With the rapid proliferation of Industrial Internet of Things (IIoT) devices, massive Delay Sensitive and Computation Intensive (DSCI) tasks are generated. Traditional Mobile Edge Computing (MEC) systems face limitations like inter-cell interference at cell edges, degrading Quality of Service (QoS). To address this, Cooperative Access Edge Networks (CAEN) enable dynamic Access Point (AP) clusters for enhanced transmission reliability in IIoT. However, challenges arise from multi-user interference, bandwidth contention, dynamic environments, and heterogeneous resources, complicating joint resource orchestration. This paper proposes EdgeDiffuse, a diffusion-enhanced distributed resource orchestration algorithm, which optimizes task offloading selection, transmission power control, and computational resource allocation to minimize long term task completion time while promoting system load balancing. EdgeDiffuse enables adaptive and hierarchical coordination between user agents and edge servers. It integrates diffusion models under a Multi-Agent Deep Reinforcement Learning (MADRL) framework for improved policy exploration in high dimensional offloading decision spaces, and further uses convex optimization for server side resource allocation. Experimental results demonstrate that EdgeDiffuse achieves 28.17% reduction in task completion time, 7.40% improvement in task transmission rates, and 15.71% enhancement in load balancing compared to advanced baselines, showcasing superior performance in multi-user and resource constrained scenarios.

As edge computing, AI data centers, and supercomputing systems continue to expand, the challenge of deterministic computing power routing has become increasingly prominent. In response, this paper proposes a new hierarchical reinforcement learning algorithm that combines node clustering with routing optimization. Our approach employs a hybrid clustering method that integrates Gaussian Mixture Models (GMM) and K-Means algorithms to categorize computing nodes into distinct groups based on their operational states and past performance. This framework uses reinforcement learning techniques to optimally match deterministic applications with the relevant node clusters, while modeling the selection of nodes and path planning as a Stackelberg game problem. We solve this game-theoretical problem using a dual-agent reinforcement learning architecture, enhanced by graph neural networks to boost generalization. Additionally, we incorporate a shortest-path-based link attention mechanism to speed up model convergence. Our proposed solution addresses the shortcomings of traditional methods, which often treat node selection and path planning separately. This integrated approach leads to more efficient use of resources and better satisfies deterministic transmission needs.

The development of the Internet of Things (IoT) has led to the rapid growth of the types and number of connected devices and has generated large amounts of complex and diverse traffic data. Traffic identification on edge servers solves the real-time and privacy requirements of IoT management and has attracted much attention, but still faces several problems: (1) traditional machine learning (ML) models rely on artificially constructed features, and the existing deep learning (DL) traffic identification models have reached their performance limit; and (2) insufficient computing resources of edge servers limit the possible improvement in the performance of deep learning models by increasing the number of parameters and structural complexity. To address these issues, we propose a lightweight fusion model. First, the Network-in-Network (NiN) model and Random Forest (RF) model are used on the cloud server to construct a traffic identification fusion model. The excellent representation extraction capability of the NiN compensates for the RF’s dependence on manual feature extraction, and its modular structure is suitable for the subsequent model compression operations. Then, the NiN was distilled. We propose Growth-Adaptive Distillation to lightweight the NiN model, which can reduce the operation of manually adjusting the structure of the student model and ensure the efficiency and low power consumption of the fusion model deployment. In addition, both the RF in the cloud and the distilled NiN are deployed on the edge server. Comparisons with multiple algorithms on two network traffic datasets show that the proposed model achieves state-of-the-art performance while ensuring the use of minimal computational resources.

As the development of B5G and 6G continues to progress, higher network bandwidth and increasingly complex vehicle connectivity are driving greater concurrency in highly dynamic and delay-sensitive transportation tasks within the Internet of Vehicles (IoV). Existing resource allocation methods such as Deep Reinforcement Learning (DRL), Graph Neural Network (GNN), Lyapunov and simple Transformer series often result in insufficient individual consideration or unprioritized attention on key resource characteristics, causing high task execution time cost and energy consumption. To overcome above problems, this paper proposes a Dynamic Self-Feedback (DSF) resource allocation approach. First, DSF models task latency and requirements along with diverse computing power to support allocation and dynamically adjusts the dimensions of self-attention heads according to resource consumption prediction in a self-feedback manner. Then, DSF adjusts dimensions of attention embedding to light and heavy tasks as feedback and leads next round of allocation optimization. Therefore, DSF enables individually tailored and energy-efficient allocation of computing resources for high concurrent IoV tasks. Simulations show the proposed mechanism achieves up to 85% tasks execution efficiency and 38% fewer timeout tasks, more than 50% of low energy consumption tasks after allocation, with almost 100% units having a workload lower than 40%.

With the rapid proliferation of the Internet of Things (IoT), network traffic prediction has become crucial for intelligent network management, enabling more reliable and flexible services for a vast array of IoT devices and applications. The heterogeneous and dynamic nature of IoT networks introduces complex spatial relations and underlying periodic dependencies in spatial-temporal graphs that existing methods struggle to model effectively. In this article, we propose multirepresentation spatial-temporal graph convolutional networks (MRSTGCNs), a novel unified framework specifically designed to address these challenges. MRSTGCN integrates a multirepresentation graph convolutional network (MRGCN) module to model node heterogeneity and complex traffic propagation, and two complementary embedding modules—Historical Embedding and Temporal Embedding—to capture and fuse periodic dependencies across different fine-grained temporal cycles. Extensive experiments are conducted on two network traffic datasets, and the results demonstrate that MRSTGCN achieves state-of-the-art performance with obvious improvements in MAE, RMSE and MAPE on three prediction horizons.

Federated Learning is a promising paradigm, of-fering advantages such as access to extensive datasets and robust data privacy preservation. However, a notable challenge arises from the predominant reliance of most federated learning algorithms on labeled data for model training, leaving a limited presence of algorithms capable of effectively utilizing unlabeled data. In real-world scenarios, individuals using electronic devices inadvertently generate copious volumes of unlabeled data, often accompanied by a small fraction of labeled data. This wealth of unlabeled data harbors valuable information, underscoring the importance of developing high-quality federated semi-supervised learning algorithms adept at harnessing both labeled and unlabeled data. This paper introduces FedIDE, an advanced federated semi-supervised learning algorithm. Our approach integrates the principles of pseudo-labeling and instance discrimination, drawing inspiration from contrastive learning, to unlock the potential of unlabeled data. Concurrently, supervised learning is applied to a labeled dataset to enhance model performance. Additionally, we design the LocalEMA local model update algorithm, which amalgamates local and global models during local training, yielding a hybrid model. FedIDE undergoes extensive testing across multiple datasets, surpassing state-of-the-art baselines.

