This paper presents a dual-cell configuration model that incorporates dual reconfigurable intelligent surfaces (RISs) to boost the secure transmission efficacy of joint transmission (JT) coordinated multipoint (CoMP) systems utilizing non-orthogonal multiple access (NOMA) in downlink communications. Our investigation primarily centers on the joint optimization of power allocation parameters for base stations (BSs), active beamforming, and passive beamforming after user grouping (UG) configuration, with the aim of enhancing system secrecy performance while conforming to exacting quality-of-service (QoS) standards and ensuring effective successive interference cancellation (SIC). The problem is inherently non-convex, complicating direct solutions. To address intrinsic complexity, we utilize the built-in function fmincon in MATLAB to improve the power allocation coefficients (PAC). By using the successive convex approximation (SCA) technique, non-convex constraints are transformed into convex constraints, thereby converting the optimization subproblem of active beamforming into a solvable second-order cone programming (SOCP) problem. Meanwhile, semidefinite programming (SDP) is applied to address the problem of passive beamforming design. Additionally, by integrating an alternating optimization (AO) algorithm, we ensure robustness and efficiency under practical hardware impairments (HWI). Simulation data reveal that the RIS-assisted CoMP-NOMA framework greatly improves the secrecy rate compared to traditional CoMP-NOMA systems lacking RIS, as well as the RIS-NOMA scheme.

Antenna tuning plays an essential role in ensuring high quality wireless communications. Targeting for higher Quality of Service (QoS), many existing network antenna tuning schemes are based on expert knowledge, rule-based policies or conventional optimization theory. However, maximizing the traffic-related QoS does not guarantee that all customers experience good services. In addition, existing schemes are often limited to some handcrafted rules or heuristics and lack of adaptability especially in a time-varying environment. Quality of Experience (QoE), a user-centric metric, can better measure users' satisfaction for services in wireless networks. This paper proposes the cooperative tuning of antennas based on QoE, a paradigm shift from network-centric QoS to user-centric QoE domain. In a normal cellular network, besides the need of improving the overall QoE, it requires handling faults from different cells. As Multi-agent Reinforcement Learning (MARL) has the capability of self-learning the dynamics of environment, we propose an antenna configuration algorithm based on multi-goal MARL. In our framework, agents from different cells not only need to cooperate with each other to achieve the global goal of increasing the overall QoE of the wireless network but also complete some personal goals by combating the faults encountered in their own cells. To accelerate the training efficiency, we introduce a novel two-stage curriculum learning. To reduce the collection time of each QoE sample, we develop an accurate and timely QoE/QoS mapping model with the cascading of a Random Forest Classifier (RFC) and a Deep Neural Network (DNN) (abbreviated as RFC-DNN), which can help us obtain QoE by collecting QoS measurements and perform QoE-based antenna configurations with smaller time granularity. Our proposed RFC-DNN model can reduce the time by 70% when predicting the QoE of a single sample. A huge amount of time will be saved in MARL when tens of thousands of transitions/samples need to be collected. The performance results show that our proposed antenna tuning schemes can not only address specific faults in each cell, but also significantly improve the global average QoE with a faster and more stable convergence speed.

Mobile edge computing (MEC) holds great promise as an effective solution that empowers resource-constrained intelligent applications to transfer computation-intensive operations to neighboring edge servers. To realize its potential, reconfigurable intelligent surface (RIS) provides high spectral and energy efficiency, can effectively reduce the computation costs. This paper discusses a joint computation offloading and power allocation strategy for non-orthogonal multiple access (NOMA) based MEC scenario assisted by RIS. First, we formulate a cost minimization problem which considers task buffering delay, power consumption, and task queue length constraints. Then, we use Lyapunov optimization method to transform the task queue length constraint into a queue stability problem. Finally, a Markov decision process (MDP) model and a double deep Q-network (DDQN) based computation offloading and power allocation (DCOPA) algorithm are proposed to obtain optimal computation offloading strategy and achieve the system’s cost objective. Through simulation results, it is demonstrated that the proposed method can effectively reduce the computation offloading delay and has a lower computation cost than other methods. The algorithm is effective in both convergence and long-term performance.

