Cellular traffic prediction provides significant support for the management of intelligent networks. Existing models commonly combine recurrent neural networks (RNNs) with attention mechanisms, convolutional neural networks (CNNs), or graph convolutional networks (GCNs) to capture spatial-temporal correlations of cellular traffic. However, attention mechanisms lack sensitivity to local information; CNNs ignore the interaction among distant regions with similar semantics; GCNs exhibit limitations in exploring high-order (beyond pairwise) spatial correlations. To this end, we develop a hypergraph attention recurrent network (HARN) that exploits locality, semantics, and high-order correlations for cellular traffic prediction. Specifically, we first propose a spatial trend-aware attention to perceive local trends, thus easing the mismatching problem of attention mechanisms. Then, we construct a hypergraph to characterize the interactions between distant regions with similar semantics, and leverage a hypergraph convolution network to extract high-order correlations. More importantly, to extract heterogeneous and varying spatial patterns, we further enhance the hypergraph convolution network by incorporating spatial-temporal representations. Last, extensive experiments on three real-world datasets demonstrate the superiority of HARN over state-of-the-art baselines in terms of mean absolute error and root mean square error, with specific improvements of 1.83% and 5.79% on SMS (short message service) dataset, 3.05% and 11.27% on Call dataset, and 1.36% and 1.65% on Internet dataset, respectively.

Traffic prediction is vital to traffic planning, control, and optimization, which is necessary for intelligent traffic management. Existing methods mostly capture spatiotemporal correlations on a fine-grained traffic graph, which cannot make full use of cluster information in coarse-grained traffic graph. However, the flow variation of clusters in the coarse-grained traffic graph is more stable compared with nodes in the fine-grained traffic graph. And the flow variation of a fine-grained node is generally consistent with the trend of the cluster to which the node belongs. Thus information in the coarse-grained traffic graph can guide feature learning in the fine-grained traffic graph. To this end, we propose a Spatiotemporal Multiscale Graph Convolutional Network (SMGCN) that explores spatiotemporal correlations on a multiscale graph. Specifically, given a fine-grained traffic graph, we first generate a coarse-grained traffic graph by graph clustering, and extract spatiotemporal correlations on both fine-grained and coarse-grained traffic graphs. Then we propose a cross-scale fusion (CF) to implement information diffusion between the fine-grained and coarse-grained traffic graphs. Moreover, we employ an adaptive dynamic graph convolution network to mine both static and dynamic spatial features. We evaluate SMGCN on real-world datasets and obtain a$1.18\% -3.32\%$improvement over state-of-the-arts.

The combination of mobile edge computing and 5G heterogeneous networks (5G HetNets) provides new vehicular task offloading research solutions. Most existing task offloading studies assume that vehicle tasks are unique and there are no redundant tasks between vehicles. However, there is a duplication of tasks for vehicles within the same base station. That causes a waste of computing resources and increases task offloading costs. To address this problem, this paper proposes the task offloading algorithm TOERT to eliminate redundant tasks in 5G HetNets. The TOERT algorithm is designed to eliminate redundant tasks, improve vehicle task completion rates and reduce offloading costs. Specifically, we consider two cases of redundant tasks within the macro cell base station (MCBS). When the task results have been stored in the MCBS, vehicles directly agree on the transaction price with the MCBS to obtain the task results. The MCBS first eliminates redundant tasks between vehicles when task results are not stored. Then, the MCBS determines the appropriate small cell base station (SCBS) to participate in the partial offloading. Finally, the vehicles negotiate with the MCBS to obtain task results. Against the other five algorithms considered for comparison purposes, the TOERT algorithm effectively eliminates redundant tasks, improves the task completion rate and increases the benefits of both the vehicles and the MCBS.