Network traffic prediction is crucial for network operation and management, forming the basis for utilizing big data in decision support. Traditional deep learning methods require extensive, assumed independently and identically distributed(IID) data. However, with IoT development, privacy protection gains importance, resulting in distributed data collection with varying distributions. This leads to a significant performance drop when applying a well-trained model to a new dataset, causing domain shift. To tackle domain shift from inconsistent data distributions and meet privacy protection needs, this paper proposes a spatial-temporal feature learning method within the federated domain generalization framework for network traffic prediction. The ultimately trained model effectively generalizes to an unseen domain, as confirmed by experimental results.

The complexity and dynamism of modern networks pose significant challenges to network management services. Existing technologies often exhibit latency in migrating services after encountering problems. However, adopting a proactive approach through anomaly detection before migration enables the early reservation of resources, thereby ensuring overall performance and stability. This paper proposes a Network Management Service Composition (NMSC) migration method leveraging anomaly detection. The method includes an anomaly detection approach using a Transformer model with a time decay mechanism and a multi-agent reinforcement learning algorithm enhanced by a graph attention autoencoder. First, a time decay mechanism is designed to enhance the self-attention mechanism, allowing the model to capture long-term dependencies while maintaining high sensitivity to recent events. Second, a critic network, enhanced by a graph attention autoencoder, enables the multi-agent algorithm to comprehend the interaction dynamics among agents during computation. Experimental results demonstrate that the proposed anomaly detection algorithm significantly outperforms existing algorithms. Furthermore, the service composition migration algorithm exhibits superior performance in terms of reward value and migration delay, thus proving its effectiveness and feasibility.

Augmented Reality (AR) applications are latency-sensitive and contain significant heterogeneous content, such as mixed static objects and interactive data. Relying solely on real-time edge caching makes it difficult to meet the latency requirements of AR, disrupting user’s immersive experience. In addition, the operator can motivate terminal caching foreground content and reduce transmission costs through device-to-device (D2D). Therefore, we proposes a cloud-edge-terminal collaborative proactive caching and differentiated delivery mechanism of heterogeneous content, which reduces service response latency and improves comprehensive revenue through efficient edge collaboration methods, accurate heterogeneous content pre-caching strategies, and differentiated delivery mechanisms. Firstly, we synthetically considers AR user’s service response latency and operator’s comprehensive revenue, proposing a user behavior and resource-aware edge collaborative service domain construction method to improve the collaborative service capability of edge nodes. Then, it proposes a pre-caching algorithm for heterogeneous content based on foreground/background content separation, user preference prediction, and storage space partitioning to improve cache utilization in the edge network. In particular, a D2D-assisted differentiated delivery strategy is designed to improve service response speed and overall revenue. The numerical results show that the proposed mechanisms are better than other solutions and can improve cache hit rates and operator’s comprehensive revenue.

The occurrence of faults increases in edge networks as the service types and component architecture become increasingly complex. Traditional centralized cloud fault prediction technology cannot be directly applied to edge network systems that are typically required to handle real-time data due to their high-computational complexity. Therefore, this article proposes a lightweight fault prediction algorithm for edge networks that realizes fault prediction with cross-layer cooperation. First, for edge devices with limited computation resources, the time feature lightweight extraction method of brain neurology fusion long short term memory (LSTM) based on scene reappearance mechanisms is proposed, which solves the single-step dependency problem of neurons and improves the accuracy. And the LSTM neuron connection method based on pulse dynamics is designed. This method prunes the structure of the LSTM network based on relevant knowledge of biological neurology to realize a lightweight time feature extraction model of fault information. Then, on the edge server side, a spatial feature lightweight extraction method based on a two-way residual structure is proposed. This method uses decomposition convolution to reduce the number of network parameters and realize a lightweight model. Finally, the spatio-temporal correlation features of the extracted fault information are spliced to realize fault prediction. To verify the effectiveness of the proposed model, we compare the improved model with the existing fault prediction model. The experiments show that the algorithm proposed in this article has higher accuracy, lower complexity and lower memory requirements. Therefore, it has high-deployment potential in edge network scenarios.

Network traffic classification is a key technology in network communication management, which is of great significance for building intelligent communication and so on. Due to the difficult and time-consuming process of network traffic labeling, it is difficult to obtain any labeled traffic data in some special networks. At the same time, in a real network environment, there are multiple network traffic domains, and the data distribution of each network traffic domain is different, making it extremely difficult to train a network traffic classification model that performs well on multiple traffic domains simultaneously. Therefore, this paper proposes a network traffic classification method in unsupervised scenarios, aiming to study how to learn traffic knowledge from multiple source traffic domains and achieve accurate classification of unlabeled network traffic without labeled traffic data in the target traffic domain. This paper divides three traffic domains from the data set, namely VPN, nonVPN and nonTor. And three traffic classification tasks of unsupervised multi-source domain are constructed. The accuracy of traffic classification tasks in the source traffic domain is nonTor and nonVPN, and the target traffic domain is VPN reaches 89.76%. The source traffic domain is VPN and nonTor, the accuracy of the classification task is 91.73% when the target traffic domain is nonVPN, and 90.35% when the source traffic domain is VPN and nonVPN, and the target traffic domain is nonTor. Experimental results show the effectiveness of the network traffic classification algorithm proposed in this paper.

Deep convolutional neural networks are hindered from empowering resource-constrained devices due to their demanding computational and storage resources. Structured pruning effectively removes the redundant components from neural networks and obtains compact models. Previous pruning methods usually evaluate the importance of filters from a layer-wise perspective, which is deprived of global guidance. We propose an adaptive pruning algorithm based on relevance scores to evaluate the contribution of each channel by calculating its relevance score from the back-propagation of the neural network's output. Our method identifies and removes channels with low contribution from a global perspective. Unlike previous methods that manually set the pruning rate for each pruning iteration, our method adaptively adjusts the pruning rate. In addition, our method performs satisfactorily with limited data for one-shot pruning in the absence of fine-tuning. The ability to obtain compact models through one-shot pruning with limited data is ideally suited for edge computing scenarios. We validate the effectiveness of our method with multiple combinations of convolutional neural networks and datasets. Our approach outperforms existing pruning methods in scenarios with limited data.