With the development of the Internet of Vehicles(IoV), the combination of networks and vehicles has brought great convenience to people. However, hackers can attack vehicles through technical loopholes in the external network, which seriously affects the driving safety of vehicles. In this paper, we propose a new intrusion detection system (IDS) framework named the Leading Model and Confidence Decision Method (LMCDM). The LMCDM is built on three distinct machine learning models(Extreme Gradient Boosting (XGBoost), random forest (RF), and decision tree (DT)) to select the model exhibiting the best identification performance across attack types. Furthermore, the LMCDM combines prediction confidence to facilitate precise predictions. Finally, the LMCDM model was assessed using the CICIDS2017 dataset, and relative to other IDS systems, F1 scores demonstrated an improvement of no less than 0.88%. The experimental results show the effectiveness of LMCDM in external network intrusion detection.

With the rapid development of mobile communications services and applications, deep edge networks (DENs) have become a new paradigm for addressing data traffic and network delay by combining mobile edge computing (MEC) and artificial intelligence (AI). In this network, edge caching can provide low-latency and reliable services in resource-constrained scenarios by caching content in the wireless access points (APs). In this paper, we propose a joint cooperative caching replacement and resource allocation algorithm based on a multi-agent deep deterministic policy gradient (MADDPG), which aims to minimize the average content download delay. The proposed algorithm regards each AP as a reinforcement learning agent that receives diverse state information (e.g., user request behaviors, cache status updates, content popularity information, and network conditions) to learn the caching replacement and bandwidth resource allocation strategy to maximize system rewards. Simulation results show that the proposed algorithm can efficiently decrease global content download delay, improve network efficiency, and enhance the user experience when compared to the benchmark algorithm.

With the development of telecommunication technology and the popularity of intelligent devices, user experience in cellular network has become the primary factor of concern. At the same time, network operators are plagued by two problems: Prediction of users real-time experience and find network parameters that have a decisive impact on user experience. We proposed a novel scheme for user experience prediction to deal with these two problems. Causal structure learning for cellular networks was used to analyze numerous performance indicators (KPIs) collected from base stations and key quality indicators (KQIs). Through causal structure learning, a directed causal graph based on the association between KPIs and KQI can be obtained. This causal structure can be embedded in graph attention network. Among them, attention mechanism was selected to further strengthen the correlation between parameters. This correlation between each KPI and between KPIs and KQI was used to predict future value of cell level user experience. Results showed that proposed method performance well in cellular network data analysis and user experience prediction.

In the Vehicle-to-grid (V2G) network, two-way energy transactions can be performed between electric vehicles (EVs) and charging stations (CSs), which are an important technology to support greener and energy-saving networks. As the EV ownership rate continues to rise, the unbalanced loads of CSs in some regions may cause undermine the stability of the power grid system. This paper proposes a CS matching algorithm based on an incentive mechanism to intelligently schedule electric vehicle charging activities for regional load balance. In addition, we propose a blockchain-based anonymous identity authentication scheme to enable EVs, CSs, and the utility data center (UDC) to perform secure mutual authentications to prevent identity privacy leakages. Simulation results show that the peak-to-valley ratio of the algorithm proposed in this paper can reach 75% and approximately 25% higher than the other schemes. It can optimize the charging behavior of electric vehicles and effectively balance the load between the CSs in the area. The security analysis also demonstrates that the scheme can ensure power transactions’ security by protecting identity privacy and preventing eavesdropping.

Mobile Edge Computing (MEC) is a promising solution for vehicular task offloading to meet the stringent delay and high-reliability requirements. In addition, cloud-assisted MEC can further improve resource utilization of MEC and cloud computing server. However, the current cloud-assisted MEC offloading schemes have high algorithm complexity and a single optimization target (e.g., latency). At the same time, the mobility of vehicles will also lead to varying influences on communication links. Frequent disconnection and reconnection of communication links will easily lead to failure of computing task transmission. In this paper, we present a Collaborative Computation Offloading and System Energy optimization (CCOSEO) scheme. First, the computation complexity of the scheme is reduced by a computation task classifying algorithm. Then, combined with the mobility of vehicles, we formulate the offloading decision as a joint optimization problem of latency and energy consumption. Finally, a Game Theory-based Offloading Strategy optimization (GTOSO) algorithm is proposed to achieve the optimal solution. The simulation results show that the proposed scheme can greatly enhance system energy efficiency and reduce the total delay by 20% in the dense-vehicle scenario.