Future wireless networks, such as 6G, are envisioned to deliver ultra-reliable, high-quality services with ultra-low latency and dynamic connectivity across heterogeneous environments, driving the adoption of edge–cloud collaborative architectures. Within this paradigm, container-based microservices, with their lightweight, modular, and portable characteristics, offer an effective foundation for scalable and adaptive service provisioning in heterogeneous wireless networks. The layered architecture of microservices facilitates efficient resource management through layer scheduling and caching. However, dynamic service requests and diverse container layers pose major challenges for layer-aware service provisioning in future wireless environments. These includetime-exceeded offline service provisioning, tangled microservice orchestration, andlayer cache redundancy. To address these challenges, we propose Tri-Ring, an asynchronous online provisioning framework for future wireless networks, empowered by large AI models (LAMs). The framework optimizes request dispatching, orchestration, and layer updates across three timescales. At the small timescale, we formulate request dispatching as a linear programming (LP) subproblem. At the medium timescale, the estimator-assessor algorithm manages microservice orchestration, where a diffusion-enhanced prediction model serves as the estimator to predict layer caching strategies. Moreover, submodular optimization serves as the assessor to determine deployment and scheduling. At the large timescale, we introduce the age of layer (AoL) to guide the pruning of infrequently accessed cached layers to reduce storage overhead. Comprehensive evaluations on real-world datasets demonstrates that Tri-Ring outperforms existing baselines, increasing utility by 44.78%, reducing microservice startup time by 78.64%, and optimizing storage resources by 36.38%.

To meet the demands of high-capacity and low-delay services, Fifth Generation (5G) Base Stations (BSs) are typically deployed in ultra-dense configurations, especially in urban areas. While this densification enhances coverage and service quality, it also leads to substantially increased energy consumption. However, the dense deployment pattern makes BS workloads more responsive to the spatiotemporal variations in user behavior, offering opportunities for energy-saving strategies that dynamically adjust BS operation states. In this context, we propose a Delay-aware and Energy-efficient Integrated Optimization System (DEIS) based on Deep Reinforcement Learning (DRL), which jointly optimizes energy consumption and network delay while maintaining user satisfaction. DEIS leverages a real-world dataset collected from operational 5G BSs provided by partner network operators, containing both BS deployment data and high-volume user request logs. Extensive simulations demonstrate that DEIS can achieve a 41% reduction in energy consumption while ensuring reliable delay performance.

Computing Power Networks (CPNs) represent an innovative, collaborative architecture that integrates resources via the communication network, optimizing resource allocation to support service demands. Due to the increased need for services powered by artificial intelligence across various domains, CPNs are increasingly required to allocate users efficiently to appropriate servers to meet the low-latency needs of service computing. However, challenges such as users' dynamic mobility, weak communication paths, and high-dimensional solution spaces persist in optimizing user allocation in CPNs. In this context, we propose a diffusion-driven optimization approach for mobility-aware user allocation. To tackle the challenge of users' dynamic mobility, we adopt a user location prediction approach incorporating the users' movement patterns to forecast future movement, calledCAMPE. To tackle the challenge of weak communication paths, we establish the new transmission path by reconfigurable intelligent surface and enhance the quality of the communication link by adjusting the phase configurations. Moreover, faced with the challenge of high-dimensional solution spaces associated with phase adjustment and user allocation decisions, we devise an action-generation strategy based on diffusion models namedDiffUser. This approach motivates the generation of optimal solutions even in complex and dynamic environments. Finally, we conduct extensive simulations in user location prediction and system latency optimization. Compared with other solutions, the superiority of our approach has been demonstrated.

As the rapid development of artificial intelligence (AI) and large language models (LLM), how to deploy related applications onto computing nodes has become a hot topic, and containerized service provides an excellent approach for this. The most time-consuming step of this approach is image extraction, the procedure of decompressing all layers of image package downloaded from remote image registry. Therefore, achieving fast image extracting is crucial for the efficient deployment of AI services. In this paper, we introduce a collaborative orchestration and extraction strategy, CORES. Firstly, we eliminate the dependencies among image layers, which impede unordered extraction of image layers. Based on this, we model the image extraction as a mixed integer linear programming (MILP) problem, aiming to minimize total extraction time. Then we use improved Benders decomposition to iteratively obtain a near-optimal solution with lower time complexity. Extensive experiments conducted on the real system validate the superior performance of our strategy. Compared with our closest baseline LOPO, CORES reduces the average image extracting time by 19.60%, significantly enhancing the efficiency of AI service deployment.

The rapid development of Artificial Intelligence Generated Content (AIGC) technology has led to a strong demand for elastic computing resources. The crowdsourced edge cloud system builds a flexible resource pool by integrating heterogeneous idle servers and even personal devices to meet the dynamic computing requirements of AIGC services. The system relies on the serverless architecture to realize the dynamic scheduling of resources, which needs to trade off resource benefits and energy consumption costs to improve the overall social welfare, resource efficiency, and environmental sustainability. However, challenges such as unfair resource pricing, dynamic resource availability, and the complexity of strategy optimization remain unresolved for green and efficient resource management. In this paper, we propose a resource management framework named ReFluid. We introduce a game-theoretical pricing model to ensure fair pricing, a fluid model-based analysis for promoting a more sustainable management of computing resources, and a diffusion-based optimization mechanism to enhance model stability and adaptability. The evaluation shows that ReFluid significantly improves average social welfare and reduces energy consumption.