Federated Learning (FL) is a distributed learning framework that enables data sharing among multiple devices to protect data privacy. Blockchain is a decentralized ledger that can record data securely and reliably. The blockchain-based FL (BFL) framework has been used to share data and computing resources in multiple clusters. However, for the BFL framework among multi-institutional clusters, data sparsity in a cluster is a key issue. Most of the relevant works assume that the data in one cluster is rich enough to build a suitable model, which is not always satisfied in all scenarios. One method to address the problem is that enlarging the size of a BFL cluster that covers as many nodes as possible is one way. However, this method will increase communication overheads and reduce transaction throughput of the blockchain. To solve the above issues, we propose a communication-efficient blockchain-based FL framework called CCFL, which connects multiple BFL clusters to solve the data sparsity issue. We also design a pearson correlation coefficient-based dynamic model filtering mechanism that filters unnecessary models to reduce communication costs and exclude malicious models. Moreover, we illustrate a reliable contribution-based interactive validation reputation mechanism to prevent malicious nodes from participating in the training. We carry out some experiments to show the feasibility and efficiency of the proposed framework.

Blockchain-based Federated learning, called BFL, has attracted widespread attention to construct trust among multiple parties and solve a single point of failure of the central server while protecting privacy. Many researches utilize cluster and cross-chain technologies to improve poor model quality and interoperability between clusters. However, those researches still suffer from 1) high communication overhead when devices of clusters locate far away, and 2) high consensus latency since devices require frequent interactions on consensus. In this paper, we propose a cross-cluster federated learning framework based on state channels, called SCFL, to split devices into multiple clusters according to locations. We also propose a cross-cluster consensus algorithm based on cross-chain and state channels to improve the security and efficiency of off-chain and inter-chain interactions. And we also propose a hierarchical clustering method to make the model adaptable to the partition scenarios where the data is non-IID. Numerical results show that SCFL can effectively solve data sparse problems and improve the system efficiency in non-IID data partitioning cases.

The rapid development of digital technology is reshaping the architecture of the Industrial Internet of Things (IIoT). The traditional architecture cannot process vast amounts of data exchanges and provide entities with trust. The future IIoT is expected to be a decentralized architecture in which blockchain and digital twin-driven IIoT can enable trusted data exchanges. However, this architecture cannot obtain huge amounts of external real-time data and isolated data. Moreover, it cannot handle complex industrial computing tasks. Therefore, we combine oracle with decentralized learning to propose a novel IIoT-oriented digital twin architecture. We also propose an effective decentralized collaboration mechanism to support external data and resources exchanges. Moreover, we propose a novel computing collaboration mechanism to expand the learning capabilities of the industrial ecology. Experiments show that our proposed paradigm has less processing time, a more stable process, and better learning ability compared to other paradigms.

Federated learning (FL) lately has shown much promise in improving the shared model and preserving data privacy. However, these existing methods are only of limited utility in the Internet of Things (IoT) scenarios, as they either heavily depend on high-quality labeled data or only perform well under idealized conditions, which typically cannot be found in practical applications. In this article, we propose a novel federated unsupervised learning method for image classification without the use of any ground truth annotations. In IoT scenarios, a big challenge is that decentralized data among multiple clients is normally nonindependent and identically distributed (non-IID), leading to performance degradation. To address this issue, we further propose a dynamic update mechanism that can decide how to update the local model based on weights divergence. Extensive experiments show that our method outperforms all baseline methods by large margins, including +6.67% on CIFAR-10, +5.15% on STL-10, and +8.44% on SVHN in terms of classification accuracy. In particular, we obtain promising results on Mini-ImageNet and COVID-19 data sets and outperform several federated unsupervised learning methods under non-IID settings.

Vehicular ad hoc networks (VANETs) have the characteristics of high mobility, frequently changing topology and uneven distribution, which made it a challenge to design an efficient and robust routing protocol with low latency and high packet delivery rate. Currently, intersection-based routing method and full-path based routing method are two popular solutions for the packet routing in VANETs. Although the intersection-based routing method has better real-time performance, it has the problem of local optimization, making the routing results not global optimal. Although the full-path based method can obtain the global optimal solution, it is weak in dealing with the dynamically changing topological network. Aiming at solving the above problems, this paper designs an intersection-based QoS routing (IQRRL) algorithm, which mainly includes two crutial steps: the next intersection selection and the next hop vehicle selection. In the selection of the next intersection, this paper uses an improved intersection-based routing protocol. In addition to considering connectivity and delay, IQRRL also considers the communication quality from the neighbor’s road to the destination node while evaluating the quality of the neighbor’s road, which minimizes the problem of local optimization. When the next intersection is determined, a road is then determined, and then the next hop vehicle within the road should be chosen to relay the packet forward. In the next-hop vehicle selection step, this paper adopts multi-hop evaluation technology based on reinforcement learning. In addition to using “greedy decision-making” to select the next-hop vehicle, it also comprehensively evaluates whether the next-hop vehicle is still optimal in the future, so that the stability and reliability of data forwarding are improved and local optimal problems are avoided. Besides, this article uses a simulation system to compare IQRRL with other routing algorithms. The result reveals that IQRRL outperforms in terms of packet delivery ratio and transmission delay.

When an online service, such as an online Web service, encounters an abnormality, operators need to analyse many abnormal monitoring indicators on the affected machine and rapidly determine the root cause indicators, which can quickly locate specific problems. Then, the abnormality is isolated until the cascading effects caused by the anomalies are eliminated. This paper proposes a root cause indicator location algorithm named ProphetKdeRCL. First, the improved Prophet algorithm detects many abnormal time-series indicators. Then, the abnormal deviation degree algorithm based on kernel density estimation is used to measure the fluctuation of each abnormal indicator for sorting. The analyses of the delay causal factor dependence are combined with the time window. Finally, a root cause location list is generated to assist operators in quick troubleshooting operations. This paper uses public datasets to evaluate the overall effectiveness of the algorithm. The results show that compared to other algorithms, the ProphetKdeRCL algorithm has higher accuracy on evaluation indicator AC@1 and superior accuracy on the other commonly used indicators, namely, AC@2 and AC@3.

