The anonymity and decentralization of blockchain facilitate illicit blockchain transactions, while the dispersed computing resources in IoT(Internet of Things) scenarios pose challenges like insufficient high-dimensional feature processing capability, poor unknown anomaly detection, and high model update costs for identifying illicit accounts. To address these issues, we propose FLTG-Double GAT, a dedicated monitoring method for decentralized resource scenarios. It aggregating multi-party knowledge to enable cross-organizational detection of illicit transaction, while protecting data privacy by only uploading detection model parameter. It adopt a customized feature extraction paradigm combining double GAT and PCA balances deep feature mining and efficiency, enabling high-precision modeling on edge devices. At the same time, a GRU-driven real-time update mechanism is used. This realizes lightweight adaptation of the detection model to dynamic transactions and enhances early warning capability. Experiments on the Elliptic++ dataset show it achieves 99.80% detection recall and 99.28% prediction recall with low computational complexity, verifying its scalability and practical value in large-scale distributed blockchain monitoring systems.

Communication overhead represents a primary bottleneck in distributed deep learning, impeding training scalability. Although existing gradient sparsification techniques reduce network traffic, they introduce critical limitations: they fail to optimize intra-node data paths and are incompatible with efficient, decentralized Allreduce operations. To address these issues, we propose D-DOSA, a DPU-based communication offloading framework. D-DOSA incorporates two key innovations: 1) D-DO, an architecture that establishes a direct GPU-DPU data path to offload data loading and intra-node communication from the host CPU; and 2) D-SA, a novel sparse Allreduce algorithm that, for the first time, enables compatibility between sparse tensors and high-performance, ring-based communication. We evaluated D-DOSA on a 8-node, DPU-enabled cluster using representative models including VGG, LSTM, and BERT. Experimental results demonstrate that our framework accelerates training by up to 1.32x compared to the state-of-the-art sparse training baseline, without compromising accuracy. Ultimately, D-DOSA shows that co-designing data-flow architectures and communication algorithms on the DPU resolves key bottlenecks in sparse training and presents a viable path toward scalable performance in larger systems.

Transmitting multimodal data through semantic communication offers a promising way to enhance the quality of experiences. However, existing single-modal semantic communication systems struggle to efficiently support multimodal data transmission. Additionally, users have different communication requirements for different modalities, while existing work lacks the capability to generate personalized communication schemes tailored to diverse requirements. In this paper, we propose a cognitive multimodal semantic communication system. At its core is a cognitive semantic communication agent (CSCA) powered by edge large AI model (LAM), enabling low-latency modality alignment and natural language intent understanding. The CSCA integrates a cognitive communication planning algorithm that leverages intent cognition and environment cognition to create personalized communication schemes for users. Experimental results demonstrate that our system outperforms baseline systems in terms of semantic accuracy, intent satisfaction rate and communication latency.

Blockchain’s openness and high market value have led to the increasing prevalence of phishing scam in blockchain transactions, which seriously threatens the safety of users’ assets. The existing blockchain phishing scam detection methods have made some progress. However, the performance of feature engineering-based methods is easily affected by subjective bias, and the detection effect of Graph Neural Network-based methods is suboptimal due to the over-smoothing problem. To overcome the above problems, we propose DRL-BPSD, a blockchain phishing scam detection method enhanced by Deep Reinforcement Learning (DRL). Specifically, we first models blockchain transaction data as graph data, and then propose a node multidimensional representation model that concatenates transaction semantic information and graph structure information. Specifically, Gate Recurrent Unit and Max pooling are combined to deeply mine transaction semantic information, while Graph Convolutional Network is employed to extract graph structure information. Then, we propose a DRL-based information adaptive aggregation algorithm. It mitigates the over-smoothing issue on detection effect by incorporating the representation discrepancy between nodes into the detection process of phishing nodes. Compared with 10 existing methods on two large-scale blockchain transaction datasets, DRL-BPSD shows excellent detection performance in different experimental scenarios.

