Amid recent advances for multivariate time series forecasting, self-supervised learning has emerged as a promising paradigm for deriving transferable knowledge from multi-domain data. Despite its effectiveness, existing approaches exhibit two critical limitations: (1) Underestimating the significance of multivariate dependencies in learning generalizable representations and (2) Failing to reconcile the complementary strengths of autoregressive and one-shot generative paradigms. In this work, we propose TimeCAP, a novel channel-aware pre-training framework that internalizes latent causal relationships among variables inherent in multi-domain data, and effectively transfers the acquired knowledge to downstream applications. Technically, we present a flexible channel-grouping learning approach, complemented by an adaptive meta-routing mechanism, enabling TimeCAP to parallel recognize intra-group local patterns while maintaining global coherence. Intra- and inter-group multivariate dependencies are captured through the self- and cross-attention with channel-aware mask, which strictly confine interactions among time-aligned, fine-grained multivariate tokens. To seamlessly unify two advanced generative paradigms, we propose a novel dynamic dual-head decoding and optimization strategy, empowering TimeCAP to leverage critical dependencies in the output series while avoiding cumulative errors over time. In the few-shot evaluation, TimeCAP achieves average MSE and MAE reductions of 11.8% and 6% over leading baselines, while also outperforming state-of-the-art models in full-shot and zero-shot settings by large margins.

Maximum utilisation of minimal amount of resources is pivotal for achieving a sustainable operation in large-scale Cloud Data Centres. Prediction driven resource provisioning in Cloud Data Centres is a potential approach to execute Cloud workloads in a sustianable way. Traditional prediction models often struggle to deliver accurate predictions under dynamic and heterogeneous cloud workloads, as capturing long-range dependencies and sudden workload spikes is often challenging in Cloud environments. In addition, recent time series models such as the Adversarial Error Correction Generative Adversarial Network (AEC-GAN) characterise shortcomings when applied to cloud workload datasets, particularly whilst managing volatility and learning irregular patterns. To address such challenges, this paper proposes a novel prediction model using Data Augment Aware Transformer Rectification-based Generative Adversarial Networks (TR-GAN), which incorporates a continuous and conditional learning Transformer block in the GAN's generator module to serve both as a data distribution moderator and as a data augmentation generator, ultimately to deliver accurate predictions. TR-GAN is the first GAN-based model tailored for long-term cloud workload forecasting that explicitly couples data augmentation with sequence rectification. Unlike discriminative forecasters, Its generative formulation allows it to model the intrinsic variability and uncertainty of cloud workloads,generate context-aware synthetic data to improve generalization under sparse or irregular patterns, and iteratively refine predictions through an adversarial learning process, thereby reducing error accumulation in long-horizon forecasts. The prediction performance of the proposed model is evaluated with two widely-used cloud workload datasets, namely the Google clusters and Alibaba traces. Experimental results demonstrate that the proposed TR-GAN model can deliver a prediction improvement of around 15% than notable state-of-the-art models, including Informer, Autoformer and AEC-GAN, for long forecasting horizons.

The abuse of community detection algorithms posed significant risks of privacy leakage. To protect personal privacy in complex networks, community detection attack (CDA) algorithms have been proposed, which modify a small number of connections to obscure the original community structure. However, most of the existing studies focus on designing effective attack strategies while the attack budget should be given by decision makers in advance. In this article, we transform CDA into a biobjective optimization problem, where the attack effectiveness and the attack budget are optimized simultaneously. To solve this problem, an effective multiobjective evolutionary algorithm (MOEA) named CDA-MOEA is proposed, which provides the decision maker with a holistic view for assessing attack strategies. Additionally, a budget-aware population repair operator based on betweenness and permanence is suggested to enhance the diversity and quality of the nondominated solutions in CDA-MOEA. Experimental evaluations are conducted by comparing CDA-MOEA with four state-of-the-art baseline methods against five community detection algorithms on eight real-world networks. The results indicate that CDA-MOEA significantly improves attack effectiveness at the same attack cost comparing to baseline methods, confirming its superiority and practical applicability.