With the emergence of massive data and advances in artificial intelligence (AI), large-scale transformer based model have demonstrated superior performance. As its critical applications, performing inference near users, e.g., distributed inference on edges, can significantly reduce response latency. Thus, many studies have investigated collaborative inference across edges. However, collaborative inference across edges has brought about significant resource constraints and heterogeneity. These characteristics have posed unprecedented challenges, including the inaccurate parallelism mechanism, and low-time efficient inference decision. In this paper, we propose a chunking adaptive mixed parallelism mechanism, namely ChAMP. To tackle the problem of inaccurate parallelism, we introduce a transformer chunking adaptive mechanism, to adapt the input sequence chunking and the workload distribution, and use a hybrid parallelism approach. To tackle the challenges of low-time efficient inference decision, we learn an adaptive inference adjustment, where a hierarchical reinforcement learning method is designed to perform local chunking adjustments and real-time optimization. Finally, we evaluate the performance of ChAMP in heterogeneous edge computing environments. We compare ChAMP with two state-of-the-art parallel approaches, i.e., achieved a time efficiency increase of approximately 23.8% compared to M-LM and 18.0% compared to SP.

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.

With the rise of AI-Generated Content (AIGC) services, deployments within edge-cloud environments are becoming increasingly prevalent. Containerization offers resource isolation, lightweight deployment, and portability, making it a suitable technology for AIGC services. However, deploying AIGC services often requires large container images, leading to high deployment latency and bandwidth consumption. Based on real-world trace analysis showing the long-tail effect, where a few popular images account for the majority of requests, there is strong potential for optimizing caching mechanisms. This pattern can result in frequent cache misses and increased bandwidth consumption, especially under heavy load. In this paper, we propose a ValueOptimized Distributed Caching Mechanism (VODCM), which dynamically optimizes caching policies through a value-driven framework combined with deep reinforcement learning (DRL). VODCM prioritizes high-value images based on access frequency, layer size, and network latency, significantly improving cache hit rates and reducing network overhead. Preliminary evaluations show that VODCM enhances cache efficiency and reduces network and resource demands, offering an effective solution for AIGC image management in edge-cloud environments.

Pre-trained Transformer-based large models have revolutionized personal virtual assistants, but their deployment in cloud environments faces challenges related to data privacy and response latency. Deploying large models closer to the data and users has become a key research area to address these issues. However, applying these models directly often entails significant difficulties, such as model mismatching, resource constraints, and energy inefficiency. Automated design of customized models is necessary, but it faces three key challenges, namely, the high cost of centralized model customization, imbalanced performance from user heterogeneity, and suboptimal performance from data heterogeneity. In this paper, we propose ACME, an adaptive customization approach of Transformer-based large models via distributed systems. To avoid the low cost-efficiency of centralized methods, ACME employs a bidirectional single-loop distributed system to progressively achieve fine-grained collaborative model customization. In order to better match user heterogeneity, it begins by customizing the backbone generation and identifying the Pareto Front under model size constraints to ensure optimal resource utilization. Subsequently, it performs header generation and refines the model using data distribution-based personalized architecture aggregation to match data heterogeneity. Evaluation on different datasets shows that ACME achieves cost-efficient models under model size constraints. Compared to centralized systems, data transmission volume is reduced to 6%. Additionally, the average accuracy improves by 10% compared to the baseline, with the trade-off metrics increasing by nearly 30%.

High-precision semantic segmentation is an important research topic in the communities of computer vision and intelligent transportation. The existing unsupervised domain adaptation methods based on image translation often lead to artifacts and structural distortions. To overcome this problem, a novel adaptive semantic segmentation method of traffic scenes via frequency domain analysis is proposed. Firstly, we leverage the frequency domain space to decouple style and semantic features. The Fast Fourier Transform is applied to achieve structural-preserving style alignment. Subsequently, a content enhancement module is proposed based on the Wavelet transform, which utilizes the original source images to correct and enhance high-frequency structural and semantic details. Furthermore, a convolutional enhancement attention module is proposed, which utilizes depthwise separable convolution to capture more local details. The experimental results based on the GTA5→Cityscapes and SYNTHIA→Cityscapes tasks have respectively attained state-of-the-art mIoU of 76.4 and 67.7, convincingly demonstrating the effectiveness of the methods.

In the Fifth Generation (5G) era, different operators keep their Base Stations (BS) active in the same area to ensure user service coverage. However, this high level of redundant coverage leads to significant energy waste, especially given the high power consumption of 5G BSs. To address this issue, this paper proposes the Collaborative Operator Partnership based Energy-efficient framework (COPE), a 5G network optimization approach based on multi-operator collaboration. COPE encourages operator cooperation through revenue incentives, combines time series analysis to predict user distribution and service demand, and uses deep reinforcement learning to guide BS leasing, facilitating cross-operator resource collaboration. Extensive experimental results demonstrate that COPE reduces total BS energy consumption by approximately 19% and optimizes costs by about 9% in multi-operator scenarios.

Artificial Intelligence Generated Content (AIGC) services based on text-to-image generation tasks have driven change in the AI industry in recent years. Diffusion models are widely used in AIGC services for generating high-quality images from complex prompts. However, the process of generating diffusion models requires a large number of autoregressive denoising steps, posing significant challenges related to service latency and privacy issues, especially in resource-constrained edge devices. To further improve the quality of service (QoS) of edge AIGC services, we design a multi-edge cooperative caching mechanism based on the idea of reusing early intermediate results of similar prompts to reduce denoising steps. First, a collaborative filtering algorithm based on prompt similarity is developed to analyze user preferences. The designed multi-agent reinforcement learning-based cache management (MARLCM) algorithm utilizes the preference data as input and determines the caches that need to be replaced in the cache space. Secondly, we propose an adaptive edge server cooperation strategy that instructs servers to build efficient cache pools based on server similarity and workload differences. The experiment conducted on a high-resolution generation task with multiple diffusion cache frameworks shows that the proposed method reduces task latency by 23.1 %, and achieves up to 1.57 times higher cache hit rate compared to existing methods.