Celluar traffic forecasting is critical for optimizing resources, balancing loads, and reducing costs in cellular networks. However, newly established base stations often suffer from data scarcity due to the lack of historical traffic data, and the varying traffic demands across regions and times further complicate accurate predictions. While deep learning models typically perform well in data-rich environments, their accuracy drops significantly in data-scarce areas. To tackle this challenge, we propose a Deep Attention-based Graph Transfer Network(DAGTN), a novel framework that leverages cross-domain transfer learning. The framework includes a spectral clustering algorithm based on Dynamic Time Warping (DTW) to group similar base stations, enabling effective knowledge transfer and capturing spatial dependencies. We also introduce DSAN, a deep temporal prediction model that integrates attention mechanisms and sampling strategies to capture traffic patterns more accurately. Additionally, Generative Adversarial Networks (GANs) are used for domain adaptation, aligning the distribution between source and target domains while maintaining data privacy. Our experiments show that DAGTN outperforms existing methods, improving prediction accuracy by 8.7% in RMSE, MAE, and R2. Ablation studies further validate the contribution of each component.

Artificial Intelligence Generated Content (AIGC) technology, with its highly efficient automation and intelligent algorithms, is transforming the way information is produced. However, the resource-intensive nature of large generative AI models, combined with traditional cloud-based inference approaches, leads to significant bandwidth consumption and unpredictable communication latency. On the other hand, directly deploying AIGC models on edge nodes faces challenges such as limited computational resources and storage space. To address these issues, we proposes an AIGC inference framework based on edge node collaboration, and develops an optimization model using model splitting methods. Building on this, we also designed a deep reinforcement learning algorithm incorporating Graph Attention Networks (GAT), which adaptively adjusts model partitioning points and resource scheduling strategies to effectively deploy AIGC models. Finally, simulation results show that the proposed algorithm improves task success rates by an average of 20% compared to Soft Actor-Critic (SAC) and Proximal Policy Optimization (PPO) algorithms, achieving a balance between computation and communication latency in edge environments.

Blockchain’s anonymity and decentralization improve financial efficiency but also facilitate illicit activities like money laundering and fraud. In the field of blockchain illicit transaction detection, researchers are confronted with several challenges, including the difficulty of analyzing high-dimensional data features, the imbalance in the quantity of training data, and the absence of certain features in the training data. This paper proposes a reinforcement learning-enhanced temporal generative adversarial networks (DRL-TGAN) model for detecting illicit transactions in blockchain. Firstly, this model adopts a dynamic feature selection strategy to achieve feature compression, saving computing resources without affecting accuracy. Secondly, we tackle the issue of training data imbalance by introducing noise during the generator training process to synthesize illicit data. Moreover, we propose a sliding window method based on TCN to capture the dynamic changes and long-term dependencies between transactions at different timesteps. We conducted the experiment using two Elliptic dataset, DRL-TGAN achieved a precision of 96.4%, outperforming existing methods in handling imbalanced and incomplete data.

In recent years, the rapid development of Internet of Things (IoT) technology has led to a significant increase in the amount of data stored in the cloud. However, traditional IoT systems rely primarily on cloud data centers for information storage and user access control services . This practice creates the risk of privacy breaches on IoT data sharing platforms, including issues such as data tampering and data breaches. To address these concerns, blockchain technology, with its inherent properties such as tamper-proof and decentralization, has emerged as a promising solution that enables trusted sharing of IoT data. Still, there are challenges to implementing encrypted data search in this context. This paper proposes a novel searchable attribute cryptographic access control mechanism that facilitates trusted cloud data sharing. Users can use keywords To efficiently search for specific data and decrypt content keys when their properties are consistent with access policies. In this way, cloud service providers will not be able to access any data privacy-related information, ensuring the security and trustworthiness of data sharing, as well as the protection of user data privacy. Our simulation results show that our approach outperforms existing studies in terms of time overhead. Compared to traditional access control schemes ,our approach reduces data encryption time by 33%, decryption time by 5%, and search time by 75%.

Vehicle road cooperation (VRC) services closely related to personal safety impose stringent requirements on reliability and real-time performance. However, the growing trend of vehicle to network (V2N) connections has significantly intensified the threat of distributed Denial of Service (DDoS) to the end-cloud communication links. To address this challenge, this article introduces a comprehensive DDoS defense architecture for VRC, named in-network DDoS-oriented Balancer, Inspector, and Filter (IDBIF). Leveraging programmable switches, IDBIF adopts an in-network mode to dynamically mitigate volumetric DDoS traffic in real-time, which coordinates three data plane functions for traffic processing: 1) load balancing; 2) packet inspection; and 3) traffic filtering. Our work faces the starved data plane resources and establishes the problem model for high reliability requirements of VRC services when subjected to DDoS attacks. Furthermore, we developed a multiagent hierarchical structure policy gradient (MAHSPG) algorithm that combines the inherent characteristics of DDoS attacks to tackle the runtime deployment of high-dimensional and heterogeneous defense function chains. Simulation experiment results show that the proposed approach alleviates the data plane resource bottleneck and improves the DDoS defense effect by 24.80%, highlighting its advantages in ensuring reliable VRC services.

