Deep neural networks (DNNs) form the cornerstone of modern AI services, supporting a wide range of applications, including autonomous driving, chatbots, and recommendation systems. As models increase in size and complexity, DNN workloads such as training and inference tasks impose unprecedented demands on distributed computing resources, making accurate runtime prediction essential for optimizing development and resource allocation. Traditional methods rely on additive computational unit models, limiting their accuracy and generalizability. In contrast, graph-enhanced modeling improves performance but significantly increases data collection costs. Therefore, there is a critical need for a method that strikes a balance between accuracy, generalizability, and data collection costs. To address these challenges, we propose ScaleDL, a novel runtime prediction framework that combines nonlinear layer-wise modeling with graph neural network (GNN)-based cross-layer interaction mechanism, enabling accurate DNN runtime prediction and hierarchical generalizability across different network architectures. Additionally, we employ the D-optimal method to reduce data collection costs. Experiments on the workloads of five popular DNN models demonstrate that ScaleDL enhances runtime prediction accuracy and generalizability, achieving 6 times lower MRE and 5 times lower RMSE compared to baseline models.

Workload prediction in multi-tenant edge cloud platforms (MT-ECP) is crucial for efficient application deployment and resource provisioning. However, the heterogeneous application patterns, variable infrastructure performance, and frequent deployments in MT-ECP pose significant challenges for accurate prediction. Existing clustering-based methods often incur excessive costs due to maintaining multiple data clusters and models, while end-to-end time-series prediction methods struggle with dynamic environments. To address these challenges, we perform a comprehensive analysis on a large-scale workload dataset in real-world MT-ECP and propose DynEformer, an end to-end framework with global pooling and static context aware ness, offering a unified workload prediction scheme for dynamic MT-ECP. Meticulously designed global pooling and information merging mechanisms can effectively identify and utilize global application patterns to drive local workload predictions. The integration of static content-aware mechanisms enhances model robustness in real-world scenarios. We also extend DynEformer's capabilities to Long-term workload forecasting (LTLF) and Long-period service (LPS) tasks. Experiments on six real-world datasets demonstrate that DynEformer achieves state-of-the-art performance, with a 32% relative improvement on nine baselines and a 52% improvement in application switching and new entity scenarios. Additional experiments on long-term prediction and online learning further confirm its effectiveness for LTLF and LPS tasks.

With the rapid proliferation of streaming services, network load exhibits highly time-varying and bursty behavior, posing serious challenges for maintaining Quality of Service (QoS) in Crowdsourced Cloud-Edge Platforms (CCPs). While CCPs leverage Predict-then-Schedule architecture to improve QoS and profitability, accurate load forecasting remains challenging under traffic surges. Existing methods either minimize mean absolute error, resulting in underprovisioning and potential Service Level Agreement (SLA) violations during peak periods, or adopt conservative overprovisioning strategies, which mitigate SLA risks at the expense of increased resource expenditure. To address this dilemma, we propose HRS, a Hybrid Representation framework with Scheduling awareness that integrates numerical and image-based representations to better capture extreme load dynamics. We further introduce a Scheduling-Aware Loss (SAL) that captures the asymmetric impact of prediction errors, guiding predictions that better support scheduling decisions. Extensive experiments on four real-world datasets demonstrate that HRS consistently outperforms ten baselines and achieves state-of-the-art performance, reducing SLA violation rates by 63.1% and total profit loss by 32.3%. Our code is available at [29].

Efficient workload forecasting is pivotal for both service orchestration and request dispatching in quality of service (QoS)-oriented multi-tenant edge cloud platforms (MT-ECPs) with a native tiered architecture. However, the spatial-temporal heterogeneity and structural constraints of native tiered architecture present significant challenges for the forecasting in sophisticated MT-ECPs. To tackle these challenges, we propose SCOUT, which is a novel Self-supervised learning-enhanced Cloud-edge collabOrative Unified workload forecasTing framework. First, we design a cross-granularity collaborative mechanism that enables SCOUT to balance accuracy and efficiency in forecasting within the tiered architecture of MT-ECPs. Notably, we employ an auxiliary self-supervised learning method at the cloud that enhances workload pattern representations, making them reflective of both spatial and temporal heterogeneity. Extensive experiments on two real-world workload datasets show that SCOUT outperforms state-of-the-art methods for MT-ECP's workload forecasting, decreases time consumption and reduces communication costs.