Network traffic classification is a key foundation of traffic management and network security. With the development of traffic encryption technologies and more attention given to user privacy, traditional rule-based and payload-based traffic classification methods have become less effective. To address this problem, recent studies have introduced deep learning-based methods. However, most of these studies do not consider both the flow-level and packet-level characteristics, which we believe are significant in network traffic classification. To further improve the accuracy of traffic classification, this paper proposed DM-HNN, a hybrid neural network based on dual-mode features. First, we treat the packet length sequence as the flow-level feature and the initial byte of the packet as the packet-level feature. Then, we diverge into two paths to analyze the dual-mode features using neural networks. Finally, we combine the two-path features and output the final classification results. We have performed the experiments on public datasets, the results comparing to single-mode and dual-mode traffic classifiers indicate that DM-HNN can achieve excellent performance and has certain effectiveness.

Federated learning (FL) is considered to be a promising paradigm to solve data privacy disclosure in large-scale machine learning. To further enhance the privacy protection of federated learning, prior works incorporate the differentially private data perturbation into the federated system. But it is not feasible given the impairment of the model from noise, as adding Gaussian noise to achieve differential privacy (DP) deteriorates the accuracy of the model. In particular, the assumption that the sophisticated system is homogeneous is not realistic for real scenarios. Heterogeneous networks exacerbate noise disruptions. In this paper, we present FedSeC, a novel differential private federated learning (DP-FL) framework which operates with robust convergence and high-accuracy while achieving adequate privacy protection. FedSeC improves upon naive combinations of federated learning and differential privacy approaches with an updates-based optimization of relative-staleness and semi-synchronous approach for fast convergence in heterogeneous networks. Moreover, we propose a valid client selection scheme to trade-off fair resource allocation and discriminatory incentives. Through extensive experimental validation of our method in three different heterogeneities, we show that FedSeC outperforms the previous state-of-the-art method.

With the rapid development of communication networks, there are more stringent requirements for maintenance management. To carry out smart network maintenance automatically and effectively, this paper uses wearable devices, robots, and Unmanned Aerial Vehicles (UAVs) to collect on-site video data and detect defects in real-time. However, the deep learning models deployed in these devices should have fewer model parameters and less storage space. Therefore, we propose a model compression algorithm based on model pruning and model clustering in smart network maintenance. First, model pruning combines channel pruning and layer pruning and uses deep reinforcement learning to determine the pruning ratio of each layer automatically. This method can effectively compress the width and depth of the model while maintaining the accuracy of the model. Second, although the pruning operation greatly reduces the redundancy of the number of weight parameters, the number of bits of floating-point weights is still redundant. We propose an adaptive model clustering method to cluster the remaining nonzero parameter weights and compress the model. It combines advanced balanced iterative reducing and clustering using hierarchies (BIRCH) clustering and K-meansII clustering and takes the result k value of BIRCH clustering as the input of K-meansII. It can avoid limitations of prior knowledge and reduce clustering time. Simulation results show that the target detection model can reduce parameter redundancy, save storage space, and simplify calculation using the proposed algorithm. In addition, it can be better applied in the smart network maintenance environment.

The continuous development of network technology has driven the emergence of smart devices, and the demand for smart devices interconnection has increased sharply, which requires the identity of devices to be authenticated to carry out secure communication. The traditional certificate-based identity authentication scheme can no longer meet the authentication requirements of massive devices. As an authority that issues and manages certificates, Certificate Authority (CA) creates data islands of intra-domain certificates, increasing the complexity of cross-domain authentication. In order to improve the efficiency of cross-domain authentication, this paper introduces blockchain technology, which can establish trust in an untrusted environment. We propose a multi-CA-based authentication architecture to establish distributed trust and share cross-domain certificate information among multiple domains. On this basis, we design a simplified identity authentication scheme to quickly complete cross-domain identity authentication and reduce authentication overhead. To further improve the efficiency of cross-domain authentication, a cross-domain certificate revocation mechanism is designed. The scheme has passed the formal security analysis, and the simulation results show that the cross-domain authentication scheme is efficient.

With the development of Big Data technology and Internet, the surge of data in the network will cause network congestion and untimely task processing. Additionally, caching content in the core network may cause redundant access of content and backhaul bottlenecks. Due to the increasing requirements of users for task processing efficiency, the centralized maintenance system based on traditional cloud computing cannot meet the current computing requirements. In view of these problems, we propose a content collaborative caching mechanism based on joint decision of download delay and energy consumption. By integrating network coding and content caching technology, the work content maintained in the communication network is deployed near the edge of the network in the form of coding to reduce the redundant transmission of content and acquisition time of content. This article establishes a user QoE satisfaction model, which consists of two indexes that measure time delay and energy consumption. This article proposes a$\varepsilon$-hybrid Q-learning algorithm to optimize the placement of cache files, and made the cache action selection based on the combination of improved heuristic greedy algorithm and simulated annealing algorithm. The experimental results show that the proposed cache strategy can reduce the delay of users downloading content and the energy consumption of content cache, so as to improve the quality of field maintenance work in communication network.

Intelligent reflecting surface (IRS) is advanced as an effective technology to meet the high requirements of frequency spectrum and energy efficiency (EE) in future wireless communication systems, which can dynamically adjust its reflecting elements to control the incident signal and change the signal transmission path, thus improve the channel transmission environment. The prior works on IRS mostly considered the uplink scenarios with single cell, which however, did not address the issue of co-channel interference between different cells. This paper investigates an uplink wireless communication system with single IRS serving multiple cells with multiple users (UEs). The transmit power of users and the phase shifts of IRS are jointly optimized for maximizing the system throughput. The resulting non-convex optimization problem is solved by a heuristic algorithm, in which we exploit a non-cooperative game algorithm to solve the co-channel interference dilemma. Presented simulation results illustrate that the proposed scheme achieves a better performance in both system throughput and EE than other baseline algorithms.

Blockchain as a new decentralized chain structure can be used in edge computing to solve the security issue caused by edge nodes in model training. However, large amounts of data exchanges in the process of model training of edge computing reduce the performance of blockchain, and meanwhile, the block needed to be saved in the edge node challenges storage capacity of the edge node. Therefore, in the paper we propose a safe and efficient model training mechanism based on onchain and offchain collaboration. In the mechanism, edge nodes train models locally, store the model parameters in offchain and only return identifiers for model aggregation. By the method, the storage pressure of the edge node is reduced and the efficiency of executing consensus algorithms are increased. Moreover, in the mechanism we design a reputation evaluation model based on confidence factors to avoid the uploading of random and wrong data of edge nodes. Evaluation results show that our schemes can reduce the average delay and resources consumption, increase transaction throughput and maintain security compared with a state-of-the-art scheme.