In the industrial Internet of Things (IIoT), blockchain technology has been employed to ensure the trustworthiness of federated learning (FL) services. However, the existing framework that combines blockchain and FL suffers from poor training performance and high computational overhead due to the complex consensus mechanism. Although recent studies have explored architectures that integrate Directed Acyclic Graph (DAG) with FL, the aggregation process in DAG-based multi-branch structures still faces significant challenges due to strong statistical heterogeneity across branches. To accommodate the heterogeneity, this paper proposes a DAG-based asynchronous aggregation framework for decentralized FL services. In this framework, the local models are aggregated with global models in the DAG ledger to form a new transaction block (TB). The verified TB becomes the subsequent node of the tail node in the DAG multi-branch structure. Additionally, an FL model delivery mechanism based on improved ensemble distillation is designed. This mechanism merges the models in verified TBs from multiple branches of the DAG, enhancing the accuracy of the final delivery model without compromising system training efficiency. Extensive ablation and comparative experiments demonstrate that our proposed scheme enhances the training efficiency and accuracy of DAG-FL systems while ensuring the security and trustworthiness.

With the initiation of the Internet of Everything, edge computing has emerged as a pivotal paradigm, shifting from cloud computing to better address the growing data demands and latency issues in Industrial Internet of Things (IIoT). However, securing edge computing systems remains a critical challenge as malicious attackers can compromise the IIoT systems, gain control over edge servers, and tamper with computation programs and results. Existing solutions, such as cryptographic encryption, intrusion detection, and blockchain-based methods, have been widely used to enhance security. Yet, these approaches often suffer from high computational overhead, limited adaptability to dynamic IIoT environments, and a lack of foundational trusted assurance mechanisms. Although Trusted Execution Environment (TEE)-based solutions provide a hardware-enhanced secure execution environment, they face scalability and usability challenges and cannot fully support the parallel execution requirements of multiple and diverse IIoT applications. To overcome these limitations, a novel secure edge computing system is proposed for IIoT that strengthens security from the physical layer. By establishing a computing sandbox model, we extend the trust boundaries of the TEE using a virtual Trusted Platform Module (TPM), enabling secure and efficient execution for diverse IIoT applications. The proposed approach integrates a trust guarantee mechanism with decentralized adaptive attestation, ensuring real-time integrity verification while reducing performance overhead. Through security analysis and experimental validation, it is shown that our system improves Non-Volatile Random-Access Memory (NVRAM) launch time by approximately 1,700 times compared to hardware TPM-based virtual TPM implementations, while enhancing protection against attacks such as rollback.

Large-scale models, also referred to as pretrained models, have attracted significant attention due to their outstanding performance and robust generalization. However, the high demands for data quality, stringent data privacy and security requirements, and limited computational and communication resources have imposed restrictions on the further development of large-scale models. Federated Learning (FL) is a popular machine learning framework that can effectively address this issue. However, when collaboratively training large-scale models using FL, local training and the transmission of large-scale parameters impose significant computational and communication burdens on mobile devices. This paper proposes a light-weight and high-efficiency federated learning framework (FedLH) for large-scale models. This framework divides large-scale models into semantic block-based submodels, allowing clients to transmit these submodels to the server for heterogeneous aggregation. This approach enables both communication and computational efficiency. With the proposed framework, each device can learn personalized, structured sparse models that can efficiently run on terminal devices. Experimental results demonstrate that FedLH outperforms other baseline algorithms by significantly reducing the number of training parameters and transmitted data. It also exhibits strong generalization and scalability.

