The computing power network (CPN) overcomes the limitations of single-point computing performance by integrating computing and network resources. Latency and energy consumption during the task offloading process are key performance indicators for evaluating the CPN. However, most existing algorithms execute tasks based on their order of arrival, which fails to meet the requirements of latency-sensitive tasks. Additionally, they lack adjustment of offloading preferences when the number of network devices dynamically increases, leading to uneven task distribution and increased energy consumption. To address these issues, this paper proposes a priority-based multiobjective weight-adjusted Q-value task offloading optimization algorithm (PMWQ). First, tasks are prioritized before offloading to ensure that latency-sensitive tasks are processed first, thereby reducing latency. Second, an adaptive dynamic weight Q-value adjustment strategy is employed to balance the load among devices at different levels and reduce energy consumption. Moreover, the algorithm optimizes the feedback mechanism through a dual Q-function table to improve decision accuracy. Simulations show that, with 210 devices, the PMWQ algorithm outperforms baseline methods by increasing task success rates by 3.72%-17.47%, reducing average waiting delays by 58.81%-75.93%, lowering average energy consumption by 4.32%-10.24%, and enhancing average CPU utilization by 14.82%-27.92%.

The cloud-edge-end network architecture is an emerging model that integrates the advantages of both cloud and edge computing to effectively enhance the system's computational capacity. However, a key challenge within this architecture is how to efficiently offload tasks to fully utilize distributed computing resources while minimizing task execution latency. Most existing approaches assume that complete system information can be obtained in real time to make task offloading decisions. However, this assumption often leads to high communication overhead in practical applications, and the system's dynamic nature can make obtaining complete information impractical. To address this challenge, we propose a partially observable task offloading algorithm (POTO) that makes efficient offloading decisions based on partial system information. First, we model the task offloading problem as a partially observable Markov decision process (POMDP) and design an encoder using a Long Short-Term Memory (LSTM) network to extract system state information from past offloading decisions. Finally, we improve the actor-critic algorithm with a clipping mechanism and action masking to achieve an efficient offloading strategy. Experimental results show that POTO achieves a 95% task success offloading rate while reducing latency by at least 14% compared to other algorithms. Furthermore, even with partial system information, POTO performs at 96% of the effectiveness of algorithms utilizing complete system information.

The Computing Power Network (CPN) represents an emerging architecture for large-scale distributed computing, however, it remains vulnerable to external attacks and malicious behaviors during task offloading. Federated learning (FL)-based intrusion detection systems (IDSs) have been widely adopted as an effective defense mechanism. However, it faces two significant challenges within the CPN: data heterogeneity across edge computing nodes (ECNs) and poisoning attacks from malicious ECNs. To address the first challenge, we propose SECFL-IDS, a clustered Federated Learning framework for intrusion detection in CPN. By assessing each ECN's local model performance with public data on the cloud server, the framework groups ECNs with similar data characteristics into the same clusters. To tackle the second challenge, we introduce a lightweight poisoning detection (LPD) algorithm that compares the update directions of each ECN's local model with those of the global model within the cluster. This method enables the dynamic identification of malicious ECNs during the iteration phase of FL, thereby boosting the system's robustness. Experiment results on two datasets demonstrate that SECFL-IDS achieves improvements of 4.88% and 5.93% in F1 score compared to FedAvg in highly heterogeneous data environments. Furthermore, under poisoning attacks that flip all labels, SECFL-IDS-LPD achieves improvements of 7.87%and 7.65%in F1 score compared to FedAvg.

Federated Learning (FL) is an emerging distributed learning framework for collaboratively training global models while protecting data privacy. However, FL faces serious threats from malicious attacks such as model poisoning and data poisoning. To address these challenges, this paper proposes FedMRA (MRA: Multimodal feature analysis and Reputation Aggregation). FedMRA establishes an anomaly detection index system through multimodal feature extraction, combines HDBSCAN clustering, historical trajectory sparsification analysis and dynamic reputation assessment mechanism, and adopts an aggregation strategy based on reputation weight fusion to defend against malicious client damage. Experiments show that FedMRA performs well against multiple types of attacks (label flipping attack, gaussian attack, and random gradient attack), especially when up to 30% malicious clients are involved, and still significantly improves the robustness and accuracy of the global model. FedMRA provides an efficient and robust defense scheme for FL, and it performs well in both no-attack and attack scenarios.

