijacking, path forgery, route leakage, and other BGP security threats. Meanwhile, the traditional BGP security mechanism, relying on a public key infrastructure, faces issues like a single point of failure and a single point of trust. The decentralization, anti-tampering, and traceability advantages of blockchain offer new solution ideas for constructing secure and trusted inter-domain routing mechanisms. In this paper, we summarize the characteristics of BGP protocol in detail, sort out the BGP security threats and their causes. Additionally, we analyze the shortcomings of the traditional BGP security mechanism and comprehensively evaluate existing blockchain-based solutions to address the above problems and validate the reliability and effectiveness of blockchain-based BGP security methods in mitigating BGP security threats. Finally, we discuss the challenges posed by BGP security problems and outline prospects for future research.

Edge computing nodes close to the perception layer of IoT systems are susceptible to data leaks and unauthorized access. To address these security concerns, this paper proposes a trusted IoT data sharing method based on secure multi-party computation (SMC). By running a reliable third-party blockchain service at edge computing nodes, the data computation relationships between IoT devices in the perception layer are registered in blockchain smart contracts. This constructs a publicly verifiable IoT data sharing method combining on-chain audit verification and off-chain SMC. Furthermore, a Bloom filter is maintained at the on-chain smart contract layer to track the trust status of IoT devices in the perception layer, filtering out non-trustworthy device requests and enabling secure data sharing among trusted devices. Comparative analysis and performance tests demonstrate the proposed method’s high computational efficiency for IoT device nodes.

Container technology enables rapid deployment of computing services, while edge computing reduces the latency of task computing and improves performance. However, there are limits to the types, number and performance of containers that can be supported by different edge servers, and a sensible task deployment strategy and rapid response to the policy is a must. Therefore, by jointly optimizing the strategies of task deployment, offloading decisions, edge cache and resource allocation, this paper aims to minimize the overall energy consumption of a mobile edge computing (MEC) system composed of multiple mobile devices (MD) and multiple edge servers integrated with different containers. The problem is formalized as a combinatorial optimization problem containing multiple discrete variables when constraints of container type, transmission power, latency, task offloading and deployment strategies are satisfied. To solve the NP-hard problem and achieve fast response for sub-optimal policy, this paper proposes an energy-efficient edge caching and task deployment policy based on Deep Q-Learning (DQCD). Firstly, the pruning and optimization of the exponential action space consisting of offloading decisions, task deployment and caching policy is completed to accelerate the training of the model. Then, the iterative optimization of the training model is completed using a deep neural network. Finally, the sub-optimal task deployment, offloading and caching policies are obtained based on the training model. Simulation results demonstrate that the proposed algorithm is able to converge the model in very few iterations and results in a great improvement in terms of reducing system energy consumption and policy response delay compared to other algorithms.

With the development of next-generation communication technologies and smart handheld devices, mobile services have multiplied the global network traffic. Due to the subjectivity of user expectations and the instability of wireless environments, the Quality of Experience (QoE) of the mobile service is not always satisfactory. Recently, many optimization schemes have been proposed to evaluate and improve the QoE, but it is still challenging to deliver advanced mobile services without addressing individual preferences and system integrity. To deal with these challenges, this article considers user preferences in wireless communication resource management, including the preference-aware optimization for user side adaptive streaming, coordinated bandwidth allocation, and network side caching content selection. Moreover, the continuous QoE evaluation models are investigated to act as the performance indicator of the optimization system. These proposals can provide a new perspective for future research on preference-aware resource management and can make the optimization system get smarter with what users really want.

Meta-path-based heterogeneous graph neural networks have received widespread attention for better mining the similarities between heterogeneous nodes and for discovering new recommendation rules. Most existing models depend solely on node IDs for learning node embeddings, failing to leverage attribute information fully and to clarify the reasons behind a user’s interest in specific items. A heterogeneous graph neural network for recommendation named MIMA (multi-feature interaction meta-path aggregation) is proposed to address these issues. Firstly, heterogeneous graphs consisting of user nodes, item nodes, and their feature nodes are constructed, and the meta-path containing users, items, and their attribute information is used to capture the correlations among different types of nodes. Secondly, MIMA integrates attention-based feature interaction and meta-path information aggregation to uncover structural and semantic information. Then, the constructed meta-path information is subjected to neighborhood aggregation through graph convolution to acquire the correlations between different types of nodes and to further facilitate high-order feature fusion. Furthermore, user and item embedding vector representations are obtained through multiple iterations. Finally, the effectiveness and interpretability of the proposed approach are validated on three publicly available datasets in terms of NDCG, precision, and recall and are compared to all baselines.