The distribution of computing resources in the Computing Power Network (CPN) is uneven, leading to an imbalance in resource supply and demand within domains, necessitating cross-domain resource scheduling. To address the cross-domain resource scheduling challenge in CPN, this paper presents an Improved Multi-Agent Actor-Critic (IMAAC) resource scheduling approach leveraging Data Processing Unit (DPU) offloading. Initially, we introduce a cross-domain resource scheduling architecture tailored for CPN by leveraging DPU offloading. Specifically, we delegate certain functionalities of the Multi-Agent Deep Reinforcement Learning (MADRL) Agent to DPUs, aiming to mitigate communication costs incurred during the generation of cross-domain scheduling decisions. Second, we introduce the parallel experience ensemble and multi-head attention mechanism in the Multi-Agent Actor-Critic (MAAC) framework to compress the state-space dimensionality of agent association across domains. Finally, we introduce the parallelized dual-policy network structure to mitigate training instability and convergence challenges within the actor and critic networks. Experimental results showcase that IMAAC achieves noteworthy reductions of 5.98%~13.56%, 23.54%~33.55%, and 41.17%~58.88% in total system delay, energy consumption, and the number of discarded tasks, respectively, compared to benchmark experiments.

With the advancement and widespread adoption of Artificial Intelligence (AI) and Internet of Things (IoT) technology, machine learning (ML) can be leveraged in au-tomated factories to enable intelligent robot fault detection and recognition. As an emerging distributed machine learning framework, federated learning (FL) enables collaborative model training while safeguarding the privacy of user data. However, FL encounters various challenges, including the lack of stable energy supply to maintain continuous training and the existence of malicious terminals in the system. These situations could result in issues such as free-riding attacks and robots running out of energy during the training process. Hence, this paper presents a reliability and energy balanced computation resource allocation mechanism in FL system for IoT businesses. Firstly, a training latency and model contribution based reputation evaluation model is proposed to reveal the reliability of IoT terminals. Then, a training client reliable selection and delayed admission strategy is proposed, which takes into account both the reputation and energy consumption, aiming at enabling terminals with high-quality data and low energy capacity to keep contributing to the model during the later training stage. Especially, we integrate reputation and computing capability of IoT terminals to decide the freshness level of the allocated FL global model, which can effectively defend against free-riding attacks. The simulation results verify that the proposed mechanism outperforms non-delayed/partial-delayed admission mechanisms in terms of model quality and system stability.

As the future trend, more and more vehicles access to the Internet of Vehicles, which means that a huge number of tasks of the vehicle terminals need to be transformed and completed on the network. Edge computing makes the tasks executed on the edge nodes near the terminal, but some vehicle terminals are at a relatively idle state and these additional computing resources are not utilized, causing great waste of resources. What is more, it is hard to highly and comprehensively satisfy the high real-time requirements of some tasks. In order to execute these tasks efficiently, we propose a dynamic edge–end computing collaboration architecture for urban IoV. In this architecture, edge nodes and vehicle terminals can cooperate with each other, which means tasks can be allocated more dynamically and flexibly. We evaluate the completion of the task by considering task latency and overhead, task transmission model, task priority, as well as edge node and vehicle terminal’s capacity when defining task comprehensive utility. Then weformulate the task allocation as an optimization problem and propose an improved quantum particle swarm optimization algorithm to solve the problem. Simulation results show that the proposed strategy have better task allocation utility than other strategies, which can effectively solve the multi task allocation problem.

With the rapid development of the 5G and 6G technology, it has become an inevitable trend to share the cross-domain scattered data and enhance data value transmission. As a new data-sharing technology with intelligence and privacy computing, federated learning (FL) receives wide attention. It can realize data value delivery and data privacy protection at the same time, however, it lacks supervision in the application process, and the reliability of the calculation process and result transmission cannot be guaranteed. As a distributed ledger technology, blockchain has the trust property but lacks computing power. Therefore, we propose to extend the computing and supervision capabilities of blockchain with state channel, using state channel to create sandboxes and instantiate FL tasks in order to realize the trust supervision mechanism based on sandboxes. In this article, we establish an FL-based distributed data-sharing architecture and on the basis of the architecture we design a state channel-based distributed data-sharing trust supervision mechanism. Through theoretical analysis and experimental verification, the supervision mechanism we designed has an excellent performance in improving system security, resisting malicious attacks, and improving data model quality.

As a new trusted data sharing pattern with privacy protection, the integration mechanism of blockchain and Federated Learning has attracted extensive attention. Generally, this mechanism uses blockchain technology to supervise the original data and calculation results, which ignores the supervision of the Federated Learning model and computing process. Therefore, we introduce the concepts of the sandbox and state channel to construct a new data privacy sharing paradigm via Blockchain and Federated Learning. Under this paradigm, we use state channel to connect Blockchain and Federated Learning. And state channel is used to create a “trusted sandbox” to instantiate Federated Learning tasks in the trustless edge computing environment. Meanwhile, we also mainly solve problems about data privacy sharing in Federated Learning and system performance degradation caused by data quality. The simulation results show that the proposed method has better performance and efficiency than the traditional data sharing method.