Federated learning (FL) is a distributed framework for machine learning (ML) model training. Training agents upload local model parameters rather than original training data, and the central server performs parameter aggregation. FL can protect user data privacy and break the information island when training the ML model. Federated Average (FedAvg) is an aggregation method commonly used in the FL training task. The central server calculates the mean value of the local model parameters to obtain the new global parameters. FedAvg assumes that all the training agents are honest, which means the central server lacks terminal agents' knowability. When there are attackers in the training agents, the global model's performance may be deeply affected, and the training task cannot be completed normally. To solve this problem, we propose a Federated Learning method with aggregation based on the Importance of training agent (FedIM), in which the central server performs pre-evaluation on the agent parameters before aggregation, calculates the weights of parameters according to the historical behavior records of training terminals and performs federated aggregation to improve the anti-poisoning ability of learning task. Experiments show that our method can effectively improve the global model's anti-poisoning ability and accelerate the training speed compared with the FedAvg method when malicious agents are involved.

The blockchain system allows various trans-actions and information storage to be executed in a decentralized manner, while smart contracts require multiple nodes to be executed in the local sandbox environment according to preset settings to ensure the consistency of each node, which makes smart contracts unable to proactively obtain data from the outside world. Decentralized oracle can realize the acquisition of off-chain data with a low speed under the premise of ensuring the decentralization of the blockchain. Some oracles use on-chain data storage and maintenance to speed up data acquisition, but this will face higher costs of data storage and maintenance, so current oracles cannot simultaneously ensure privacy and security while taking into account execution cost and processing speed. In this article, we propose Select-Storage, a new oracle design pattern to achieve low operating cost and high processing speed without compromising security. Through experimental analysis, and comparison with other design patterns in processing time and on-chain and off-chain call costs, we have proved the superiority of the Select-Storage design pattern.

The mining of association rules plays an important role in fault prediction. Many studies have shown that there is an obvious temporal and spatial correlation between the failure records of the cluster system. Therefore, most cluster system failure prediction engines are built based on causal correlation analysis between log events. However, the original system log file usually contains a large number of invalid records (duplicate or non-fault related records), which makes the mining of event correlation extremely difficult and seriously affects the efficiency and accuracy of fault prediction. Therefore, this paper proposes an association rule mining and self-updating method based on weighted increment, named IWApriori (improved weighted Apriori algorithm). The method includes two important steps: 1) log preprocessing; 2) mining and updating of association rules based on improved algorithm IWApriori. This method can effectively improve the rule completeness and realize the efficient mining and updating of rules in the whole life cycle of the system. In addition, we used the real log data set Blue Gene/L to validate our method. The results show that our association rule mining method is better than other methods in terms of time performance, space performance and the effectiveness of mining rules.

With the rapid development of communication technology, communication networks are playing an increasingly important role in people's lives. Effective management of increasingly complex networks can improve the efficiency and stability of network operations. Fault management is one of the important functions of network management. The analysis of the alarms generated in the network can dig into the underlying rules to provide useful information for fault management. However, the existing alarm association rule mining algorithms often have the problem of parameter rigidity. In this paper, a two-level windows based alarm transaction extracting algorithm is proposed to solve the problem of low efficiency when using fixed size windows. Then this paper proposes an experience extraction method based on alarm priority in deep Q network (DQN), which can calculate the sampling probability according to the importance of alarm when the memory unit enters the queue. Aiming at the rare item problem caused by the fixed support threshold in association rule mining, the improved DQN is used to dynamically adjust the minimum support in rule mining algorithm. Experimental results show that the algorithm proposed in this paper can effectively improve the efficiency of alarm transaction extraction and the accuracy of alarm association rules mining.

Distant supervision relation extraction is an effective method to extract the real relation between entities from unstructured corpus. However, affected by the hypothesis of distant supervision mechanism, relation extraction model often faces the disturbance of mislabeled data and noise samples. In order to alleviate the above problems and improve the performance, we propose a relation extraction framework based on Bert-based pre-trained models, Bert for Relation Extraction (BRE). BRE uses BERT as feature extractor and loads pre-trained parameters for fine-tuning. It integrates external semantic knowledge with entity relation knowledge in specific tasks to improve the performance of classifier. In addition, we designed position enhanced CNN module and time-decay selective attention mechanism for BRE to bridge the semantic gap between external knowledge and relation knowledge, and alleviate the problem of mislabeling and noise in the multi-instance learning mode. We conducted experiments on NYT-10 and GIDS datasets, and the results show that BRE achieves the best performance.

With the increasing complexity of the network, the current network traffic has strong nonlinearity and burstiness. Therefore, the traditional traffic prediction model is no longer applicable. The neural network model, especially the LSTM, can well fit the nonlinearity of time-series data and preserve the information memory of the past. However, as for the periodicity of long-term span network traffic data, the neural network model does not perform well. Based on this, this paper proposes LTS-TP (Long-Term Span Traffic Prediction model), a network traffic prediction model, to solve the problem. First, the model decomposes the collected network traffic data using the improved STL decomposition algorithm to preserve the seasonal component. Then, the trend component and the remainder component are input into the Seq2Seq model based on the LSTM added with the improved attention mechanism for prediction. Finally, the predicted value of the output is added to the seasonal component, and the final network traffic prediction value is obtained. In the simulation part, this paper uses the MAWI public data set to test the proposed network traffic prediction model and compared performance with other models. The results show that the network traffic prediction model proposed in this paper has a good predictive effect on long-term span network traffic data.

Due to the connectivity of the communication network, the occurrence of faults is often cascaded. The infrastructure of the communication network is extremely vulnerable to the failure of the hardware and software, resulting in the node to fail to work. Moreover, large-scale application service failure is often caused by the cascade effect after the failure occurs. Therefore, researching and predicting fault behavior becomes important for maintaining the reliability of the communication network. This paper analyzes the mechanism of fault cascading propagation in communication networks, and proposes a fault prediction model based on load capacity model, resetting the node load and capacity to exhibit a non-linear relationship and sets the node load to be dynamically changing, which is more suitable for the flow of the actual network. The original load capacity model has only two states of normal and fault, but the state can be between normal and fault in the real network. Therefore, this paper adds a third state-congestion state to the model to make the model more meet the actual characteristics of the communication network. In addition, this paper also proposes a load redistribution strategy based on Top K node intermediary, which is used to simulate network traffic redistribution. The experimental results show that the fault prediction model proposed in this paper has improved the precision and accuracy of the prediction, and has a good prediction effect.