Semi-supervised learning methods combine a small amount of labeled data with a large amount of unlabeled data to achieve high-precision segmentation while reducing the annotation cost. However, existing semi-supervised learning methods usually focus on data-level perturbations or improvements in network structures, ignoring the problem of insufficient information interaction between different branches and regions in complex texture tasks. In addition, in scenarios that require high-resolution processing (such as 3D medical images), traditional Transformer-based methods are not only computationally expensive but also prone to overfitting problems. Therefore, to address the above problems, we propose a Mamba based Consistency Constraints network (MCC-Net) for semi-supervised 3D medical image segmentation. Specifically, the model is organized by a shared encoder and three-branch decoder architecture. First, a consistency regularization constraint mechanism is introduced to combine the segmentation map of one decoder with the pseudo-labels of other decoders, thereby capturing more valuable features in high-uncertainty areas and generating stable, low-entropy predictions; second, a new consistency loss function is designed to construct constraints between the signed distance map (SDM) of the two auxiliary decoders and the segmentation map of the main decoder to enhance the learning ability of the target geometric structure. In addition, a Fusion Mamba(FM) Block is proposed to improve the model’s capabilities in deep semantic feature extraction and computational efficiency by modeling long-distance dependent features. Experimental results on public dataset show that, compared with six state-of-the-art semi-supervised segmentation methods, our method achieves Dice scores of 89.48%, 91.46% and 91.96%, respectively, when 10%, 20% and 30% of labeled data are used for training, significantly outperforming the other methods. The experimental results show that the model has strong advantages in both segmentation accuracy and utilization of unlabeled data.

The cloud-edge–terminal architecture relies on hierarchy for resource allocation but lacks global optimization. The computing power network (CPN) introduces a new distributed computing paradigm, integrating cross-domain, heterogeneous resources for global scheduling. However, most CPN research focuses on task optimization during resource allocation, while neglecting the similarity of random tasks before the allocation stage. Additionally, fragmented CPN resources and complex task demands pose challenges to global load balancing. This article proposes a deep reinforcement learning framework with task merging and congestion avoidance for on-demand resource allocation. Specifically, a low-complexity similar task merging algorithm reduces redundant resource consumption during task preprocessing. In task offloading, the principal neighborhood aggregated graph neural network captures CPN’s intricate features. Lyapunov optimization, integrated into a multithreaded training framework, minimizes resource backlog congestion. A carefully designed reward function balances multiple objectives, enhancing computing resource utilization efficiency and ensuring system stability. Theoretical analysis shows that with control parameter V, the tradeoff between resource utilization efficiency and system stability follows the relationship [O(1/V), O(V)]. Extensive experiments demonstrate a 33.5% improvement in resource utilization efficiency and a 62.7% increase in task offloading success rates with respect to those in state-of-the-art algorithms. The proposed algorithm exhibits robustness and effectiveness, particularly in high-load and real network topologies.

Nuclei detection and segmentation are indispensable prerequisites in digital pathology research, whereas the precise segmentation of nuclei by domain experts relies heavily on global spatial information and the inter-nuclei correlation. However, previous automatic nuclei segmentation works are mostly built on convolutional neural networks, which are unable to capture long-range global context with their inherent convolutional operations. Additionally, window-based design in few transformer-based approaches limits remote token interactions. The present study introduces a novel Multi-Local Perception (MLP) network, MLPSeg, which is proposed to address the aforementioned challenging issues. Specifically, the parallel computation of depthwise separable convolution and local window attention is designed to extract local information. Then, the parallel module of local horizontal attention and local vertical attention is designed to establish the global dependency. Moreover, to model the cross-scale dependencies and narrow the contextual semantic gap, the Context Cross Attention (CCA) is introduced for optimising skip connections. A tri-decoder structure is adopted to generate nuclei instance masks, normal edge masks and clustered edge masks. The superior performance of MLPSeg for nuclei segmentation is demonstrated across two datasets with different modalities, resulting in a 2.29% - 5.82% improvement compared to the state-of-the-art methods.