As Internet-of-Things (IoT) service becomes richer, data sharing among different IoT systems gets popular. The traditional IoT system provides data storage and access service with the central cloud, which faces serious trust and security challenges. To provide a cross-system data sharing service, we adopt blockchain to build a multicenter data management (DM) framework and construct a trustable environment for data sharing. As regards to a security problem, attribute-based encryption (ABE) has been applied to the IoT system, but it still relies on the central server. Therefore, we design an ABE algorithm that could be used for multicenter scenario and shift DM to blockchain instead of a central server. Moreover, IoT devices always cannot afford complex encrypt computations as they have limited computing resource. To solve this, we design an obfuscating policy to shift encryption computations to the cloud instead of terminals. In this way, IoT devices could encrypt data with low computation cost. Security analysis and simulations prove that the algorithm we designed could reduce computation burdens of IoT terminals in data encryption and decryption phases effectively and safely.

The rapid development of the Internet of Things has put forward higher requirements for the processing capacity of the network. The adoption of cloud edge collaboration technology can make full use of computing resources and improve the processing capacity of the network. However, in the cloud edge collaboration technology, how to design a collaborative assignment strategy among different devices to minimize the system cost is still a challenging work. In this paper, a task collaborative assignment algorithm based on genetic algorithm and simulated annealing algorithm is proposed. Firstly, the task collaborative assignment framework of cloud edge collaboration is constructed. Secondly, the problem of task assignment strategy was transformed into a function optimization problem with the objective of minimizing the time delay and energy consumption cost. To solve this problem, a task assignment algorithm combining the improved genetic algorithm and simulated annealing algorithm was proposed, and the optimal task assignment strategy was obtained. Finally, the simulation results show that compared with the traditional cloud computing, the proposed method can improve the system efficiency by more than 25%.

Network Function Virtualization (NFV) technology decouples network functions from the proprietary hardware by using generalized equipment and software, which lowers the cost of network operator. However, the existing mapping mechanisms in NFV environment can't optimize the cost of deployment and improve the rationality of network resource allocation while ensuring the basic service quality requirements of users. To solve the problem, a mathematical model which looks on the assurance of quality of service and cost optimization is established in this article. The model aims at maximizing the total revenue from service chain deployment in resource-constrained network, and takes the resource demand, end-to-end delay requirement and reliability requirement of the service request as the basic constraints. Furthermore, a greedy algorithm of service chain mapping named GA+LCB is proposed to solve the problem. Simulation results show that compared with other algorithms, GA+LCB can effectively improve the success rate of receiving service requests, reduce the cost in the deployment process and achieve higher deployment benefits while ensuring the QoS requirements.

Private and public networks sharing resources for Internet of Things (IoT) network through network function virtualization (NFV) and software-defined networking (SDN) forms a heterogeneous cloud-edge environment. However, the heterogeneous cloud-edge network faces trust and adaptation issues in resource allocation. To address these two problems, we introduce consortium blockchain and deep reinforcement learning (DRL) to construct the trusted and auto-adjust service function chain (SFC) orchestration architecture. In the architecture, this article integrates the consortium blockchain into the distributed SFC orchestration model to realize trusted resource sharing. In addition, for realizing auto-adjusted service provision, this article designs a dynamic hierarchical SFC orchestration algorithm (DHSOA) based on DRL to minimize the orchestration cost and improve the quality of service. Moreover, considering the dynamics of network entities, this article proposes a time-slotted model to support dynamic service migration which adapts to the high-mobility IoT network. The simulation results show that DHSOA has better performance than the link-state routing algorithm and deep Q -network placement algorithm not only in cost saving of 15.8% and 10.1% but also in time saving of 22.0% and 10.0%.

