To ensure real-time performance and reliability, workloads in an airborne-cloud are often planned in advance, thereby making key task attributes—such as estimated arrival time, execution duration, and resource requirements—available prior to scheduling. Such foresight provides an opportunity to optimize scheduling from a long-term perspective, whereas most existing airborne-cloud schedulers are designed for online settings and assume that future task information is unavailable. To bridge this gap, we formalize the planned task scheduling problem and propose ElitePT (Elite Genetic Algorithm for Planned Tasks), a scheduling strategy that explicitly exploits planned information. ElitePT evaluates candidate schedules with a long-term performance objective that jointly accounts for load balancing and energy consumption over a planning horizon, and it strengthens the evolutionary search by injecting heuristic-constructed elite individuals while enforcing population diversity through Hamming-distance-based initialization. Experiments in CloudSim show that, compared with representative baselines including least-loaded scheduling, rotating scheduling, and a standard genetic algorithm, ElitePT delivers consistently better long-term scheduling quality and stability; across diverse cluster scales, heterogeneity settings, and overlap levels, it improves long-term load balancing by 20–50

Avionics systems are evolving from Integrated Modular Avionics (IMA) to Distributed Integrated Modular Avionics (DIMA), where distributed computing nodes are interconnected through real-time networks to support flexible resource sharing and latency-critical services. This architecture is highly consistent with the paradigm of Mobile Edge Computing (MEC), in which distributed edge resources collaboratively process computation workloads close to users to meet stringent real-time requirements. However, efficient task scheduling and migration remain key challenges in such distributed MEC platforms, since many existing approaches are designed for traditional centralized architectures and lack effective support for runtime workload dynamics and migration overheads. In this paper, we abstract the computing resource and task models for DIMA-oriented MEC systems and propose two algorithms: an Efficient Workload Scheduling Algorithm (EWSA) for workload placement and a Workload Migration Algorithm (WMA) for adaptive task relocation. CloudSim-based simulations show that the proposed methods significantly outperform the benchmark JIT-C approach in scheduling performance and migration efficiency, demonstrating their effectiveness for real-time distributed edge computing environments.

In smart factory operations, equipment inspection is a critical process for ensuring production safety and efficiency. Owing to their flexibility, safety, and efficiency, Unmanned Aerial Vehicles (UAVs) have been widely adopted in smart factory inspection systems. However, constrained by limited computational power and battery capacity, data collected by UAVs can be offloaded to servers for collaborative computation. Meanwhile, inspection tasks typically exhibit strong dependencies, heterogeneity, and periodicity, which complicates offloading decisions and compromises real-time performance. To address these challenges, we establish a three-layer computational offloading architecture, a cloud-edge-UAV collaborative inspection system, and propose a Cache-Assisted Task Offloading (CATO) strategy aimed at minimizing system delay. First, a multi-metric task prioritization mechanism optimizes the execution order of subtasks. Second, an edge cache placement strategy reduces redundant computation for periodic tasks. Further, a preference-based task-server bi-directional matching model incorporating a stable matching algorithm ensures efficient offloading. Finally, we implement dynamic co-optimization of caching and offloading via iterative updates to further enhance system performance. Simulation results show that CATO reduces system delay by up to 20.0 % compared to NoCache strategy.

Low Earth Orbit (LEO) satellite constellations are crucial for enabling global coverage and low-latency services. Satellite Edge Computing enables on-board processing to improve task responsiveness and reduce backhaul load. Microservices, with their modular and lightweight design, naturally fit the dynamic and constrained satellite environment. However, deploying microservices on LEO satellites faces unique challenges, including stringent energy constraints, highly dynamic connectivity, and complex service dependencies across mobile nodes. In this paper, we propose a Microservice Deployment Framework for Satellite Edge Computing (SEC-MDF). We construct a microservice deployment model that includes real track dynamics, service dependencies, resource constraints, and data transfer patterns, and design a deployment strategy based on deep reinforcement learning (DRL). This strategy is augmented by Heuristic-based Episodic Reward Optimization (HERO), a tailored reward optimization mechanism for SEC-MDF. By integrating A*-based heuristic cost estimation, stage-aware episodic reward buffer, and adaptive reward normalization, HERO significantly enhances the performance of the deployment. Extensive experiments against both heuristic algorithms and DRL variants demonstrate that our framework reduces end-to-end latency by 40 % and system energy consumption by 29 %, significantly outperforming existing approaches. Ablation studies further confirm the critical contribution of the HERO mechanism to overall performance.