Identifying influential spreaders in complex networks is a crucial problem. This topic has garnered significant interest in network science research, and it is of considerable significance in traffic accident prediction, infectious disease prevention, and targeted advertising. The goal of it is to select a set of seed nodes that maximize the spread of influence. Traditional approaches, such as k-core decomposition, identify seed nodes based on their connectivity. However, these methods often select highly overlapping nodes, thereby limiting their overall influence. Alternative methods leverage Neighbourhood Coreness centrality to mitigate this issue by considering the$k$-shell indices of a node's neighbours, but they still fail to account for highly connected peripheral nodes or the influence of selected nodes on their neighbours. To address these limitations, we propose an Improved Neighborhood Coreness-based Heuristic Algorithm for Influence Maximization in Complex Networks (INC-HAIM). It iteratively selects uncovered nodes with the highest NC centrality and updates the coverage status and the centrality of neighbouring nodes and edge nodes, effectively reducing the impact of edge contributions. Experimental evaluations under the Independent Cascade (IC) model across multiple datasets demonstrate that as network size and propagation probability increase, INCHAIM consistently achieves superior influence spread compared to existing heuristic and centrality-based approaches.

Time series forecasting is a pivotal task across diverse fields such as finance, energy, and meteorology, providing critical insights for informed decision-making and resource management. The growing complexity and scale of these tasks demand high-performance computing capabilities, which are crucial for efficiently processing vast amounts of temporal data and achieving real-time forecasting. Despite considerable progress, existing deep learning models face challenges in capturing complex temporal dependencies, lack explicit mechanisms to enhance temporal learning, and are encumbered by the computational overhead and limited adaptability of layer normalization in Transformer architectures. To address these limitations, we propose a novel GPDT model that integrates an auto-regressive pretraining framework, promoting temporal consistency and enabling the effective capture of both shortand long-term temporal dependencies. This pretraining strategy establishes a robust temporal inductive bias, which is further refined through task-specific fine-tuning to optimize forecasting performance. Additionally, the static layer normalization in the standard Transformer encoder is replaced with an adaptive dynamic tanh mechanism, which not only reduces computational costs but also improves the model's adaptability to evolving temporal patterns. Moreover, GPDT further leverages instance normalization, channel independence, and patch embedding to enhance both efficiency and accuracy. Comprehensive evaluation across a range of forecasting scenarios validates the model's superior performance and strong generalization capability.

Time series forecasting plays a crucial role in cloud computing resource management. However, existing models often struggle to balance prediction accuracy with computational efficiency when handling complex cloud resource data. This study, for the first time, applies the recently proposed TiDE (Time-series Dense Encoder) model to the Azure cloud dataset and introduces a novel forecasting framework based on classical time series decomposition techniques. The proposed architecture decomposes the original time series into seasonal, trend, and residual components, each of which is modeled specifically using dedicated TiDE models. By leveraging our sequence-decoupling strategy, we achieve substantial gains in forecasting accuracy while markedly reducing computational overhead. Experimental results show that the TiDE-enhanced framework outperforms state-of-the-art models in both accuracy and robustness. In particular, on high-dimensional, multi-channel Azure cloud workload prediction tasks, our approach demonstrates exceptional generalization and strong practical deployment potential.

The rapid development of the Internet-of-Things (IoT) has transformed human interaction with the world. The Social Internet-of-Things (SIoT) integrates social, emotional, and behavioral aspects into traditional IoT, creating an intelligent network that connects various smart devices. By combining Edge Computing with Artificial Intelligence (AI), data can be processed and analyzed directly on edge devices, improving processing efficiency. However, limited edge resources hinder local AI training, requiring cloud-based training of high-precision models, which are then deployed on edge devices for inference. In time series forecasting, Multilayer Perceptrons (MLPs) are widely used for their computational efficiency but often overlook correlations between time series. Some models adopt channel mixing mechanisms to improve modeling capability but increase computational complexity. To address this problem, we propose the Core Fusion Time Series Dense Encoder (CFTD) model, which incorporates a Core Extract-Distribute (COED) module for efficient channel fusion. Extensive experiments on real-world datasets demonstrate that this novel CFTD model achieves excellent predictive performance compared to the state-of-the-art models.

