Quality of experience (QoE) is a vital metric that indicates how well the wireless network provides transmission services to users, while quality of service (QoS) help better configure the network parameters for higher performance. The evaluation time of QoE is usually several orders of magnitude larger than that of QoS, because QoE is the perception of users over a period of time, but QoS can be collected every millisecond. Therefore, the implementation of QoE/QoS mapping model can help us obtain QoE by collecting the QoS measurements, and perform QoE-based network configurations with smaller time granularity. Many studies are made to obtain the QoS to QoE mapping, including the use of machine learning (ML) methods. However, traditional ML-based regression methods for QoE/QoS mapping face the challenge of high regression error and catastrophic forgetting in dealing with continuously arriving data. In this paper, we propose a novel QoE model based on continual deep learning in wireless network. This model is formed with two deep neural networks (DNNs) concatenated. The first DNN classifies data into different subsets, which are then fed into the second DNN for regression. The second DNN dynamically form the corresponding subnets, each with nodes and connections adaptively selected in each new time period with new arriving data. We solve the catastrophic forgetting problem with the use of node splitting and hidden state augmentation. Our proposed learning framework greatly reduces the regression error to as low as 0.9314%. The experimental results demonstrate that our proposed model reduces the root mean square error (RMSE) by $21 \sim 86$ times compared with several existing approaches, specially, the testing error of our proposed model is more than 80 times lower than that of traditional DNN. Compared with other DNN-based cascade models, our proposed method provides good performance in both training time and RMSE.

The slice-based Open Radio Access Network (O-RAN) enables rapid deployment of logical networks and provides personalized services. In designing the inter-slice resource sharing scheme, multiple factors need to be considered. Firstly, resource isolation level (RIL) and interference isolation level (IIL) are two key factors in ensuring slice isolation. Secondly, the new business models brought by network slicing imply the need to consider tenants’ resource costs. However, to date, no prior studies have considered RIL, IIL and costs simultaneously, often involving only one or two of them. Accordingly, we propose an inter-slice resource block (RB) leasing and association adjustment scheme (ISRLA) that allows slices to borrow RBs from the shared resource pool and other slices. ISRLA is divided into three modules, namely, prediction module, leasing module, and RB association adjustment module. Firstly, the prediction module uses a Long Short-Term Memory model to predict RB demand and guide subsequent resource optimization. Then, the leasing module balances RIL and costs to determine the number of RBs to be leased in or leased out. This is defined as a non-linear integer programming problem, which is solved through an iterative strategy based on camp swapping (ISBCS). ISBCS is further proven to be convergent. Finally, the RB association adjustment module determines specific RB adjustment strategies based on the results obtained from the leasing module, aiming to ensure IIL. Here, we design a potential game based on the Lagrangian relaxation (LR) method to obtain an approximate optimal solution while reducing computational complexity. Compared with camp enumeration (CE), solver (MOSEK), and genetic algorithm (GA), the proposed ISRLA reduces simulation time by up to 84%, 95%, and 99%, respectively. When the number of slices is 4, the performance of ISRLA is the same as that of CE. Moreover, the IIL gap between ISRLA and MOSEK is less than 4.5%. The simulation results show that the proposed ISRLA can obtain the approximate optimal solution with low computational complexity.

Relay-aided Device-to-Device (D2D) communication combining visible light communication (VLC) with radio frequency (RF) is a promising paradigm in the internet of things (IoT). Static relay limits the flexibility and maintaining connectivity of relays in Hybrid VLC/RF IoT systems. By using a drone as a relay station, it is possible to avoid obstacles such as buildings and to communicate in a line-of-sight (LoS) environment, which naturally aligns with the requirement of VLC Systems. To further support the application of VLC in the IoT, subject to the challenges imposed by the constrained coverage, the lack of flexibility, poor reliability, and connectivity, drone relay-aided D2D communication appears on the horizon and can be cost-effectively deployed for the large-scale IoT. This paper proposes a joint resource allocation and drones relay selection scheme, aiming to maximize the D2D system sum rate while ensuring the quality of service (QoS) requirements for cellular users (CUs) and D2D users (DUs). First, we construct a two-phase coalitional game to tackle the resource allocation problem, which exploits the combination of VLC and RF, as well as incorporates a greedy strategy. After that, a distributed cooperative multi-agent reinforcement learning (MARL) algorithm, called WoLF policy hill-climbing (WoLF-PHC), is proposed to address the drones relay selection problem. Moreover, to further reduce the computational complexity, we propose a lightweight neighbor–agent-based WoLF-PHC algorithm, which only utilizes historical information of neighboring DUs. Finally, we provide an in-depth theoretical analysis of the proposed schemes in terms of complexity and signaling overhead. Simulation results illustrate that the proposed schemes can effectively improve the system performance in terms of the sum rate and outage probability with respect to other outstanding algorithms.