Crowdsourced edge-cloud clusters utilize idle third-party resources to provide cost-effective, scalable environments. This decentralized model reduces capital expenditures and carbon footprints but introduces hardware instability, as servers may unpredictably join or leave, affecting service availability. While integrating serverless computing enables automated management to lower operational costs, the dynamic nature of server availability still significantly impacts service quality. In this paper, we present RESCUER, a QoS-aware service rescheduling framework for serverless crowdsourced edge-cloud clusters. Partnering with a real-world provider, we collected data from over 10,000 edge servers over 400+ days, enabling a detailed analysis of server availability patterns. Based on these insights, we propose a predictive algorithm that forecasts the future online duration of each node, assigning them labels based on their predicted availability. Additionally, we introduce a rescheduling algorithm that combines these labels with node resources, latency constraints, and other factors to select the most suitable node for deploying containers. Evaluations on the real-world trace show that RESCUER significantly improves service availability and system efficiency compared to existing methods.

The rapid evolution of Industrial Cyber-Physical Systems (ICPS) with cloud-fog automation calls for the deployment of Deep Neural Networks (DNNs) on edge devices to enable intelligent and autonomous decision-making. However, the resource constraints, heterogeneity, and dynamic nature of edge devices pose limitations to the efficient deployment of DNNs. Federated Learning-based Neural Architecture Search (FL-NAS) has been proposed to address these limitations, but achieving an effective balance between the generalized global model and personalized local models remains a non-trivial task due tosuboptimal aggregation of homogeneous neural blocks, knowledge waste of heterogeneous neural blocks, and high communication and energy overhead. In this paper, we proposeF²NAS, an energy-friendly federated neural architecture search framework tailored for ICPS. The fine-grained aggregation strategy adapts weights for each device during aggregation, enhancing the global and personalized local models. The bidirectional knowledge transfer mechanism leverages heterogeneous neural blocks, promoting knowledge sharing among local and global models. The adaptive communication strategy optimizes interactions between edge devices and the cloud server based on model performance, reducing energy costs while maintaining effective model collaboration. Extensive experiments demonstrate thatF²NASoutperforms baselines by up to 30.31% in accuracy on edge devices, 38.75% on the cloud server, and achieves a 65.2% reduction in energy consumption. When applied to the surface defect detection task in ICPS,F²NASsurpasses other baselines by up to 13.38% and 302.46% for edge devices and cloud servers, respectively, and reduces energy consumption by 44.8%.

In edge computing, energy-limited distributed edge clients present challenges such as heterogeneity, high energy consumption, and security risks. Traditional blockchain-based federated learning (BFL) struggles to address all three of these challenges simultaneously. This article proposes a Graph-Partitioning Multi-Granularity Federated Learning method on a consortium blockchain, namely GP-MGFL. To reduce the overall communication overhead, we adopt a balanced graph partitioning algorithm while introducing observer and consensus nodes. This method groups clients to minimize high-cost communications and focuses on the guidance effect within each group, thereby ensuring effective guidance with reduced overhead. To fully leverage heterogeneity, we introduce a cross-granularity guidance mechanism. This mechanism involves fine-granularity models guiding coarse-granularity models to enhance the accuracy of the latter models. We also introduce a credit model to adjust the contribution of models to the global model dynamically and to dynamically select leaders responsible for model aggregation. Finally, we implement a prototype system on real physical hardware and compare it with several baselines. Experimental results show that the accuracy of the GP-MGFL algorithm is 5.6% higher than that of ordinary BFL algorithms. In addition, compared to other grouping methods, such as greedy grouping, the accuracy of the proposed method improves by about 1.5%. In scenarios with malicious clients, the maximum accuracy improvement reaches 11.1%. We also analyze and summarize the impact of grouping and the number of clients on the model, as well as the impact of this method on the inherent security of the blockchain itself.

While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.

Real-time video detection is essential for many mobile visual applications, which brings the heavy computational burden of deep neural networks. Mobile edge computing offers a promising solution by deploying computational resources near mobile devices. However, achieving efficient video detection on mobile devices requires addressing challenges such as different performance requirements, diverse computing and network conditions, and system dynamics. We propose a realtime video detection framework in mobile edge computing, where multiple video streams from mobile devices are processed while balancing key performance metrics with consideration of grouping. A joint optimization problem of task scheduling, model selection, and resource provisioning is formulated for the system, where decisions are made on two timescales. To this end, we propose a window controller to unify decision-making at the time-slot level. We design an online scheduling algorithm based on multi-agent deep reinforcement learning to enable adaptive and distributed scheduling, while a masking-enhanced attention mechanism enables efficient explicit information exchange between mobile devices. Experimental evaluations across different numbers of mobile devices demonstrate that, in terms of average reward, the proposed algorithm outperforms local processing by 14.600%, fixed offloading by 10.007%, and four learning-based scheduling baselines by an average of 2.267%.

The new real-time interactive services, such as virtual and augmented reality, demand significantly higher network bandwidth and quality, which the traditional centralized cloud struggles to meet. In addition, centralized optimization management becomes inefficient as the scale of the scene continues to expand. In response, edge cloud systems have emerged, but distributed geographic locations, burstable billing business models, and large numbers of servers in large-scale scenarios pose new challenges for resource management. In this article, we proposeGeoCC, a novel strategy to save bandwidth overhead in burstable billing edge cloud systems.GeoCCaddresses challenges through a dual approach. First, a geography-aware graph construction and partitioning algorithm is used to organize server resources, and a large number of servers are reasonably divided into multiple server pools for parallel processing. Second, it introduces an enhanced burstable billing optimization mechanism that considers contextual factors and adaptive bandwidth capacity. Experiments based on real data from an edge cloud operator demonstrate the effectiveness ofGeoCC. Compared with the baseline,GeoCCcan effectively reduce bandwidth peaks, decreasing bandwidth costs by an average of 28.30% and up to 81.83% at the 95th percentile billing.