Due to the rapid development of the network, the network security situation is increasingly severe. The network security situation forecast analyzes the past network data and predicts the network situation to the warning of possible network threats in the future. Network security situation prediction can play an important role in network defense, network security warning and network resource allocation. We chose to predict network data first and then evaluate the network situation. We proposed a network security situation prediction method based on LSTM-XGBoost model. We built an improved LSTM neural network model to predict network security data and then used the XGBoost model to conduct situation assessment on the predicted data. The results of comparative experiments show that the model proposed in this paper can complete the task of network security situation prediction more efficiently and accurately.

To alleviate the security concerns caused by the openness of the edge computing network and meet the time-sensitive requirements of the edge devices' collaborative tasks, an effective trust evaluation mechanism is needed urgently to resist multi-attacks from various malicious devices. In this work, a light- weight trust mechanism based on multi-source feedback is proposed for edge computing. First, we design a light-weight data-processing algorithm executed in edge brokers and edge devices, which could reduce the data transmission pressure in communication networks effectively and work efficiently in large-scale edge networks. Then, a comprehensive evaluation method is designed for edge brokers based on the Dempster Shafer theory and multi-source feedback mechanism, which makes our mechanism more reliable and pluralistic when resisting various multi-attacks at the same time. At last, we originally develop a neural network in the centralized cloud to update edge brokers' hyper-parameters and weights of the key factors by auditing trust evaluation results uploaded from the edge network according to deep Q-learning algorithm, which are usually weighted manually and subjectively in traditional schemes. The experimental results show the proposed trust mechanism outperforms existing methods in reliability and calculation efficiency when resisting various malicious attacks.

With the development of the edge computing and cloud computing technology, the cloud-edge collaboration framework is proposed as a new effective computing architecture and applied in many fields. However, due to the openness of the edge networks, the security of cloud-edge framework is an unavoidable problem and most recent trust mechanism could not resist mixed malicious attacks at the same time. In this work, a light-weight and reliable trust mechanism based on the improved LightGBM algorithm is originally proposed to evaluate the credibility of edge devices. First, we design a light-weight trust mechanism for edge devices to process raw interaction data and extract trust features, which reduces the amount of data transmission and the pressure on the communication networks. In addition, an evaluation algorithm based on the entropy weight method (EWM) and punishment factors is designed for edge brokers to distinguish the malicious devices from the normal ones, which performs great against mixed malicious attacks. At last, we propose an improved LightGBM algorithm developed in the centralized cloud to learn other researchers' evaluation methods and check the evaluation uploaded from edge brokers, which could make the punishment factors of edge networks weighted adaptively with the change of edge networks. The experimental results show the proposed trust mechanism outperforms existing methods in the accuracy and discriminating speed under mixed malicious attacks.

Task offloading has been a hot topic in the field of edge computing. Resources fairness of edge computing servers which is the destination of task offloading directly impacts life of server and the process quality of task. In this paper, we propose a subtask-virtual machine mapping model (subtask-VM mapping model) to complete task offloading from the terminals to the servers. Considering the reasonable allocation of server resources, we also propose stack-based cache mechanism (SCM) to ensure the fairness of server resources allocation. We transform the problem of mapping model solution into the problem of optimal matching in the bipartite graph, and verify the performance of our algorithm by contrast experiment. In particular, the fair performance of our algorithm for server-side is over 84%.

In order to reduce the cost and energy consumption in wireless sensor network's charging process, this paper proposes a Recharging Scheme based on Lifetime Prediction (RSLP) for wireless rechargeable sensor networks. First of all, based on the historical quantity of electricity variation sequence of the sensor nodes, the lifetime prediction scheme of the sensor nodes is established; and then, considering the sensor nodes need to be recharged and the Sink nodes chosen by the mobile charger (MC) according to the charging value to establish an undirected complete diagram. A Hamilton charging circuit is established by using the Gene-Expressive cuckoo algorithm to solve the charging problem of the rechargeable sensor networks. The simulation experiments show that the proposed algorithm can improve charging efficiency and reduce the mobile energy consumption.

Mobile edge computing is a promising paradigm to compensate for the lack of traditional cloud computing, which has a variety of application scenarios. However, the migration of user-generated data in edge networks is a key issue which involves in transmission costs, the mobility of users, transmission resources, etc. In this paper, we focus on migrating deadline-varying user-generated data to edge servers, considering the tasks characteristics and contact patterns between nodes. We design a heuristic algorithm and propose the online algorithm using real-time information to save the cost of transmission. Further, we conduct the extensive simulations to demonstrate the effectiveness of our algorithms.

Opportunistic offloading can be utilized to offload computing tasks and traffic data in Mobile Edge Computing (MEC). To improve the ratio of successful data offloading and reduce unnecessary data redundancy in opportunistic forwarding process, some methods of evaluating a device’s forwarding capability are proposed. However, most of these methods do not consider the temporal impact from device mobility and the efficiency influence from the capability computation process. To settle these problems, we proposed a Transient‐cluster‐based Capability Evaluation Method (TCEM) to evaluate a device’s data forwarding capability. The TCEM can be divided into two steps. The first step aims to reduce computational complexity by evaluating a device’s possibility of contacting the destination within a time constraint based on the transient cluster generated by our proposed Transient Cluster Detection Method (TCDM). The second step is to calculate a device’s probability of directly and indirectly forwarding data to the destination. The probability as a metric of evaluating a device’s forwarding capability can be used in different data forwarding strategies. Simulation results demonstrate that the TCEM‐based data forwarding strategy outperforms other data forwarding strategies from the aspect of the proportion of the data delivery ratio to the data redundancy.

Fault-tolerant topology control is a critical problem in WSNs. It is important for improving network lifetime and reliability. In this paper, we present a novel algorithm FTMRT, which ensures Fault Tolerance by constructing a Multi-Routing Tree. We firstly construct a multi-routing tree of the initial topology, which ensures there are at least k-disjoint paths from each sensor to the set of supernodes. And then each sensor adjusts its transmission power according to the multi-routing tree to form the fault-tolerant network topology. In the topology maintenance phase, topology reconstruction is invoked each time there are some node fail and the supernode connectivity is broken. The effectiveness of the proposed algorithm is validated through simulation experiments.