In our exploration of Mobile Edge Computing (MEC) systems, we address the critical challenge of edge server deployment, aiming to enhance application responsiveness through optimized server placement and cooperation. Our study diverges from traditional approaches that prioritize server location, instead highlighting the untapped potential of server collaboration for sharing computing resources. This cooperative strategy not only boosts resource utilization and trims response times but also intricately complicates deployment strategies. We introduce an innovative Collaboration-Based Server Deployment (CBSD) algorithm that stands out by facilitating cooperative communication between edge servers via Base Stations (BSs), even under stringent resource constraints. This algorithm employs a dual-phase approach: initially utilizing a non-collaborative Gradient algorithm for resource allocation among cooperative regions, followed by a strategic distribution of resources based on regional demand. Our comprehensive simulations show that our proposed methodology improves system utility and throughput by 35% and 25%, respectively, while robustness reaches 90% compared to the baseline. These results represent improvement in managing limited edge resources effectively.

Edge cloud computing extends cloud resources to the network edge, catering to the increasing demands of edge devices and applications. Traditional container orchestration engines, while suitable for edge environments, often rely on static scheduling algorithms that consider only CPU and Memory, inadequate for the diverse needs of edge applications. This paper proposes an enhanced scheduling algorithm that incorporates two new metrics: pod-rate and ephemeral-storage, offering a more comprehensive approach to resource optimization. Additionally, it introduces a dynamic weighting mechanism using the Dynamic Load Balancing Scheduling Algorithm, which adjusts resource weights in real time based on usage during Pod deployment. Experiments demonstrate that this algorithm reduces the standard deviation of comprehensive loads by 57% compared to standard scheduling algorithms under high cluster loads. This boost improves edge computing's load balance and resource efficiency.

We investigate the problem of path planning and task offloading for UAV clusters in a UAV-assisted edge computing scenario. UAVs autonomously make decisions regarding path planning, continuous service provision, and task offloading based on collected information. In this setting, terminal equipment (TE) cannot directly connect to servers; thus, UAVs act as both edge servers and communication relays, proactively providing services to TEs. We construct a fine-grained temporal scale model that decomposes UAV actions into atomic time units, transforming decision-making on specific behaviors into state transition decisions. This approach better accommodates the needs of time-varying environments. Regarding path planning, given the time-sensitive nature of TE requests, we focus on how to provide stable and timely computational services to TEs. We propose a multi-agent reinforcement learning algorithm capable of dynamically sensing task priorities to enhance Quality of Service (QoS), with optimizations made in terms of task completion rate, UAV energy consumption, and processing delay. About task offloading decision, we introduce a dual-keyword-based offloading algorithm to optimize the binary offloading process. Finally, we conduct simulation experiments to demonstrate the effectiveness of the proposed algorithms, and comparative experiments confirm their superiority.

Cross machine traffic caused by distributed microservice deployment in edge computing significantly affects service performance. And the dynamics of the edge computing, such as fluctuating user request patterns and different network delay make static scheduling stategies challenging. To address these two issue, we first propose a Cross-Machine Traffic-Aware Scheduling Algorithm (CTSA), which models the microservice deployment process as a Markov Decision Process and utilizes a Dueling DQN-based approach to minimize cross-machine traffic while balancing node resource usage. Furthermore, we propose a Dynamic QoS-Aware Scheduling Framework (DQSF) that adapts deployment decisions in real time based on system monitoring to address the challenge of dynamics. Experimental evaluations using a real-world microservice application show that our approach significantly reduces request response time up to 30.2%, improves throughput to 36.7% and ensure Quality of Service (QoS) under dynamic edge computing continuum.