The escalating demands for Artificial Intelligence-generated content (AIGC) services greatly require computing resources. The edge-cloud market offers an effective solution for AIGC services by integrating, managing, and trading distributed computing resources. Within this novel service market, participants contribute idle resources to support AIGC services to earn income, creating a more flexible market environment. Meanwhile, the generation quality and computing resource requirements of AIGC services are related to input prompts. Therefore, this relationship introduces new challenges, such asthe information uncertainty in input prompts, the inability to model resource continuity, and high-dimensional complexity for optimization.In this paper, we propose a resource fluid equilibrium management strategy for supporting AIGC services within edge-cloud market, termedFluE. To address the challenge of information uncertainty in user prompts, we measure the content value of AIGC prompts by information entropy and introduce a redundancy reduction approach to focus on meaningful information in prompts. To tackle the challenge of the inability to model the continuity provision of computing resources, we utilize the fluid model to ensure seamless resource provision and facilitate a more balanced management of computing resources. To address the challenge of high-dimensional complexity of strategy optimization, we develop a diffusion-based algorithm namedReDiffto reconstruct the target strategy distribution and generate precise and effective optimization decisions. We evaluate our proposed scheme under a dynamic resource provisioning environment. Based on the DiffusionDB dataset, the publicly available real trace of AIGC service prompt, ourReDiffalgorithm achieves up to 69.8% and 77.4% improvements in average social welfare compared to LySAC and CD-PPO, respectively.

Federated learning (FL), an advanced variant of distributed machine learning, enables clients to collaboratively train a model without sharing raw data, thereby enhancing privacy, security, and reducing communication overhead. However, in edge computing scenarios, there is an increasing trend towards diversity, heterogeneity, and complexity in clients’ data and models. The fundamental challenges, such as non-independent and identically distributed (non-IID) data and multi-granularity data accompanied by model heterogeneity, have become more evident and pose challenges to collaborative training among clients. In this paper, we refine the FL framework and propose the Multi-granularity Weighted Federated Learning (MGW-FL), emphasizing efficient collaborative training among clients with varied data granularities and diverse model scales across distinct data distributions. We introduce a distance-based FL mechanism designed for homogeneous clients, providing personalized models to mitigate the negative effects that non-IID data might have on model aggregation. Simultaneously, we propose an attention-weighted FL mechanism enhanced by a prior attention mechanism, facilitating knowledge transfer across clients with heterogeneous data granularities and model scales. Furthermore, we provide theoretical analyses of the convergence properties of the proposed MGW-FL method for both convex and non-convex models. Experimental results on five benchmark datasets demonstrate that, compared to baseline methods, MGW-FL significantly improves accuracy by almost 150% and convergence efficiency by nearly 20% on both IID and non-IID data.

The presence of Artificial Intelligence Generated Content (AIGC) has garnered widespread interest. AIGC enables content creation by analyzing big data, leveraging the capabilities of extensive AI models, and substantial AI computing. Computing power networks (CPNs) represent an excellent approach for offering pervasive AI computing resources to AIGC. However, these characteristics have posed unprecedented challenges to the CPNs helped AIGC, including the uncertainty of prompts’ information value, the inability to model the continuity of computing resources, and the incapacity to represent complex multi-dimensional spaces. In this paper, we propose a computing resources equilibrium strategy based on the fluid model for AIGC helped by CPNs, namely FluE. This mechanism obtains information entropy by constructing an AIGC prompt tree to measure the information value of AIGC prompts. In addition, we model the continuity of computing resources by the fluid model. A fluid-stopping equilibrium strategy is formulated to obtain the average fluid level of computing resources based on the Laplace-Stieltjes transform. To solve the equilibrium strategy, we develop a diffusion-based algorithm for FluE to adjust the fluid policy dynamically to maximize resource rewards. Finally, the evaluations demonstrate improvements in average social welfare.

With the rapid increase in user scale and the explosive rise of emerging applications, the contradiction between heavy load pressure and excellent network performance is becoming increasingly prominent, and task processing is gradually shifting towards the edge of the network. However, the resources of edge networks are limited, making it difficult to meet the huge computing and storage needs, and managing and allocating edge nodes is also a huge challenge. The Kubernetes (K8S) framework for deploying and orchestrating containerized applications provides a solution for this. How to improve the adaptability of K8S in edge networks, meet the demand of services for heterogeneous resources, and train decision models with better performance using limited datasets has become an urgent problem to be solved. Based on the above issues, we propose a distributed service migration architecture for multi-user access, and design a service migration algorithm based on imitation learning to achieve resource combination optimization and reduce the impact of insufficient data on model training. Design agent models based on diffusion models to accelerate model convergence and avoid the increase in training costs caused by constantly updating agent models. Our results show that the efficiency of the expert model is 92.0%, and the learning process of the agent model can converge within 100 training cycles with an accuracy of 97.89%. The service processing delay, throughput rate, and model convergence are all significantly better than those of classical algorithms.

Recent advances in the diffusion model mark a significant leap in AI-generated image technology while extending its application to the Internet of Things (IoT). However, deploying these models on resource-constrained edge devices presents considerable challenges, primarily due to their high computational energy demands and stringent quality requirements. In response to these challenges, we introduce a collaborative inference system tailored for green edge networks. First, we propose a multi-exit U-ViT model that achieves the balance between inference quality and processing speed by allowing adaptive selection of exit points during diffusion for efficient processing. Next, we develop a novel generative AI-assisted reinforcement learning algorithm that controls the exit selections and offloading decisions of the device to achieve maximum global gain. Furthermore, we design a novel policy network incorporating an attention-based state-embedded policy network to enhance the algorithm’s ability to perceive and make decisions about the state of the environment. Experimental results demonstrate that our system achieves energy-efficient inference while ensuring the quality of the generated content.