The wireless sensors deployed at the highway can ensure the safety of the traveling vehicles. However, the ribbon deployed wireless sensor network in the roadside infrastructure can easily to generate energy hole. Cooperative communication between sensors and vehicles is an effective way to improve this situation and reduce the energy consumption of the sensors. A cooperative relay selection algorithm based on residence time (CRSR) and cooperative relay selection algorithms based on prediction (CRSP) are proposed in this paper. In order to improve the data transfer amount of the vehicle, residence time is considered in CRSR when sensors select the vehicles. To further improve energy efficiency CRSP considers arrival time of the vehicle to store collected data in the delay tolerance situation. Energy is also considered in CRSP to reduce the energy consumption and ease energy hole. Simulation results show that the CRSR and CRSP methods can reduce the energy consumption and prolong sensor network lifetime than the traditional algorithm.

HDFS is designed for storing large files, but it suffered performance penalty when storing large amount of small files such as the space occupied by the metadata cause high consumption of NameNode and low efficiency of file reading. Currently, there are many approaches implemented to solve the small file problem. In this paper we use additional hardware named SFS (Small File Server) between users and HDFS to solve the small file problem. The proposed approach includes a file merging algorithm based on temporal continuity, an index structure to retrieve small files and a prefetching mechanism to improve the performance of file reading and writing. The experimental results show that the proposed approach efficiently optimizes small files storing in HDFS with reducing the overload of NameNode and improving the performance of file accessing.

This paper proposes a novel indoor-outdoor caching relay system (CRS) and develops the corresponding caching mechanism, which can improve the utilization of wireless resources. It operates in two phases periodically. In Phase I, spectrum resources of the established links between MBS and user equipment (UE) are extracted to support data caching. In Phase II, caching relay system can directly serve indoor users and the fronthaul resources are released to serve other users. Simulations verify that compared with the conventional relay system (RS) the proposed CRS can improve the system throughput by at most 142% in the reusable data caching cases, only at the cost of temporarily suppressing the traffic rate to establish caching links.

To meet different communication requirements, a smart grid communication framework based on a hybrid network has been widely used. Virtual networks are established for various types of services respectively, and are embedded into heterogeneous substrate networks. Based on the framework, wireless network virtual mapping algorithm based on particle swarm optimization is proposed. In this scheme, the throughput is considered as fitness function, and parameters and operations of the particles are redefined. At last, comparing to basic heuristic algorithms, the proposed algorithm can perform better in term of throughput while satisfying the reliability of real time services.

Container transportation has become the main transportation form for international freight. In this paper, the energy saving and reliability tactics are considered and we design a new E-ZBR routing algorithm based on the original ZBR routing protocol. Firstly we propose the score criterion for estimating a path, and then based on nodes' connectivity, we select two existed better routing paths through improved FCM clustering algorithm. Through clustering, we get rid of those nodes with possible failure and construct a fault tolerance routing path with more reliability and robustness. We demonstrate that E-ZBR routing protocol has higher the energy efficiency and fault tolerance.

Fault detection in wireless sensor networks is a crucial and challenging task. Many detection approaches relying on specific rules or inference models have been proposed to distinguish faulty sensors by exploring spatial-temporal correlations among sensor readings. However, these approaches may require high communication overhead or computational cost, and many potential faulty sensors that may not generate anomalous sensor readings remain undetected. In this paper, we propose a metric-correlation-based distributed fault detection (MCDFD) approach. It is motivated by the fact that the correlations between sensor nodes' system metrics usually perform regularly, whereas abnormity of such correlations indicates failures. MCDFD explores sensor nodes' internal metric correlations using correlation value matrixes. An improved cumulative summation (CUSUM) algorithm is used to track gradual changes or abrupt changes. Once any changes occur in correlation value time sequences, potential failures can be detected. The apply of metric correlations has made MCDFD with high-energy efficiency and low computational complexity, since no communication overhead is incurred and CUSUM algorithm is simple for computation. Simulation results demonstrate MCDFD performs well in respects of higher detection accuracy and lower false positive rate even under high node failure ratios and dense distribution conditions.

Fault detection plays a crucial role in wireless sensor networks (WSNs). Many fault detection approaches requiring a priori knowledge of network faults have been proposed to distinguish faulty sensors by exploring spatial-temporal correlations among sensor readings. However, many faulty sensors that may not generate anomalous sensor readings, and potential failures with unknown types and symptoms remain undetected. In this paper, we propose a Metric-Correlation-Based Fault Detection (MCFD) approach using clustering analysis. It is motivated by the fact that the system metric correlations of most fault-free sensors usually show strong similarities, whereas different patterns of such correlations indicate potential failures. MCFD explores internal metric correlations inside sensors using correlation value views. An improved Neighbor-based Local Density Clustering Analysis (NLDCA) algorithm based on the Neighbor-based Local Density Factor (NLDF) is applied in spatial domain detection to cluster similar correlation value views together, thus potential faulty sensors with abnormal views not belonging to any cluster can be detected. Simulation results demonstrate that MCFD approach performs well in respects of higher detection accuracy and lower false positive rate even under high node failure ratios and dense distribution conditions.

The user's Quality of Experience (QoE) is an assessment of the human experience. It's not only influenced by Quality of Service (QoS) parameters but also influenced by user's preference for video content. This article studies user's preference for video content and how user's QoE changes on account of their biases. Through two experiments, it is concluded that the higher the user's preference score is, the higher the user rate MOS and the less MOS reduces when the resolution of video decrease. That is, the more user likes the video content, the more tolerant they will be to quality reduction of videos. Then a network resource management strategy is proposed based on the conclusion, and a web site platform is established for the test. Eventually we get the result that 87.0% of the participants have their MOS value increased after using the strategy.

MapReduce is an important distributed programming model for large-scale data-parallel applications like web indexing, data mining, and scientific simulation. Hadoop is an open-source implementation of MapReduce and it is often applied to short jobs for which low response time is critical. When the cluster nodes are homogeneous, Hadoop has a good performance. In practice, the homogeneity assumptions do not always hold. In heterogeneous environment, there are various devices which vary greatly in the capacities of computation, communication, architectures, memories and power. When different nodes process the same amount of data, load balancing problem occurs. In this paper we address the problem of how to assign data after Map phase to balance the execution time of each Reduce task by proposing a novel load balancing algorithm based on nodes performance (LBNP), in which the input data of poor performance nodes are decreased. Simulation results indicate that all the Reduce tasks can be completed in the same time which shortens the whole Reduce phase. Thus the efficiency of MapReduce is improved.