Self-healing is one of the most important parts in self-organizing mobile communication network. It focuses on detecting the decline of service quality and finding out the cause of network anomalies and repairing it with high automation. Diagnosis is a particularly important task which identifies the fault cause of problematic cells or regions. To perform the diagnosis, this paper presents two modified ensemble classifiers by using Support Vector Machine (SVM) with different kernels, i.e., SVM with the radial basis function (RBF) kernel (RBFSVM in short) and SVM with the linear kernel (LSVM in short), as component classifier in Adaptive Boosting (AdaBoost), and we call the two ensemble classifiers as Adaptive Boosting based on RBFSVM (AdaBoostRBFSVM in short) and Adaptive Boosting based on linear kernel (AdaBoostLSVM in short). Different with previous AdaBoostSVM classifiers using weak component classifiers, in this paper, the performance of the classifiers is adaptively improved by using moderately accurate SVM classifiers (the training error is less than 50%). To solve the accuracy/diversity dilemma in AdaBoost and get good classification performance, the training error threshold is regulated to adjust the diversity of classifier, and the parameters of SVM (regularization parameter C and Gaussian width σ) are changed to control the accuracy of classifier. The accuracy and diversity will be well balanced through reasonable parameter adjustment strategy. Results show that the proposed approaches outperform individual SVM approaches and show good generalization performance. The AdaBoostLSVM classifier has higher accuracy and stability than LSVM classifier. Compared with RBFSVM, the undetected rate and diagnosis error rate of AdaBoostRBFSVM decrease slightly, but the false positive rate does reduce a lot. It means that the AdaBoostRBFSVM classifier is indeed available and can greatly reduce the number of normal class samples that have been wrongly classified. Therefore, the two ensemble classifiers based on the SVM component classifier can improve the generalization performance by reasonably adjusting the parameters. To set the parameter values of component classifiers in a more reasonable and effective way, genetic algorithm is introduced to find the set of parameter values for the best classification accuracy of AdaBoostSVM, and the new ensemble classifier is called AdaboostSVM based on genetic algorithm (GA-AdaboostSVM in short) (including AdaboostLSVM based on genetic algorithm and AdaboostRBFSVM based on genetic algorithm). Results show that GA-AdaboostSVM classifiers have a lower overall error than AdaboostSVM classifiers. Genetic algorithm could help to achieve a more optimal performance of the ensemble classifiers.

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.

Analysis of urban area function is crucial for urban development. Urban area function features can help to conduct better urban planning and transportation planning. With development of urbanization, urban area function becomes complex. In order to accurately extract function features, researchers have proposed multisource data mining methods that combine urban remote sensing and other data. Therefore, the research of efficient multisource data analysis tools has become a new hot topic. In this paper, a novel urban data analysis method combining spatiotemporal wireless network data and remote sensing data was proposed. First, a Voronoi-diagram-based method was used to divide the urban remote sensing images into zones. Second, we combined period and trend components of wireless network traffic data to mine urban function structure. Third, for multisource supported urban simulation, we designed a novel spatiotemporal city computing method combining graph attention network (GAT) and gated recurrent unit (GRU) to analyze spatiotemporal urban data. The final results prove that our method performs better than other commonly used methods. In addition, we calculated the commuting index of each zone by wireless network data. Combined with the urban simulation conducted in this paper, the dynamic changes of urban area features can be sensed in advance for a better sustainable urban development.