With the continuous development of technologies such as the Internet of Things (IoT), scheduling issues in edge-cloud systems are becoming a research focus. Deep reinforcement learning (DRL) has become an effective way to address scheduling issues in edge-cloud systems due to its ability to interact with the environment and engage in adaptive learning to solve complex decision-making problems. However, due to the increasing scale of edge-cloud systems, traditional DRL still faces challenges in scheduling, such as slow convergence and high computational requirements. To address these challenges, we propose a diffusion model-based deep reinforcement learning algorithm called DMaiS, which utilizes the diffusion model as the policy network in the advantage actor-critic (A2C) to expedite policy learning. Additionally, we develop a distributed service orchestration approach utilizing multi-agent advantage actor-critic (MAA2C) to effectively and flexibly manage extensive and intricate cloud service resources. The experimental results using real-world data demonstrate that compared to the baseline algorithms, DMaiS achieves a higher system throughput rate and a lower scheduling latency when managing scheduling for the edge-cloud system. It also exhibits a faster convergence speed compared to traditional DRL algorithms.

With the rapid development of Internet of Things (loT) device performance, edge-cloud systems are generating vast volumes of complex data. Meanwhile, the distributed and multi-layer structure of edge-cloud systems pose significant challenges to scheduling decision-making and convergence of the algorithm. In this paper, from a vertical and horizontal perspective of edge-cloud systems, we propose a deep reinforcement learning (DRL) algorithm called CrossLearning. We apply a curiosity-driven multi-agent learning method horizontally to accelerate the convergence speed of the algorithm. We introduce an inter-layer decision refinement mechanism vertically to address the challenge of inaccurate decision-making. We also refine the service types and levels to efficiently match the various application needs of users in the big data era. Finally, we implement a prototype system on a network hardware system and conduct experiments using real datasets. The evaluation shows that, in comparison to baseline methods, CrossLearning demonstrates significant im-provements in terms of time efficiency and load balance, with a notable enhancement in algorithm convergence speed.

The rapid growth of edge computing calls for fine-tuned deep neural network (DNN) deployment that emphasizes energy-efficient implementation, due to the resource constraints of edge devices. Traditional Federated Learning-based Neural Architecture Search (FL-based NAS) has been instrumental in the complexities of this deployment, particularly in addressing constraints posed by device heterogeneity, limited resources, and privacy preservation. However, it is hindered by issues such as suboptimal aggregation of homogeneous neural blocks, significant knowledge waste in disregarding heterogeneous neural blocks, and excessive communication energy consumption. This paper introduces F2NAS in green edge computing, a novel energy-efficient approach that addresses these limitations by ensuring flexible and energy-efficient model design and training for edge devices. Firstly, F2NAS introduces an innovative aggregation strategy that enhances the integration of homogeneous neural blocks by using inter-block distances to optimize weight allocation. Further, it employs a unique parameter extraction technique that recaptures valuable insights from previously overlooked heterogeneous neural blocks. Finally, F2NAS meticulously calibrates communication energy consumption by balancing loss function and model interaction, setting and refining an upper limit for model communication. Experimental results reveal F2NAS enhances model accuracy by 2.8% to 4.7%, simultaneously reducing the energy consumption by nearly 50% through optimizing the communication cost.

The collaboration between clouds and edges unlocks the full potential of edge-cloud systems. Edge-cloud platform has brought about significant decentralization, heterogeneity, complexity, and instability. These characteristics have posed unprecedented challenges to the optimal scheduling problem in the edge-cloud system, including inaccurate decision-making and slow convergence. In this paper, we propose a curiosity-driven collaborative request scheduling scheme in edge-cloud systems, namely Cur-CoEdge. To tackle the challenge of inaccurate decision-making, we introduce a time-scale and decision-level interaction mechanism. This mechanism employs a small-large-time-scale scheduling learning framework, facilitating mutual learning between different decision levels. To address the challenge of slow convergence, we investigate the underlying reasons, such as the sparse reward-setting in reinforcement learning. In response, we develop a curiosity-driven collaborative exploration approach that fosters intrinsic curiosity in the cloud and simultaneously motivates dispatchers to explore the environment both individually and collectively. The effectiveness of this collaborative exploration is also supported by theoretical proof of convergence. Finally, we implement a prototype system on a network hardware system along with two real-world traces. Evaluations demonstrate significant improvements, with up to a 26% increase in time efficiency, a 40% rise in system throughput, and a 71% enhancement in convergence speed.

Giant models have transformed vision-language tasks by mastering consistent representations across text and images, highlighting the critical role of deploying such models in the expanding domain of edge scenarios, such as monitoring and segmentation. However, the deployment is challenged by device heterogeneity, limited computational resources, and privacy concerns. Federated learning (FL) presents itself as a viable solution, facilitating decentralized training on devices and preserving data confidentiality. Despite its potential, FL faces obstacles with fine-tuning efficiency, including complex granularity data, static personalized prompt generation, and high energy consumption. This paper introduces a cross-granular and personalized prompt-based green federated tuning (CP2GFed) approach, aiming to address these issues by enabling giant model deployment on devices. CP2GFed introduces a cross-granularity knowledge transfer mechanism to leverage semantic relationships across varying data granularities. Meanwhile, it pioneers in generating dynamic personalized prompts based on inter-device affinities to improve model performance. In addition, CP2GFed meticulously optimizes energy consumption, including model local learning and interaction, by setting local computing steps and selecting communication devices. Empirical results indicate that CP2GFed elevates accuracy by up to 6.64% on diverse datasets and reduces energy consumption by nearly 60% per unit of accuracy, achieving a superior tradeoff between model performance and energy consumption compared to baselines.