Responding to the escalating interest in long-term forecasting within the industry, we introduce EasyTS, a comprehensive toolkit engineered to streamline data collection, analysis, and model creation procedures. EasyTS acts as a unified solution, driving progress in long-term time series forecasting. The platform provides effortless access to various time series datasets, including a newly open-sourced multi-scenario dataset in the electricity domain. Integrated visualization and analysis tools help unveil inherent data features and relationships. EasyTS facilitates a user-friendly model validation approach with versatile evaluation criteria. This toolkit allows researchers to compare their models proficiently against renowned benchmarks. With our ongoing commitment to expanding our dataset collection and enhancing toolkit functionalities, we aspire to contribute significantly to the time series forecasting domain. Code is available at this repository: https://github.com/EdgeBigBang/EasyTS.git.

As live streaming services skyrocket, Crowdsourced Cloud-edge service Platforms (CCPs) have surfaced as pivotal intermediaries catering to the mounting demand. Despite the role of stream scheduling to CCPs’ Quality of Service (QoS) and throughput, conventional optimization strategies struggle to enhancing CCPs’ revenue, primarily due to the intricate relationship between resource utilization and revenue. Additionally, the substantial scale of CCPs magnifies the difficulties of time-intensive scheduling. To tackle these challenges, we propose Seer, a proactive revenue-aware scheduling system for live streaming services in CCPs. The design of Seer is motivated by meticulous measurements of real-world CCPs environments, which allows us to achieve accurate revenue modeling and overcome three key obstacles that hinder the integration of prediction and optimal scheduling. Utilizing an innovative Preschedule-Execute-Re-schedule paradigm and flexible scheduling modes, Seer achieves efficient revenue-optimized scheduling in CCPs. Extensive evaluations demonstrate Seer’s superiority over competitors in terms of revenue, utilization, and anomaly penalty mitigation, boosting CCPs revenue by 147% and expediting scheduling 3.4× faster.

Measurements for the quality of end-to-end network services (QoS) are crucial to ensure stability, reliability, and user experience for distributed edge clouds. Measuring all QoS data brings significant costs. Existing QoS measurement methods attempt to use sparse measured QoS data to estimate unmeasured QoS data. But they suffer from limited estimation accuracy when facing QoS data with high sparsity or significant volatility. Moreover, they also consume high sampling and training costs during continuously online measurements. Our preliminary analysis reveals that end-to-end QoS is strongly temporal-spatial related. It inspires us to leverage partially measured QoS data to impute temporal-spatial-related unmeasured QoS data for reducing measurement costs. To predict unmeasured QoS data precisely with low computational costs, we propose a novel QoS Measurement framework based on Residual Graph Neural Network (QM-RGNN), which inputs QoS data as a graph and outputs the prediction of unmeasured QoS data. It consists of three core components: 1) an encoder-decoder model QM-GNN with GCN as the encoder and MLP as the decoder is devised for efficient QoS prediction, and a residual module is introduced in QM-GNN to tackle highly sparse and volatile QoS data; 2) a dynamic adaptive sample ratio is proposed to reduce the sampling costs; 3) an online learning pattern is designed to reduce continuous training costs. Experiments on two real-world industrial edge cloud datasets demonstrate the superiority of QM-RGNN in QoS measurement. It obtains at least a 37.5% reduction of relative RMSE between ground-truth and predicted QoS data with up to 90% training cost reduction and 22.7% sampling cost reduction.