With the deep integration of computing and network development, as a new type of network infrastructure, computing power network (CPN) has become a research hotspot in the industry. Computing resource metrics integrates the computing resources connected to the CPN, realizes the collaborative management of heterogeneous resources through the measurement of multi-dimensional computing resource, and provides an accurate resource view for resource matching, which has become an important part of the CPN. The traditional measurement methods are too single to measure computing resources from a single dimension, which is difficult to adapt to the development of CPN. The existing methods of computing resource metrics need to be improved in the accuracy of resource matching and cannot reflect the comprehensive performance of computing resources. In this paper, a multi-dimensional computing resource measurement method based on entropy weight TOPSIS is designed to score the comprehensive performance of computing resources, storage resources and communication resources of computing nodes, then the nodes are divided into different categories of comprehensive performance according to the score, so as to narrow the scope of resource matching for different user requirements. At the same time, a multi-dimensional resource matching algorithm based on deep reinforcement learning is proposed. The resource matching process is constructed as a Markov decision process to realize the matching of tasks and nodes. The simulation results show that the proposed algorithm can better solve the matching problem of multi-dimensional resources, and the utilization rate of all kinds of resources reaches more than 90%.

Computing Power Network (CPN) overcome the performance limitations of computing power islands by integrating computing and network resources, dynamically scheduling business traffic to optimal nodes. However, effectively and collaboratively utilizing computing resources to reduce the delay of computing tasks has become a challenging issue in CPN due to the heterogeneity of resources and dynamic load. Existing works often treat workflow tasks as atomic tasks for offloading, disregarding subtask dependencies within a task. This approach leads to increased overall waiting time due to varying execution delays of each subtask. To address this problem, this paper proposes an optimization algorithm for workflow tasks based on slack quantity (CSA_WTO). The algorithm optimizes the arrival order of workflow task graphs before offloading, considering subtask dependencies and arranging them appropriately for subsequent offloading. This effectively reduces waiting delays for subtasks. Additionally, we utilize the Dependent Task Offloading algorithm (DTO) based on A3C to offload optimized workflow tasks, thereby improving execution efficiency in CPN. Simulation results demonstrate that compared with other algorithms, CSA_WTO significantly reduces task waiting delays by up to 85%, and DTO achieves a request acceptance rate of up to 96% while reducing the average completion time by 71%.

To solve the energy‐efficient virtual network embedding problem, this study proposes an embedding algorithm based on Hopfield neural network. An energy‐efficient virtual network embedding model was established. Wavelet diffusion was performed to take the structural feature value into consideration and provide a candidate set for virtual network embedding. In addition, the Hopfield network was used in the candidate set to solve the virtual network energy‐efficient embedding problem. The augmented Lagrangian multiplier method was used to transform the energy‐efficient virtual network embedding constraint problem into an unconstrained problem. The resulting unconstrained problem was used as the energy function of the Hopfield network, and the network weight was iteratively trained. The energy‐efficient virtual network embedding scheme was obtained when the energy function was balanced. To prove the effectiveness of the proposed algorithm, we designed two experimental environments, namely, a medium‐sized scenario and a small‐sized scenario. Simulation results show that the proposed algorithm achieved a superior performance and effectively decreased the energy consumption relative to the other methods in both scenarios. Furthermore, the proposed algorithm reduced the number of open nodes and open links leading to a reduction in the overall power consumption of the virtual network embedding process, while ensuring the average acceptance ratio and the average ratio of the revenue and cost.