Web 3.0 pursues the establishment of decentralized ecosystems through blockchain technologies, driving digital transformation in commerce and governance. With consensus algorithms and smart contracts grounded in cryptographic technologies, Web 3.0 enables secure and transparent digital services, such as digital identity, asset management, decentralized autonomous organizations (DAOs), and decentralized finance (DeFi), fostering integration between digital and physical economies. As quantum devices rapidly advance, Web 3.0 is being developed in parallel with the deployment of quantum cloud computing and quantum Internet. In this regard, quantum computing first disrupts the original cryptographic systems that protect data security while reshaping modern cryptography with enhanced quantum computing and communication capabilities. This article provides a comprehensive overview of blockchain-based Web 3.0, examining its quantum and postquantum advancements from two key perspectives. On the one hand, postquantum migration methods and quantum-resistant signatures offer robust solutions to safeguard blockchain against quantum threats. On the other hand, quantum and postquantum encryption and verification algorithms boost blockchain performance, creating a decentralized, secure, and value-driven system. Additionally, we outline potential applications of quantum blockchain and offer guidance for implementation within the Web 3.0 ecosystem. Finally, we discuss future directions for developing a provably secure and decentralized digital ecosystem.

The Internet of Things (IoT) finds applications across diverse fields but grapples with privacy and security concerns. Blockchain offers a remedy by instilling trust among IoT devices. The development of blockchain in IoT encounters hurdles due to its resource-intensive computation processing, notably in PoW-based systems. Cloud and edge computing can facilitate the application of blockchain in this environment, and the IoT users who want to mine in blockchain need to pay the computation resource rent to the Cloud Computing Service Provider (CCSP) for offloading the mining workload. In this scenario, these IoT miners can form groups to trade with CCSP to maximize their utility. In this paper, a mixed model of the Stackelberg game and coalition formation game is embraced to address the grouping and pricing issues between IoT miners and CCSP. In particular, the Stackelberg game is utilized to handle the pricing problem, and the coalition formation game is employed to tackle the best group partition problem. Moreover, a coalition formation algorithm is proposed to obtain a nearoptimal solution with very low complexity. Simulation results show that our proposed algorithm can obtain a performance that is very near to the exhaustive search method, outperforms other existing schemes, and requires only a small computation overhead.

As the primary driver of intelligent mobile applications, deep neural networks (DNNs) have gradually deployed to millions of mobile devices, producing massive latency-sensitive and computation-intensive tasks daily. Mobile edge computing facilitates the deployment of computing resources at the edge, which enables fine-grained offloading of DNN inference tasks from mobile devices to edge nodes. However, most existing studies have not systematically considered three crucial performance aspects: scheduling multiple streams of DNN inference tasks, leveraging multi-exit models to hasten task processing, and partitioning inference models for partial offloading. To this end, this paper proposes an adaptive inference framework in mobile edge computing, which can dynamically select the exit point and partition point for multiple inference task streams. We design a dynamic programming algorithm to obtain an efficient solution under the ideal condition that task arrival information is known. Further, we design a learning-based algorithm for online scheduling, whose training efficiency is improved based on historical experience initialization and priority experience replay. Experimental results show that compared with the Greedy algorithm, the online algorithm improves the performance on two environmental parameters by an average of 5.9% and 32%, respectively.

Deep neural networks are the cornerstone of many mobile intelligent systems, and their inference processes bring about computation-intensive tasks. Device-edge cooperative inference in mobile edge computing provides a fine-grained processing method to migrate the burden of inference computation. However, the geographical dispersion of resources and the mobility pattern of devices pose scheduling issues to be considered. In this paper, we propose a task scheduling framework for such device-edge systems to improve the pipeline time of model inference. First, we consider the resource provisioning strategy with a pre-fetching service migration setting in the environment of multiple mobile devices and edge nodes. Then, we leverage game theory to analyze the property of the decision-making process and propose an offline algorithm under complete information. Next, we propose an algorithm based on proximal policy optimization to enable mobile devices to make decisions in a distributed online manner. Further, we adopt a memory mechanism into the online algorithm to improve the decision-makers' understanding of the system environment. Experiments demonstrate the effectiveness of the two algorithms. The average pipeline time of the proposed online algorithm is only 61.44% of that of local processing, which is 1.196 times that of the proposed offline algorithm.

The development of the mobile Metaverse has garnered increasing attention in the next-generation Internet, fueled by the rapid advancements of mobile Internet, communication, and computing technologies. With the resource limitations faced by mobile Metaverse users (MUs), the mobile Metaverse market is flourishing. This market enables MUs to access high-quality immersive experiences by trading resources with Metaverse service providers (MSPs) across geographically distributed resource pools. However, the mobile Metaverse market still faces several challenges, includingthe hierarchical mobile Metaverse service structure, temporal dependencies, and heterogeneous incentive mechanisms. To address these problems, this paper proposes a dual-level resources trading approach for mobile Metaverse based on blockchain. This approach employs a dual-level structure consisting of resource provisioning and heterogeneous auction mechanisms. Specifically, we formulate the resource provisioning as a temporal-dependent average delay minimization problem at the low level. To solve this low-level problem, we introduce a novel algorithm calledLyDif, which leverages Lyapunov optimization techniques and diffusion models. At the high level, we propose a price-guided double dutch auction (PG-DDA) mechanism to match heterogeneous resources and determine pricing strategies. The PG-DDA smart contract is deployed on a consortium blockchain platform, facilitating resource trading management and transaction monitoring. Based on a real trace of edge-cloud service requests, our experimental results demonstrate the effectiveness of our proposed scheme in achieving optimal latency and social welfare.