Nowadays, the widely used Internet-of-Things (IoT) mobile devices (MDs) generate huge volumes of data, which need analyzing and extracting accurate information in real time by compute-intensive deep learning (DL) inference tasks. Due to its multilayer structure, the deep neural network (DNN) is appropriate for the mobile-edge computing (MEC) environment, and the DL tasks can be offloaded to DNN partitions deployed in MEC servers (MECSs) for speed-up inference. In this article, we first assume the arrival process of DL tasks as Poisson distribution and develop a tandem queueing model to evaluate the end-to-end (E2E) inference delay of DL tasks in multiple DNN partitions. To minimize the E2E delay, we develop a joint optimization problem model of partition deployment and resource allocation in MECSs (JPDRA). Since the JPDRA is a mixed-integer nonlinear programming (MINLP) problem, we decompose the original problem into a computing resource allocation (CRA) problem with fixed partition deployment decision and a DNN partition deployment (DPD) problem that optimizes the optimal-delay function related to the CRA problem. Next, we design a CRA algorithm based on Markov approximation and a low-complexity DPD algorithm to obtain the near-optimal solution in the polynomial time. The simulation results demonstrate that the proposed algorithms are more efficient and can reduce the average E2E delay by 25.7% with better convergence performance.

With the fast development of smart cities and 5G, the amount of mobile data is growing exponentially. The centralized cloud computing mode is hard to support the continuous exchanging and processing of information generated by millions of the Internet-of-Things (IoT) devices. Therefore, mobile-edge computing (MEC) and software-defined networking (SDN) are introduced to form a cloud-edge-terminal collaboration network (CETCN) architecture to jointly utilize the communicational and computational resources. Although the CETCN brings many benefits, there still exist some challenges, such as the unclear operation mode, low utilization of edge resources, as well as the limited energy of terminals. To address these problems, a reinforcement learning-based joint communicational-and-computational resource allocation mechanism (RJCC) is proposed to optimize overall processing delay under energy limits. In RJCC, a Q -learning-based online offloading algorithm and a Lagrange-based migration algorithm are designed to jointly optimize computation offloading across multisegments and on edge platform, respectively. The simulation results show that the proposed RJCC outperforms the delay-optimal, energy-optimal, and edge-to-terminal offloading algorithm by 42%-74% in long-term average energy consumption while maintaining relatively low delay.

As the great prevalence of various Internet of Things (IoT) terminals, how to solve the problem of isolated information among different IoT platforms attracts attention from both academia and industry. It is necessary to establish a trusted access system to achieve secure authentication and collaborative sharing. Therefore, this article proposes a distributed and trusted authentication system based on blockchain and edge computing, aiming to improve authentication efficiency. This system consists of physical network layer, blockchain edge layer and blockchain network layer. Through the blockchain network, an optimized practical Byzantine fault tolerance consensus algorithm is designed to construct a consortium blockchain for storing authentication data and logs. It guarantees trusted authentication and achieves activity traceability of terminals. Furthermore, edge computing is applied in blockchain edge nodes, to provide name resolution and edge authentication service based on smart contracts. Meanwhile, an asymmetric cryptography is designed, to prevent connection between nodes and terminals from being attacked. And a caching strategy based on edge computing is proposed to improve hit ratio. Our proposed authentication mechanism is evaluated with respect to communication and computation costs. Simulation results show that the caching strategy outperforms existing edge computing strategies by 6%-12% in terms of average delay, and 8%-14% in hit ratio.

Life-time represents the effective survival time of network, which is significant when measuring the performance of wireless sensor networks (WSNs). Therefore, it is so important to extend network life-time by planning appropriate path based on energy consumption and remaining energy of wireless sensors. In this paper, a path planning method of WSNs based on service priority is proposed, and a customized Dijkstra algorithm is used to solve this problem. This method minimizes the total energy consumption of network while balancing remaining energy of all nodes in network, and through the sacrifice of network delay in exchange for extension of life-time. The simulation results show that our method not only prolongs network life-time compared to shortest-path algorithm but also improves network reliability.

In this paper, we investigate the optimal location of electric vehicle (EV) charging stations. As one of the crucial infrastructures of EV, electric charging stations must be widely deployed to meet the growing needs of EV. In this study, we propose a locating method of charging station when considering economics, capacity, coverage and convenience. In order to solve the locating problem, an optimization model for charging stations location is established first, which minimizes the investment cost and transportation cost, meanwhile, the constraints of capacity, coverage and convenience should be satisfied simultaneously. Then, an improved genetic algorithm (GA) is proposed to solve the optimization problem. The simulation results indicate that the proposed locating method is effective and practical.