Traffic flow prediction is a challenging task due to complex spatial-temporal correlations. Most existing methods leverage graph convolutional network (GCN) to capture spatial correlations. However, GCN has limited ability in mining global spatial correlations. Multi-layer GCN for aggregating multi-order neighbor information will result in high-degree nodes being prone to over-smoothing. To this end, we develop a graph convolutional recurrent attention network (GCRAN) for traffic flow prediction. Specifically, we take the advantage of Gated Recurrent Units (GRU) and Attention to explore local and global temporal correlations. Moreover, we design a novel local context aware spatial attention to extract local and global spatial correlations simultaneously. Experiments on two public real-world traffic datasets demonstrate that GCRAN outperform state-of-the-art baselines.

Reinforcement learning has been applied to various decision-making tasks and has achieved high profile successes. More and more studies have proposed to use reinforcement learning (RL) for traffic signal control to improve transportation efficiency. However, these methods suffer from a major exploration problem, and their performance is particularly poor. And even fail to quickly converge during the initial stage when interacting with the environment. To overcome this problem, we propose an RL model for traffic signal control based on demonstration data, which provides prior expert knowledge before RL model training. The demonstrations are collected from the classic method self-organizing traffic light (SOTL). It not only serves as expert knowledge but also explores and improves the entire decision-making system. Specifically, we use small demonstration data sets to pre-train the Ape-X Deep Q-learning Network (DQ N) for traffic signal control. When training a RL model from scratch, we often need a lot of data and time to learn a better initialization. Our approach is dedicated to making the RL algorithm converge quickly and accelerating the pace of learning. Extensive experiments on three urban datasets confirm that our method performs better with faster convergence and least travel time than the current RL-based methods by an average of 23.9%, 23.8%, 11.6%

Federated learning, as a typical distributed learning paradigm, shows great potential in Industrial Internet of Things, Smart Home, Smart City, etc. It enables collaborative learning without data leaving local users. Despite the huge benefits, it still faces the risk of privacy breaches and a single point of failure for aggregation server. Adversaries can use intermediate models to infer user privacy, or even return incorrect global model by manipulating the aggregation server. To address these issues, several federated learning solutions focusing on privacy-preserving and security have been proposed. However, theses solutions still faces challenges in resource-limited scenarios. In this paper, we propose G-VCFL, a grouped verifiable chained privacy-preserving federated learning scheme. Specifically, we first use the grouped chain learning mechanism to guarantee the privacy of users, and then propose a verifiable secure aggregation protocol to guarantee the verifiability of the global model. G-VCFL does not require any complex cryptographic primitives and does not introduce noise, but enables verifiable privacy-preserving federated learning by utilizing lightweight pseudorandom generators. We conduct extensive experiments on real-world datasets by comparing G-VCFL with other state-of-the-art approaches. The experimental results and functional evaluation indicate that G-VCFL is efficient in the six experimental cases and satisfies all the intended design goals.

The Mobile Edge Computing (MEC)-based task offloading in the Internet of Vehicles (IoV) scenario, which transfers computational tasks to mobile edge nodes and fixed edge nodes with available computing resources, has attracted interest in recent years. The MEC-based task offloading can achieve low latency and low operational cost under the tasks delay constraints. However, most existing research generally focuses on how to divide and migrate these tasks to the other devices. This research ignores delay constraints and offloading node selection for different tasks. In this article, we design the MEC-enabled IoV architecture, in which all vehicles and MEC servers act as offloading nodes. Mobile offloading nodes (i.e., vehicles) and fixed offloading nodes (i.e., MEC servers) provide low latency offloading services cooperatively through roadside units. Then we propose the task offloading scheme that considers task classification and offloading nodes selection (TO-TCONS). Our goal is to minimize the total execution time of tasks. In TO-TCONS Scheme, we divide the task offloading into the same region offloading mode and cross-region offloading mode, which is based on the delay constraints of tasks and the travel time of the target vehicle. Moreover, we propose the mobile offloading nodes selection strategy to select offloading nodes for each task, which evaluates offloading candidates for each task based on computing resources and transmission rates. Simulation results demonstrate that TO-TCONS Scheme is indeed capable of reducing total latency of tasks execution under the delay constraints in MEC-enabled IoV.