Edge computing has evolved to enable mobile applications to run in an efficient and cost-effective manner at explosive-growing edge nodes. Under this paradigm, a new business resource trading market has emerged to provide edge-cloud services, offering a convenient way for mobile users to obtain resources from distributed computing power providers (CPPs). Blockchain, as a promising technology, provides a reliable platform for multi-party resource transactions (TXs), enabling secure and reliable computing services. Notably, the distributed CPPs not only offer mobile services but also act as blockchain nodes to maintain the stability of TXs. In this case, there exist certain bottlenecks in the blockchain-enabled edge-cloud resource market, such as limited scalability, inefficient resource allocation, and large system cost. In this paper, assisted by the permissioned blockchain, we study the fundamental problem of resource allocation by minimizing the system cost to handle mobile services and blockchain TXs in parallel. We first partition the Practical Byzantine Fault Tolerant (PBFT) consensus by hierarchical sharding to improve the scalability and ensure the security of the blockchain system. Next, based on the optimal sharding strategies, we formulate the parallel resource allocation as a multi-scale Lyapunov optimization problem, and develop a dual-alternation actor-critic with an attention mechanism (DA3C) algorithm to solve it. We evaluate the performance of theParamartusing trace-driven experiments. Simulation results demonstrate the superiority of our proposed framework as compared with the benchmark algorithms.

Edge computing has emerged as a powerful paradigm for efficient scheduling at the network edge to fulfill users' requirements for low latency. Edge servers' and clouds' ability to interact allows them to leverage edge servers' limited computing and storage resources collectively to handle all requests collaboratively. This has unlocked the potential of the edge-cloud system. However, its sophistication (e.g., heterogeneous resources, intertwined dependencies, etc.) also raised unforeseen challenges in request dispatch and service orchestration phases within the scheduling process, includingcomplex hierarchy,limited cooperationandunfocused information. Traditional resource optimization methods for edge-cloud systems cannot address these intricate situations properly, raising concerns over system efficiency, stability, and costs. This paper proposes learning-based methods to accommodate time-varying requests and dynamic service prevalence. Specifically, we employ the multi-agent advantage actor-critic (MAA2C) and the graph convolutional networks-based MAA2C (GCN-MAA2C) in two phases, respectively, to enhance individual intelligence and facilitate optimal dispatch and orchestration decisions. Inspired by the regulations in human society, we proposeSocialEdge, a socialized learning-based scheduling framework for the edge-cloud system. To leverage the hierarchical correlation, we develop an inter-layer socialized refining mechanism. The inference results from one layer guide the training process of the next layer, enabling the abstraction of optimization-critical knowledge. Moreover, we apply intra-layer socialized cooperating, where federated averaging with MAA2C is implemented to ensure the cooperation of individuals over private data for achieving optimal global solutions. Furthermore, we propose a socialized resonance mechanism across the layers to extract high-value information and induce resonance toward the system objective, aiming to improve the efficiency of scheduling. Experimental evaluations on a proof-of-concept testbed and two real traces demonstrate thatSocialEdgereduces scheduling cost by 11.2% while enhancing time efficiency by 77.4%, and system throughput by 17.9%, compared to baseline methods.

The presence of Metaverse has elicited escalating attention in the next-generation Internet, followed by a large number of computationally intensive tasks, such as augmented reality, virtual reality, artificial intelligence-generated content (AIGC) applications, etc. With the popularity of mobile communication technology, mobile metaverse is becoming increasingly widespread. The resources required for these applications are rapidly growing in parallel with increasing demands from mobile Metaverse users (MUs), putting pressure on Metaverse service providers (MSPs) with limited resources, especially in mobile computing scenarios. Inspired by the burgeoning communication and computing technologies, the mobile Metaverse market between mobile MUs and MSPs is developing vigorously. However, there still remain numerous challenges in this market, including hierarchical mobile Metaverse structure, temporal dependencies, as well as heterogeneous incentive. In this paper, we propose a bi-alternating resource provisioning and heterogeneous auction approach for mobile Metaverse, named Bi-Meta. At the high level, resource provisioning is formulated as a Lyapunov problem minimizing average delay, solved by a novel bi-level based generative adversarial network, i.e., BiGAN. At the low level, a price- guided double dutch auction (PG-DDA) mechanism is presented for heterogeneous resource matching, with the designed PG- DDA smart contract. Based on the realistic edge-cloud company's traces, the experimental results verify that our proposed scheme achieves optimal latency and social welfare.

Federated Learning (FL) has become a common method for edge devices. Due to the limited energy capacity of edge devices, and the vulnerability of FL to malicious attacks from edge devices, vanilla FL still faces several challenges in edge computing, including energy consumption, model heterogeneity, and malicious behavior. To address these challenges, we propose a multi-granularity grouping-based federated learning (MG2FL), which groups and aggregates edge devices with low communication energy consumption and latency to reduce communication costs. Additionally, we introduce a multi-granularity guidance mechanism and a credit model to enhance model accuracy while ensuring security. Experimental results show that compared to the traditional FL algorithms, MG2FL achieves a 5.6% increase in accuracy, with the highest accuracy improvement reaching 11.1% in the presence of malicious edge devices.

Nowadays, real-time interactive content services have been the most dazzling sector of next-generation Internet. The high-quality perceptions of virtual scenes have given rise to the strict requirements of high bandwidth and low latency, where the edge-cloud system promises several benefits. However, there still remain prominent challenges, when taking the economical efficiency into consideration, including location-heterogeneity, context-directability, and capacity-exploitation. In this paper, we propose a location-context-capacity aware bandwidth cost economizing strategy in the edge-cloud system, i.e., LoCoCa. LoCoCa adopts server pools partition mechanism, then achieving the optimal burstable billing in each pool. Here, a location-aware graph construction and partition algorithm is designed to solve the server pools partition problem. Then an improved burstable billing optimization mechanism, with a context index and an adaptive bandwidth capacity, is also proposed to economize bandwidth costs. Finally, the realistic edge-cloud company's trace-based experimental results verify LoCoCa reduces bandwidth costs by 81.83 %, compared with the baselines.