The emergence of next-generation latency-critical applications places strict requirements on network latency and stability. Edge cloud, an instantiated paradigm for edge computing, is gaining more and more attention due to its benefits of low latency. In this work, we make an in-depth investigation into the network QoS, especially end-to-end latency, at both spatial and temporal dimensions on a nationwide edge computing platform. Through the measurements, we collect a multi-variable large-scale real-world dataset on latency. We then quantify how the spatial-temporal factors affect the end-to-end latency, and verify the predictability of end-to-end latency. The results reveal the limitation of centralized clouds and illustrate how could edge clouds provide low and stable latency. Our results also point out that existing edge clouds merely increase the density of servers and ignore spatial-temporal factors, so they still suffer from high latency and fluctuations. Based on a quantified latency impact factor, we have proposed several optimization strategies for edge cloud latency and validated their effectiveness. We also propose a robust prototype edge cloud model based on lessons we learn from the measurement and evaluate its performance in the production environment. Evaluation result shows that edge clouds achieve 84.1% latency reduction with 0.5 ms latency fluctuation and 73.3% QoS improvement compared with the centralized clouds.

The 5G networks have extensively promoted the growth of mobile users and novel applications, and with the skyrocketing user requests for a large amount of popular content, the consequent content delivery services (CDSs) have been bringing a heavy load to mobile service providers. As a key mission in intelligent networks management, understanding and predicting the distribution of CDSs benefits many tasks of modern network services such as resource provisioning and proactive content caching for content delivery networks. However, the revolutions in novel ubiquitous network architectures led by ultra-dense networks (UDNs) make the task extremely challenging. Specifically, conventional methods face the challenges of insufficient spatio precision, lacking generalizability, and complex multi-feature dependencies of user requests, making their effectiveness unreliable in CDSs prediction under 5G UDNs. In this article, we propose to adopt a series of encoding and sampling methods to model CDSs of known and unknown areas at a tailored fine-grained level. Moreover, we design a spatio-temporal-social multi-feature extraction framework for CDSs hotspots prediction, in which a novel edge-enhanced graph convolution block is proposed to encode dynamic CDSs networks based on the social relationships and the spatio features. Besides, we introduce the Long-Short Term Memory (LSTM) to further capture the temporal dependency. Extensive performance evaluations with real-world measurement data collected in two mobile content applications demonstrate the effectiveness of our proposed solution, which can improve the prediction area under the curve (AUC) by 40.5% compared to the state-of-the-art proposals at a spatio granularity of 76m, with up to 80% of the unknown areas.

The emergence of next-generation latency-critical applications places strict requirements on network latency and stability. Edge cloud, an instantiated paradigm for edge computing, is gaining more and more attention due to its benefits of low latency. In this work, we make an in-depth investigation into the network QoS, especially end-to-end latency, at both spatial and temporal dimensions on a nationwide edge computing platform. Through the measurements, we collect a multi-variable large-scale real-world dataset on latency. We then quantify how the spatial-temporal factors affect the end-to-end latency, and verified the predictability of end-to-end latency. The results reveal the limitation of centralized clouds and illustrate how could edge clouds provide low and stable latency. Our results also point out that existing edge clouds merely increase the density of servers and ignore spatial-temporal factors, so they still suffer from high latency and fluctuations. Based on the observations, we propose a robust prototype edge cloud model based on lessons we learn from the measurement and evaluate its performance in the production environment. The further evaluation result shows that edge clouds achieve 84.1% latency reduction with 0.5ms latency fluctuation and 73.3% QoS improvement compared with the centralized clouds.