Adaptive traffic signal control plays a significant role in the construction of smart cities. This task is challenging because of many essential factors, such as cooperation among neighboring intersections and dynamic traffic scenarios. First, to facilitate the cooperation of traffic signals, existing work adopts graph neural networks to incorporate the temporal and spatial influences of the surrounding intersections into the target intersection, where spatial-temporal information is used separately. However, one drawback of these methods is that the spatial-temporal correlations are not adequately exploited to obtain a better control scheme. Second, in a dynamic traffic environment, the historical state of the intersection is also critical for predicting future signal switching. Previous work mainly solves this problem using the current intersection's state, neglecting the fact that traffic flow is continuously changing both spatially and temporally and does not handle the historical state.

Traffic light control is an extremely challenging problem in transportation. Recently, an increasing number of studies have employed reinforcement learning approaches to deal with traffic light control problems. However, these studies often observe the target intersection independently and ignore the dynamic effects from the surrounding intersections. Moreover, the dependence of historical information on current traffic conditions is also not fully exploited in multi-intersection traffic light control. In this work, we propose a spatial-temporal graph attention network based multi-agent deep Q-learning model. Our model can capture not only spatial features but also temporal features. Specifically, we first utilize the Graph Attention Network (GAT) to obtain the spatial relationship between the central intersection and surrounding intersections. Then Long Short-Term Memory (LSTM) network and the self-attention mechanism are used to get the time dimension information. Finally, we adopt a deep Q-learning network (DQN) to predict the action-value of each feasible action and choose the signal phase according to the size of the action-value. Experimental results on synthetic and realworld datasets confirm that our method can lead to both the least travel time and the maximum throughput, compared with some existing baselines.

With the networks becoming complex, traditional congestion control protocols face increasing challenges in providing high-quality services for users. Traditional TCP and its variants fail to achieve high performance due to drawbacks in architectural design: predefined actions to specific network feedback. In this paper, we develop a learning-based TCP congestion control scheme RLCC, featuring a deep Q-network framework, in which senders learn the optimal control policies from observations instead of predefined rules. To apply DQN algorithms to congestion control problems, we first prove theoretically that congestion control problems are of Markov property. Therefore, the model-free reinforcement learning algorithm DQN can be used to solve congestion control. This is because the application of DQN to the network congestion control problem is convergent, and there exists an optimal strategy to obtain the best action for congestion control. We improved the network's performance by carefully designing the reward function and choosing the appropriate form and parameters through extensive experimentation. Extensive experiments on real-world environments of Pantheon via AWS confirm that RLCC can achieve utilization improvements over the traditional TCP congestion control schemes with higher throughput and lower transmission latency, and outperform the recently proposed learning-based congestion control protocol.

Cooperative agents often need to reason about the states of a large and complex uncertain domain that evolves over time. Since exact calculation is usually impractical, we aim at providing a modeling tool that supports approximate online monitoring in such settings. Our proposed framework, the multi-agent dynamic Bayesian networks (MA-DBNs), models the dynamics of a group of cooperative agents approximately by utilizing weak interaction among them. Each dynamic agent maintains an individual chain of evolution, which enables a factorized and more efficient calculation of cooperative online monitoring. Meanwhile, agents are organized by an underlying hypertree structure to facilitate inter-agent communication. The error resulting from our model approximation is expected to be bounded over time, and a re-factorization method is proposed to improve the approximation quality. Moreover, MA-DBNs are flexible in admitting existing BN monitoring techniques for each agent's local evolution. As an example, we present an algorithm of distributed particle filters under our proposed model.