Unmanned aerial vehicles (UAVs) have attracted widespread attention in post-disaster search and rescue (SAR) due to high flexibility and low-cost advantages. However, traditional centralized control approaches face problems such as poor adaptability and low robustness in complex and dynamic post-disaster environments. In order to improve the autonomous and execution efficiency of UAV cooperative search tasks, decentralized control methods have gradually become a research focus. However, how to efficiently realize autonomous path planning for UAVs under the condition of limited computational resources is still a key challenge to be solved. In this paper, we propose a dynamic adaptive path optimization method based on evolutionary neural network (DAPO-ENN), which combines the global search capability of evolutionary algorithms with the adaptive characteristics of neural networks to realize the centerless autonomous path planning and search coverage optimization of UAVs in post-disaster environments. DAPO-ENN can optimize the performance of the model under the limitation of computational resources, and adapt to the dynamic changes of the environment by online path optimization adjustment, so as to effectively improve the coverage efficiency while ensuring a high search coverage rate. The experimental results show that the DAPO-ENN proposed in this paper has stronger environmental adaptability and lower resource consumption than the existing comparison algorithms. The results suggest that the method provides an efficient and flexible solution for the cooperative search of UAVs after disasters.

With the continuous development of business intelligence and scientific exploration, graphs have been extensively applied to various fields. Graph clustering has emerged as a crucial task for mining the structure and function of complex networks. However, existing clustering algorithms often overly emphasize the density and degree of vertices in the graph while neglecting the correlations and structural characteristics among vertices, resulting in poor performance when clustering graphs. In this paper, we propose a novel method called Structural and Cyclic Similarity (SCS) for structural graph clustering, aiming to improve the quality of clustering. Our method utilizes short-length cycles and paths, which are common graph motifs, to comprehensively capture the neighborhoods and graph motifs of connected vertices. This enables us to quantify the similarity between vertices effectively. The SCS is then applied to structural graph clustering algorithms, thereby improving the clustering quality. To efficiently compute the SCS, we give an algorithm of subgraph counting, which rapidly counts all short-length cycles in the graph. Experimental results conducted on six real-world datasets demonstrate that the clustering algorithm based on SCS outperforms other similarity measures in terms of clustering quality and can improve the effectiveness of graph clustering.

With the increasing complexity of deep neural network (DNN) models and the constrained computational and storage capabilities of user equipment (UE), the efficient inference of DNN models becomes a challenge. As an extension of cloud computing, edge computing was proposed to alleviate the pressure on cloud servers. However, the optimal offloading strategy and resource allocation for different types of DNN model tasks in Edge computing systems are still open problems. In this paper, we propose a DNN inference acceleration strategy based on deep reinforcement learning (DRL) for edge computing collaborative inference. Our approach aims to obtain the optimal DNN offloading strategy and resource allocation policy to achieve the lowest inference delay for each task request. We also consider the waiting time of tasks in resource-limited stations. Experimental demonstrate that our algorithm can decrease the average inference latency by as much as 62% than the compared to the Edge-Only algorithm.

In an intelligent transportation system, accurate traffic flow prediction can provide significant help for travel planning. Even though some methods are proposed to do so, they focus on either algorithm or data level studies. This work focuses on both by proposing a Community-based dandelion algorithm-enabled Feature selection and Broad learning system (CFB). Specifically, a feature selection method is adopted to choose suitable features aiming to avoid redundant ones affecting prediction accuracy, and a neural network-based learning algorithm, namely a Broad Learning System (BLS), is used to predict traffic flow. In order to further boost its prediction performance, a Community-based Dandelion Algorithm (CDA) is proposed by considering an individual and its multiple offspring as a community and adopting a learning strategy for different communities. The proposed CDA is used to a) choose the suitable features as a feature selection method; and b) optimize the parameters and network structure of BLS. CDA’s superiority over its competitive peers is first verified on CEC2013’s benchmark functions, and then the proposed CFB is applied to handle the traffic flow prediction problems. The results indicate that it can improve the prediction accuracy by 5%-16% compared to the updated traffic flow prediction methods.