Cloud Data Centers are typically equipped with various types and performance levels of GPUs, making it crucial to effectively leverage these heterogeneous resources when deploying deep learning tasks. However, differences in GPU performance pose complex resource management challenges. Accurate workload forecasting can help address these challenges. Many existing prediction models employ Multi-Layer Perceptrons (MLPs) due to their simplicity, computational efficiency, and general applicability. Nevertheless, most MLP-based methods tend to prioritize low-frequency features, neglecting high-frequency features that are essential for capturing fine-grained patterns in resource utilization data. Our analysis reveals that this bias primarily stems from the dominance of low-frequency features in the dataset, causing the model's attention to disproportionately focus on them. To tackle this issue, we propose a frequency domain patch-based MLP model called FP-MLP, which partitions the frequency series into small patches, thereby balancing the representation of high and low-frequency features across different bands. This approach enables the model to fully capture hidden features in high-frequency data, thus improving predictive accuracy. Extensive experiments demonstrate that the FP-MLP model consistently outperforms various state-of-the-art baseline models with stable performance. For instance, on the Alibaba dataset, compared to the best baseline model, the FP-MLP model reduces the Mean Squared Error (MSE) by 8% and the Mean Absolute Error (MAE) by 17%; meanwhile, it also achieves competitive results on the Google.

The rapid growth of Cloud Computing, Artificial Intelligence, and Big Data cloud workloads, intensifying resource contention, operational costs, and carbon emissions due to underutilized data centers. Accurate workload prediction is thus for proactive resource management and improved utilization of Cloud data centers. However, traditional statistical and machine learning methods struggle with the dynamic, high-dimensional, and heterogeneous nature of cloud workloads. This paper proposes STiFF, a novel prediction framework that, for the first time in workload forecasting, transforms time series data into graph-based image representations to capture spatiotemporal dependencies. STiFF integrates three key modules: (1) a Two-Dimensional Moving Average Decomposition (2D-MAD) for trend smoothing, (2) a Global-Local Feature Extraction (GLE) module combining CNNs and Transformers for hierarchical pattern learning, and (3) a Multi-modal Feature Fusion (MFF) module leveraging attention mechanisms and partial prior knowledge. Extensive experiments on four real-world datasets demonstrate that STiFF achieves an average error reduction of 62.14%, with a maximum of 90.84%, and outperforms state-of-the-art methods in 84.375% of the evaluated cases.

The rapid growth of Internet of Vehicle (IoV) devices and Artificial Intelligence (AI) applications has accelerated the adoption of Cloud and Edge Computing. The advent of sixth-generation mobile communication technology (6G) further facilitates the deployment of Cloud-Edge collaborative computing in large-scale Intelligent Transportation Systems (ITS). Effective ITS must efficiently handle both latency-sensitive tasks (e.g., obstacle detection, traffic signal recognition) and computationally intensive tasks (e.g., path optimization, traffic flow prediction). However, existing Cloud-Edge collaborative frameworks struggle to accurately classify diverse workloads and provide efficient low-latency processing, leading to energy inefficiencies and task failures. To address these challenges, this paper introduces a Deep Learning-based Cloud-Edge Collaboration Framework (CECF) designed to optimize energy conservation in Cloud and Edge environments. CECF employs a DNN-based classifier to categorize workloads for processing in the Cloud or Edge. The classified tasks are managed by a dedicated Cloud scheduler (DSGA) and an Edge scheduler (EA-DFPSO), respectively. To enhance scheduling efficiency for highly variable Cloud tasks, DSGA incorporates a novel self-adaptive mutation algorithm and a random point fixed distance crossover method. Extensive evaluations using real-world workload traces demonstrate that CECF achieves up to a 8.5% improvement in system reliability and reduces energy consumption by 35.88% compared to baseline approaches.