Extensive research has been done for efficient computation of probabilistic queries posed to Bayesian networks (BNs). One popular architecture for exact inference on BNs is the Junction Tree (JT) based architecture. Among all variations developed, HUGIN is the most efficient JT-based architecture. The Global Propagation (GP) method used in the HUGIN architecture is arguably one of the best methods for probabilistic inference in BNs. Before the propagation, initialization is done to obtain the potential for each cluster in the JT. Then with the GP method, each cluster potential is transformed into cluster marginal through passing messages with its neighboring clusters. Improvements have been proposed to make the message propagation more efficient. Still, the GP method can be very slow for dense networks. As BNs are applied to larger, more complex and realistic applications, the design of more efficient inference algorithm has become increasingly important. Towards this goal, in this paper, we present a heuristic for initialization that avoids unnecessary message passing among clusters of a JT, therefore improving the performance of the architecture by passing fewer messages.

The multiply sectioned Bayesian network (MSBN) model successfully extends the traditional Bayesian network (BN) model for the support of probabilistic inference in distributed multi-agent systems. However, existing MSBN inference methods do not allow agents to reason about their own problem sub-domains right after the initialization process. Extensive amount of inter-agent message passings are needed to calibrate each agent's local subnet into a correct prior marginal distribution. In this paper, we introduce the concept of prior marginal factors to facilitate this process. Based on the analysis of the prior marginal factors, minimum message passing is required during calibration. Furthermore, we have removed the requirement of maintaining a consistent junction tree (JT) during message calculation. Therefore, our marginal calibration algorithm guarantees that a prior marginal in each MSBN subnet is formed with greatly reduced communication and computational cost. Our preliminary experiments have confirmed the improved time efficiency of the proposed algorithm.

Bayesian networks have been well established as an effective framework for uncertainty management using probability. Various methods for probabilistic reasoning in Bayesian networks have been developed and matured. Recently, research has shown that there exists an intriguing relationship between Bayesian networks and relational databases. Adding to that intriguing relationship, in this paper, we reveal that the global propagation method for probabilistic reasoning in Bayesian networks has a close tie with the well known semijoin programs for query answering in relational databases. This linkage between these two apparently different but closely related knowledge representations suggests that well developed techniques for query answering in relational databases could be applied to probabilistic reasoning in Bayesian networks for large and complex domains.

A Bayesian network consists of a directed acyclic graph (DAG) and a set of conditional probability distributions (CPDs); they together define a joint probability distribution (jpd). The structure of the DAG dictates how a jpd can be factorized as a product of CPDs. This CPD factorization view of Bayesian networks has been well recognized and studied in the uncertainty community. In this article, we take a different perspective by studying a marginal factorization view of Bayesian networks. In particular, we propose an algebraic characterization of equivalent DAGs based on the marginal factorization of a jpd defined by a Bayesian network. Moreover, we show a simple method to identify all the compelled edges in a DAG. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 769–786, 2004.

We introduce an algorithm for automatic mining of data dependencies in a relation. The mined data dependencies can be used to construct a granular database scheme. Unlike the traditional approach, the granular database scheme has the following advantages: (1) it is able to present a coarse or refined view of the relations in the database; (2) queries can be answered more efficiently using the granular database scheme than the flat database scheme.

The implication problem is to test whether a given set of independencies logically implies another independency. This problem is crucial in the design of a probabilistic reasoning system. We advocate that Bayesian networks are a generalization of standard relational databases. On the contrary, it has been suggested that Bayesian networks are different from the relational databases because the implication problem of these two systems does not coincide for some classes of probabilistic independencies. This remark, however, does not take into consideration one important issue, namely, the solvability of the implication problem. In this comprehensive study of the implication problem for probabilistic conditional independencies, it is emphasized that Bayesian networks and relational databases coincide on solvable classes of independencies. The present study suggests that the implication problem for these two closely related systems differs only in unsolvable classes of independencies. This means there is no real difference between Bayesian networks and relational databases, in the sense that only solvable classes of independencies are useful in the design and implementation of these knowledge systems. More importantly, perhaps, these results suggest that many current attempts to generalize Bayesian networks can take full advantage of the generalizations made to standard relational databases.