Workload prediction in multi-tenant edge cloud platforms (MT-ECP) is vital for efficient application deployment and resource provisioning. However, the heterogeneous application patterns, variable infrastructure performance, and frequent deployments in MT-ECP pose significant challenges for accurate and efficient workload prediction. Clustering-based methods for dynamic MT-ECP modeling often incur excessive costs due to the need to maintain numerous data clusters and models, which leads to excessive costs. Existing end-to-end time series prediction methods are challenging to provide consistent prediction performance in dynamic MT-ECP. In this paper, we propose an end-to-end framework with global pooling and static content awareness, DynEformer, to provide a unified workload prediction scheme for dynamic MT-ECP. Meticulously designed global pooling and information merging mechanisms can effectively identify and utilize global application patterns to drive local workload predictions. The integration of static content-aware mechanisms enhances model robustness in real-world scenarios. Through experiments on five real-world datasets, DynEformer achieved state-of-the-art in the dynamic scene of MT-ECP and provided a unified end-to-end prediction scheme for MT-ECP.

In the 5 G era, data traffic has been growing rapidly. A small number of popular data files may dominate the network traffic and lead to heavy network congestion. Device-to-Device (D2D) communication can be used for caching and offloading significant data traffic. D2D social networks are instantiated paradigms of D2D communication. Existing studies maximize the performances of caching and offloading in D2D social networks by predicting potential content propagation paths. However, predicting such paths still faces many challenges, such as limitation of user spatial-temporal features, fragility of D2D social networks, and uncertainty of participants. As a solution, we first measure users' multi-dimensional features and content propagation paths to explore the distributions of D2D activities. Then we propose a D2D-LSTM model to predict complete content propagation paths hierarchically and design a prototype-user model for new participants. Experimental results demonstrate the state-of-the-art performances of D2D-LSTM. D2D-LSTM achieves at most 95% and at least 84.6% average precision in predicting terminal prototype-user class. Tree generation tests show that the generated trees have at most 64% and at least 17% similarity with ground-truth trees.

Bandwidth-intensive applications transmit large-scale video data in the network. It causes backhaul bottlenecks and affects user experience. Deploying edge cache on an access point (AP) is a popular method to bring content files closer to end-users, but it faces significant challenges, especially in efficiently predicting and satisfying different users’ future content requests with limited cache capacity. In this article, we propose an intelligent gateway assisted edge cache deployment strategy (GACD), which jointly considers traffic usage patterns in multiple APs and the impact of new content on the cache performance. In GACD, The cache content placement problem is formulated as a many-to-one bidirectional matching problem with a dynamic quota allocation, aiming to improve cache resource utilization and minimize the average delivery latency. To address this problem, we design a heterogeneous information networks based prediction algorithm to predict end-users’ potential preference of new content files. Then, we adapt the seasonal autoregressive integrated moving average model for traffic usage prediction, and propose a many-to-one matching algorithm to achieve dynamic matching quota adjustment and efficient cache content placement. We conduct extensive real-world trace-based experiments to validate the performance of GACD. Compared with six alternative cache strategies, GACD improves the hit rate by 23.9% on average, reduces the average content delivery delay by 19.02%, and increases the accuracy by 31.02% on average.

The arrival of 5G networks has extensively promoted the growth of content delivery services (CDSs). Understanding and predicting the spatio-temporal distribution of CDSs are beneficial to mobile users, Internet Content Providers and carriers. Conventional methods for predicting the spatio-temporal distribution of CDSs are mostly base-stations (BSs) centric, leading to weak generalization and spatio coarse-grained. To improve the spatio accuracy and generalization of modeling, we propose user-centric methods for CDSs spatio-temporal analysis. With geocoding and spatio-temporal graphs modeling algorithms, CDSs records collected from mobile devices are modeled as dynamic graphs with spatio-temporal attributes. Moreover, we propose a spatio-temporal-social multi-feature extraction framework for spatio fine-grained CDSs hot spots prediction. Specifically, an edge-enhanced graph convolutional block is designed to encode CDSs information based on the social relations and the spatio dependence features. Besides, we introduce the Long Short Term Memory (LSTM) to further capture the temporal dependence. Experiments on two real-world CDSs datasets verified the effectiveness of the proposed framework, and ablation studies are taken to evaluate the importance of each feature.