There are two mainstream strategies for image-text matching at present. The one, termed as joint embedding learning, aims to model the semantic information of both image and sentence in a shared feature subspace, which facilitates the measurement of semantic similarity but only focuses on global alignment relationship. To explore the local semantic relationship more fully, the other one, termed as metric learning, aims to learn a complex similarity function to directly output score of each image-text pair. However, it significantly suffers from more computation burden at retrieval stage. In this paper, we propose a hierarchically joint embedding model to incorporate the local semantic relationship into a joint embedding learning framework. The proposed method learns the shared local and global embedding spaces simultaneously, and models the joint local embedding space with respect to specific local similarity labels which are easy to access from the lexical information of corpus. Unlike the methods based on metric learning, we can prepare the fixed representations of both images and sentences by concatenating the normalized local and global representations, which makes it feasible to perform the efficient retrieval. And experiments show that the proposed model can achieve competitive performance when compared to the existing joint embedding learning models on two publicly available datasets Flickr30k and MS-COCO.

Deep Neural Network (DNN) has been widely used in intelligence applications due to its excellent performance in executing inference tasks. Since DNN tasks require a large amount of computation and high-resolution raw input, collaborative inference is proposed to partition the DNN model from the middle layer to minimize the end-to-end latency. However, when existing work attempts to combine collaborative inference with task offloading in cloud-edge-end systems, two challenges result in poor latency and throughput: excessive layers in the model make it difficult to find suitable partitions, and multiple decision variables make the reinforcement learning agent challenging to converge. This paper aims to reduce the long-term average end-to-end latency of DNN tasks by jointly optimizing task offloading, model partitioning, and resource allocation in dynamic environments. To solve the problem of failing to find suitable partitions, we propose a novel Optional Partition Point Compression (OPPC) algorithm, which selects the high-quality partition points based on layers’ output feature to reduce the difficulty of model partitioning. To improve the convergence performance of the agent, we propose a Reinforcement Learning based Collaborative Inference Optimization (RLCIO) algorithm. Unlike the existing reinforcement learning architecture, RLCIO decouples resource allocation using an Edge Computing Resource Allocation (ECRA) algorithm to reduce the agent’s decision variables. Simulation results show that the RLCIO algorithm performs better than five related schemes, reduces the average end-to-end latency of system tasks by 72% and improves the system throughput by 3.5x in the best case.

In the field of deep learning, a large number of correctly labeled samples are essential for model training.However, in practical applications, labeling data requires high labeling cost. At the same time, the quality of labeled samples is affected by subjective factors or tool and technology of manual labeling, which inevitably introduces label noise in the annotation process. Therefore, existing training data available for practical applications is subject to a certain amount of label noise. How to effectively train training data with label noise has become a research hotspot. Aiming at label noise learning algorithms based on deep learning, firstly, the source, classification and impact of label noise learning strategies were elaborated; secondly, four label noise learning strategies based on data, loss function, model and training method were analyzed according to different elements of machine learning; then, a basic framework for learning label noise in various application scenarios was provided; finally, some optimization ideas were given, and challenges and future development directions of label noise learning algorithms were proposed.