SUMMARY The growing number of services processed and stored in the cloud has led to difficulties in managing and discovering the required services efficiently. Multilevel index model is an efficient method to manage and retrieve services in service repositories. When adding a new service to a multilevel index model, a key needs to be selected for the service, but existing key selection methods cannot adapt to the situation that hot services change over time. To address this problem, this article proposes an adaptive key selection method to improve the efficiency of service retrieval. However, the service addition operation of the adaptive key selection method is inefficient in the multilevel index model. For this reason, this article improves the multilevel index model by introducing local equivalence partition. This indexing model improves the service addition efficiency of the adaptive key selection method without affecting the service retrieval efficiency. It is experimentally demonstrated that the retrieval and addition efficiencies of the adaptive key selection method are close to the ideal state optimum under the multilevel index model with local equivalence partitioning.

Abstract With the development of edge computing and artificial intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume. The edge intelligence (EI) has led to the emergence of edge devices in various application domains. The EI can provide efficient services to delay‐sensitive applications, where the edge devices are deployed as edge nodes to host the majority of execution, which can effectively manage services and improve service discovery efficiency. The multilevel index model is a well‐known model used for indexing service, such a model is being introduced and optimized in the edge environments to efficiently services discovery while managing large volumes of data. However, effectively updating the multilevel index model by adding new services timely and precisely in the dynamic edge computing environments is still a challenge. Addressing this issue, this article proposes a designated key selection method to improve the efficiency of adding services in the multilevel index models. Our experimental results show that in the partial index and the full index of multilevel index model, our method reduces the service addition time by around 84% and 76%, respectively when compared with the original key selection method and by around 78% and 66%, respectively when compared with the random selection method. Our proposed method significantly improves the service addition efficiency in the multilevel index model, when compared with existing state‐of‐the‐art key selection methods, without compromising the service retrieval stability to any notable level.

Cloud datacenters are turning out to be massive energy consumers and environment polluters, which necessitate the need for promoting sustainable computing approaches for achieving environment-friendly datacentre execution. Direct causes of excess energy consumption of the datacentre include running servers at low level of workloads and over-provisioning of server resources to the arriving workloads during execution. To this end, predicting the future workload demands and their respective behaviors at the datacenters are being the focus of recent researches in the context of sustainable datacenters. But prediction analytics of cloud workloads suffer various limitations imposed by the dynamic and unclear characteristics of Cloud workloads. This paper proposes a novel forecasting model named K-means based Rand Variable Learning Rate Backpropagation Neural Network (K-RVLBPNN) for predicting the future workload arrival trend, by exploiting the latency sensitivity characteristics of Cloud workloads, based on a combination of improved K-means clustering algorithm and Backpropagation Neural Network (BPNN) algorithm. Experiments conducted on real-world Cloud datasets shows that the proposed model shows better prediction accuracy, outperforming the traditional Hidden Markov Model, Naïve Bayes Classifier, and our earlier RVLBPNN model, respectively.

Real-time data processing applications demand dynamic resource provisioning and efficient service discovery, which is particularly challenging in resource-constraint edge computing environments. Network embedding techniques can potentially aid effective resource discovery services in edge environments, by achieving a proximity-preserving representation of the network resources. Most of the existing techniques of network embedding fail to capture accurate proximity information among the network nodes and further lack exploiting information beyond the second-order neighbourhood. This paper leverages artificial intelligence for network representation and proposes a deep learning model, named inductive content augmented network embedding (ICANE), which integrates the network structure and resource content attributes into a feature vector. Secondly, a hierarchical aggregation approach is introduced to explicitly learn the network representation through sampling the nodes and aggregating features from the higher-order neighbourhood. A semantic proximity search model is then designed to generate the top-k ranking of relevant nodes using the learned network representation. Experiments conducted on real-world datasets demonstrate the superiority of the proposed model over the existing popular methods in terms of resource discovery and the query resolving performance.