In order to assess the quality of experience (QoE) of HTTP video streaming, the model of three levels of quality of service (QoS): network QoS, application QoS and QoE, is employed in this paper. We mainly study the effects of pause position, and therefore propose two new application performance metrics: location of each pause and time interval of pauses. We first focus on the buffer behaviors of the video player, and correlate the application QoS with the network QoS, based on the analytical model and mathematical model. Then the subjective tests and experiments are carried out to assess how application performance metrics affect the QoE, and the Back Propagation Neural Net (BPNN) is established to map the application QoS to the QoE. This paper reveals that the pauses in the front part of the video, as well as the shorter time interval of pauses, have a higher negative effect on QoE of HTTP video streaming.

The current power consumption of intelligent terminals are over burden for their battery capacities, which directly restrict the hours used. In order to realize the energy saving of terminals in the LTE-A system, this paper puts forward the concept of virtual cells and a related uplink energy saving mechanism. Virtual Cell's resources and the outage probability of terminals are proposed by this mechanism as constraint conditions. The first step is sectioning off energy saving area in virtual cell. Secondly, we use the uplink CoMP (Coordinated Multiple Points Transmission/Reception) technology to provide diversity gain for the terminals of energy saving area. The third step depends on uplink power control which could adjust the mobile terminals' transmission power for energy saving. The simulation results show that the energy consumption of total terminals will decrease nearly 50% in the virtual cell while its capacity is lower than the 50% of maximum.

In the management of WSNs, the mechanism of fault detection and location based on active probing has been widely applied. The main optimal direction of active probing is to maximize the coverage of nodes in the network by sending minimal set of probes from probe stations. Therefore, before probing, selecting optimizational station set to improve reachable rates of probed nodes has significant influence on detection effect of active probing. In this paper, we propose an optimizational strategy of probe station selection (PSS) by Genetic Algorithm (GA) and achieve the improvement of confirmed achievable rates of probed nodes. Meanwhile, lower runtime cost and more reasonable usage of energy are reached.

The main role of wireless sensor networks is to collect environmental data. As the sensor nodes are vulnerable and work in unpredictable environments, sensors are possible to fail and return unexpected response. Therefore, fault detection and recovery are important in wireless sensor networks. In this paper, we propose a fault detection algorithm based on support vector regression, which predicts the measurements of sensor nodes by using historical data. Credit levels of sensor nodes will be determined by a contrast between predictions and actual measured values. In this paper we also propose a fault recovery algorithm according to the node credit levels combined with genetic algorithm. The simulation results demonstrate that the algorithms we propose work well in failure detection rate, fault recovery speed and energy consumption.

Since wireless sensor network has limited resources, it's important to design its task allocation algorithm reasonably to reduce energy consumption. The contract net is simple and flexible so that it can meet the needs of the wireless sensor network. In this paper, we introduce the improved C-MEANS algorithm to cluster nodes to decrease the number of bidders, and at the same time, the LMS algorithm is adopted to predict the bid value of the nodes. The simulation results show that the energy consumption and traffic flow are reduced, and the bid value more accurately reflects the status of the node when allocated tasks, which increased the complete rate of network tasks.

Coalition formation is an essential component for in wireless sensor network (WSN). Most of current coalition formation algorithms have focused on disjoint coalitions. We develop an improved ant colony algorithm to solve the overlapping coalition formation(OCF) problem in multiple coalitions in WSN domain. In this improved ant colony algorithm, we bring in mutation operation and elite strategy from genic algorithm. By doing this, it will improve the pheromone update strategy and allow sensors to allocate different parts of their resources to serve different coalitions simultaneously.

Since there is no central management center in the MANETs, nodes need to self-manage service provided by other nodes. To pursue maximal utilities, they should be able to negotiate autonomously for services, e.g., packets transmission, information share. While some selfish mobile nodes in MANETs are unwilling to provide services for other users, it directly leads to serious decline in network performances. Hence an effective negotiation mechanism is required to stimulate them to cooperation. In this paper, we present a service-oriented negotiation model between selfish nodes in view of one-to-many application scenarios, driven by the basic intuition that negotiators tend to maximize their individual payoffs while ensuring that an agreement is reached. We develop the genetic algorithm to make the negotiation more adaptive in the MANETs. The simulation results show that the algorithm reduces energy consumption and communication traffic in deed.

In the open MANETs, nodes with different goals expect to benefit from others, but are unwilling to share their own resources. These selfish behaviors have posed increasing research challenges for cooperation. Negotiation as a key form of interaction for two or more parties enables nodes to announce their contradictory demands and seek to an agreement by concession. In the paper, the Service Negotiation model for Selfish nodes in the MANETs (SNSM) combines the policies of imitating rivals' behaviors and fast-approaching reserve prices presented to generate mutual offer and counter-offer for service bargaining. Specially, the model provides three types of changing rates of bids to speculate the rivals' behaviors. In addition, we improve the Weber-Fechner's law to self-adjust the deadline in the negotiation. Simulation results demonstrate our model has superior performances in increasing the negotiation efficiency, achieving mutual benefits between the service buyer and seller.

This paper studies task allocation in cluster-based Wireless Sensor Network (WSN) using negotiation model. We study both the negotiation reasoning model and the negotiation protocol for task allocation to achieve energy efficiency while balancing nodes energy. Reasoning model determines the offer generate scheme and gives control over negotiation process. A time depending Boulware function is used as the concession strategy in reasoning model to balancing efficiency and utility. Contract net protocol is used as negotiation protocol to regulate the interaction style of nodes. The goals of this study are: 1) energy efficiency task allocation; 2) maintaining energy balance of nodes in WSN after the task to prolong the network life cycle. Experimental results using this cluster-based negotiation model task allocation approach verify its performance.

In a clustering-based MANETs, task allocation has posed increasing research challenges because the needs of management and coordination are accentuated by complicated demands of cluster members. A self-adaptive method of task allocation is designed to facilitate self-planning and self-negotiation for nodes during tasks being distributed and executed. The method is composed of two parts: for one part, the cluster head works out an integrated schedule for tasks, including selecting different sets of execution nodes and defining their functions according to task types. Cooperative group towards synergetic task is formed by policies of filtering and voting. Assignment modes based on either polling or mobile agents are also involved, the latter adopts an improved Ant Colony Optimization (ACO) algorithm to plan a migration path. For another, if a cluster member fails to accomplish a task, it could negotiate as a tenderee with other nodes using a revised contract net protocol. In addition, we employ a stimulation mechanism of distributing virtual task experience in connection with QoS guarantees to offer compensation for nodes' energy consumption and extra load. Simulation results demonstrate performance benefits of our self-adaptive method can efficaciously alleviate load of the cluster head, balance loads of nodes in consideration of energy restriction, and prolong the lifecycle of the cluster.