Data collection communications system for electric power communication network is an important entity network in electric power system. It's significant to provide a reasonable routing mechanism for data collection system. The major risk of original routing mechanism is the burst congestion. In the data collection network of smart grid, that some nodes may suffer from more congestion than others even become the bottleneck of network become the new source of risk. In order to overcome these problems, this paper proposes a routing mechanism to realize data balance. This mechanism firstly abstracts a multigate network model of data collection system. Then, it proposes a routing measurement model to balance data traffic named data balance measurement model (DBMM). Subsequently it proposes a routing algorithm based on DBMM, named RA-DBMM. The RA-DBMM handles the data traffic to achieve data balance by modifying the routing decision measurement function. So the queue length of queuing data and buffer capacity of every nodes are taken into consideration. Simulation illustrates that the proposed RA-DBMM has biggish enhancement in minishing the congestion, reducing loss ratio, overcoming bottleneck and increasing throughput of network.

This paper proposes a planning mechanism to design and plan the communication network for the smart distribution grid when considering economics, reliability and (n-1)-resilience. From the communications perspective, the smart distribution grid mainly consists of End Nodes (ENs) and Access Points (APs), in particular, a distribution grid planning problem focus on deciding which end nodes are to be enabled as access points. In order to solve the problem, an optimization problem is formulated first, which minimizes the cost of installing APs, meanwhile, the constraints of reliability and (n-1)-resilience should be satisfied simultaneously. Then, an approach based on improved genetic algorithm (GA) is developed to solve the proposed problem. Finally, simulation results in MATLAB testify that the proposed planning mechanism is capable to deal with diverse network size and planning effectively with high flexibility and scalability.

Identifying and classifying different network applications is very important for trend analysis, dynamic access control, network security and traffic engineering, while traffic classification is able to classify applications effectively. Current popular methods of traffic classification mainly include machine learning algorithm based on supervised or unsupervised and the method based load. In practical applications, the above methods have high complexity or low accuracy degree, so we propose a semi-supervised support vector machine method only based on flow statistics to identify and classify network applications. In this method, SVM, "constant" flow and co-training algorithm are the key core to obtain a classifier rapidly. The classifier got by this method has three advantages contrast to the previous classical methods: 1) high classification degree; 2) high generalization performance; 3) rapid computational performance. As a proof of concept, we implement the classification algorithm based on open-resource, and show the characteristics and feasibility of our method in the campus and resident network.

Coverage control is one of the most important technologies in Wireless Sensor Network (WSN). In the precondition of better coverage quality, how to format optimal coverage with least sensors is a significant problem to be solved. A new incomplete coverage control based on target tracking sensor network which called mobile-constrained optimal target tracking coverage algorithm (MCOTT) is presented. In our approach, static sensors will be pre-deployed, collaborating with mobile sensors to achieve an optimal coverage which based on a target trajectory prediction model. Simulation results show that, MCOTT has more advantages like good robustness, high level of target coverage, low energy consumption. The algorithm can save the number of sensors and prolong the network lifetime effectively.

With the development of high-speed networks, the challenge of effectively analyzing the massive data source for anomaly detection and diagnosis is yet to be resolved. This paper proposes a new flow-based anomaly detection method based on summary data structures and combinations of traffic features. Using IPFIX flow records as input, parallel sketches are established for chosen traffic features respectively. For each sketch, we use Holt-Winters forecasting technique to achieve their forecast sketches and deviation matrixes. When the deviation exceeds a certain threshold, sub-alarms will be generated. According to the characteristics of various attacks and combinations of traffic features, sub-alarms can be merged into final alarms. While sketches of flows are being constructed, destination addresses are recorded in linked lists which are used to locate victims by a series of set operations. This method can not only detect the existence of anomalies in near real time, but can roughly indicate the anomaly types and locate abnormal addresses.

Network monitoring is essential for assessing performance issues, identifying and locating problems. There is increasing interest in passive monitoring of flows at multiple locations within a distributed network. In order to figure out how to place monitors under cost-effective and budget constraints within the network, a new approach is presented in this paper, which solves the problem of monitoring stations selection and the tradeoff between monitoring cost and reward. Using the method from combinatorial optimization on submodular of information gain, the approach firstly proves that joint entropy and information gain in network models satisfy submodularity under certain conditions, and then an approximate algorithm is proposed to solve optimizing problem of conditional entropies. On the basis, monitoring stations selected by our solution are much better than existing classical criterion. The simulation results validate the approach, demonstrating the solution improving monitoring quality, accuracy and computation time.