在多机器人协同领域,传统的协同模型虽然解决了协同实体间的信息交互、共享和通信问题,但复杂多变的协同环境所需要的决策机制并没有在模型层得到支持,只能通过应用程序来实现,导致协同系统开发困难并影响协同决策过程的执行效率.针对传统的协同模型存在无法灵活地支持用户决策的问题,本文提出一种基于事件具有决策能力的元组空间协同模型DEBC(Decision and Event Based Coordination).DEBC模型在元组空间框架中引入决策机制,并对应用层的协同任务进行部分抽象,通过赋予元组空间一组支持决策的操作,使得协同应用程序开发具有高度的灵活性和适应性.同时引入事件机制,保证了协同实体间协同行为的灵活性和高效性.最后,对DEBC模型进行实例分析并与现有模型进行实验对比分析,验证了DEBC模型具有良好的表达能力和更高的执行效率,其提供的决策机制、事件机制具有广泛的适用性.

Service mesh is gaining popularity as a microservice architecture paradigm due to its lightness, transparency, and scalability. However, fully releasing configurations to the data plane during the business development phase can result in noticeable performance degradation. Therefore, fine-grained traffic management of microservice applications is crucial to service performance. This paper proposes a novel configuration distribution algorithm, DATM, which utilizes inter-service dependencies from the service call chain to manage data-plane traffic and dynamically maintain cluster services. The proposed algorithms enable on-demand distribution based on the obtained service dependency relationships by combining monitoring, information processing, and policy distribution. We validate the proposed mechanism and algorithms via extensive experiments. We show that the approach reduces the memory usage of data-plane agents and improves system resource utilization. Additionally, this reduces the time to issue configuration while effectively saving storage space and significantly reducing the number of cluster updates. Consequently, this approach ensures application performance and guarantees the quality of microservice applications in clusters.

With the development of cloud computing, data owners usually choose to store data in the cloud. But cloud servers may not be fully trusted. Due to privacy concerns, data owners need to encrypt the data before storing it in the cloud. There is still a lack of solutions that satisfy both safety and efficiency. To perform secure queries on encrypted data, we propose a scheme. The scheme includes an encrypted index based on B + tree, which can hide the order information of sensitive data. It also includes a secure search algorithm based on the encrypted index, which is implemented through the interaction protocol between the client and the server. We analyze the scheme’s security and prove that the scheme can protect the privacy of data, queries, results, and access patterns. At last, we perform experiments on five datasets to verify that the scheme is effective.

At present, deep learning has been well applied in many fields. However, due to the high complexity of hypothesis space, numerous training samples are usually required to ensure the reliability of minimizing experience risk. Therefore, training a classifier with a small number of training examples is a challenging task. From a biological point of view, based on the assumption that rich prior knowledge and analogical association should enable human beings to quickly distinguish novel things from a few or even one example, we proposed a dynamic analogical association algorithm to make the model use only a few labeled samples for classification. To be specific, the algorithm search for knowledge structures similar to existing tasks in prior knowledge based on manifold matching, and combine sampling distributions to generate offsets instead of two sample points, thereby ensuring high confidence and significant contribution to the classification. The comparative results on two common benchmark datasets substantiate the superiority of the proposed method compared to existing data generation approaches for few-shot learning, and the effectiveness of the algorithm has been proved through ablation experiments.

Aiming at the problems such as small object size, arbitrary object direction and complex background of remote sensing images, on the basis of YOLOv5 （You Only Look Once version 5） , algorithm, an algorithm involved with geometric adaptation and global perception was proposed. Firstly, deformable convolutions and adaptive spatial attention modules were stacked alternately in series through dense connections. As a result, a Dense Context-Aware Module （DenseCAM） , which can model local geometric features was constructed on the basis of taking full advantage of different levels of semantic and location information. Secondly, by introducing Transformer in the end of the backbone network, the global perception ability of the model was enhanced at a low cost and the relationships between objects and scenario content were modeled. On UCAS-AOD and RSOD datasets, compared with YOLOv5s6 algorithm, the proposed algorithm has the mean Average Precision （mAP） , increased by 1. 8 percentage points and 1. 5 percentage points, respectively. Experimental results show that the proposed algorithm can effectively improve the precision of object detection in remote sensing images.