With the popularization of visual machine learning, intelligent video analytics can automatically analyze and extract information from video streams, yet it brings heavy computing burdens. Edge computing can improve the processing experience by bringing computing resources near users. On top of this, various processing methods and settings have different resource requirements and output different user experiences. How to dynamically select the video processing configuration according to system states becomes a critical problem that remains to be addressed. In this paper, we propose an edge-assisted video analytic framework based on adaptive sampling and detection-based tracking. We design four functional modules to realize a cooperative computing processing flow. We consider two performance metrics, recognition accuracy and processing time to estimate the experience of real-time video analytics. Further, we design an online configuration method based on Double Deep Q-Network, which can adaptively select analytic configurations under the condition of system dynamics. Experimental results based on a real dataset demonstrate the superior performance of the proposed framework on reward, mean Intersection over Union (IoU), and processing time.

Computing Power Network (CPN) is an evolution of multi-access edge computing. Since the skyrocketing proliferation of CPN s, energy consumption aggravates explosively. However, majority of energy is wasted due to the incomplete analysis of tasks and resources, such as coarse-grained tasks consideration, coarse-grained resources integration, and unfocused complex information. In this paper, we propose a broad attention based fine-grained task offloading approach in green CPNs, i.e., Bat-FG. Specifically, for fine-grained tasks, we establish directed acyclic graphs (DAGs) subtasks offloading problem for green CPNs under the dependency and service constraints. For finegrained resources, decentralized resources are integrated into resource pools. Bridging the gap between fine-grained tasks and resource pools, we design a novel broad attention meta-reinforcement learning approach, i.e., Bat-MRL to focus on the main information for reducing the tasks' latency and energy consumption. Finally, extensive simulations show that Bat-FG significantly reduces 25.6 % task latency and 72.9 % energy consumption.

Deep neural networks are deemed to be the cornerstone of a series of mobile intelligent systems, and their inference processes bring about a mass of computation-intensive tasks. To migrate the burden of inference computation from resource-constrained mobile devices, device-edge cooperative inference in mobile edge computing provides a fine-grained processing method. However, the geographical dispersion of resources and the mobility pattern of devices pose technical issues in the scheduling of co-inference systems, which have not been fully considered. In this paper, we propose a learning-based scheduling framework for such device-edge systems to improve the pipeline time of model inference. First, we consider a resource provisioning strategy based on the number of devices and a pre-fetching service migration setting in the environment of multiple mobile devices and edge nodes. Next, we propose an algorithm based on proximal policy optimization for each device to make the decision independently. Further, we adopt long short-term memory in the algorithm to capture the temporal characteristics of the system state. Experiments using a real-world network and computing trace demonstrate that the proposed algorithm can efficiently sense the mobile system to make decisions at various system scales and two mobility scenes. The average pipeline time of the proposed algorithm is only 67.63% of that of local processing, which is 97.50% of that of the omniscient algorithm.

The ability for cloud data centres and edge data centres to collaborate unleashes the potential of the edge-cloud system. However, its sophistication causes unexpected issues in request scheduling, such as Insufficient intelligence, complicated hierarchy and limited cooperation. Traditional resource optimization methods for the edge-cloud system struggle to accommodate such intricate situations. In this paper, inspired by the behaviors and regulations in human society, we propose a socialized learning-based scheduling approach for the edge-cloud system, namely SocialEdge. In order to adapt to time-varying requests and dynamic service prevalence, we propose a learning-based approach, multi-agent advantage actor-critic (MAA2C) and graph convolutional networks-based MAA2C for two phases, respectively, which can improve individual intelligence to achieve optimal dispatch and orchestration decisions. Then, to make use of hierarchy correlation, we develop the socialized refining inter the layers, where inference results from one layer guide the training process of the other layer so that optimization-critical knowledge can be abstracted. Besides, we apply socialized cooperation to each layer, where federated averaging with MAA2C is implemented to ensure cooperation over private data for achieving optimal global solutions. Experimental evaluations on a proof-of-concept testbed along with two real traces demonstrate that baselines have 105% more delay than SocialEdge while being 76.6% less time efficiency and 21.6% less throughput.

Driven by the burgeoning growth of the Internet of Everything and the substantial breakthroughs in deep learning (DL) algorithms, a booming of artificial intelligence (AI) applications keep emerging. Meanwhile, the advance in existing computing paradigms, i.e., cloud computing and edge computing, provide assorted computing solutions to satisfy the increasingly high requirements for ubiquitous AI services. Nevertheless, there are some non-trivial issues in the computing frameworks, including the underutilization of computing power, the self-interest of computing-power trading mechanism, and the inefficiency of AI services management. To tackle the above issues, we propose a computing-power trading framework based on blockchain, also named AI-Bazaar. In AI-Bazaar, the AI consumers play multiple roles and feel free to contribute the computing power rented from the computing-power provider (CPP) for blockchain mining and AI services. Accordingly, we formulate the computing trading problem as a Stackelberg game. Based on the win or learn fast principle (WoLF), we design a profit-balanced multi-agent reinforcement learning (PB-MARL) algorithm to search the AI-Bazaar equilibrium, while finding the balanced profits for AI consumers and CPP. Numerical simulations are carried out to demonstrate the satisfactory performance and effectiveness of the proposed framework.

In a public blockchain system applying Proof of Work (PoW), the participants need to compete with their computing resources for reward, which is challenging for resource-limited devices. Mobile blockchain is proposed to facilitate the application of blockchain for mobile service, in which the lightweight devices can participate mining by renting resources from the Cloud Computing Service Provider (CCSP), but CCSP usually does not have the information about the demand preference of users. In this article, a contract model is adopted to address the cloud computing resource allocation and pricing problem in the mobile blockchain. In particular, an adverse selection contract solution is proposed to overcome the information asymmetry problem, and resource pooling is introduced to improve the stability of users’ rewards. Simulation results show that the information asymmetry problem is well overcome by adverse selection contract so that CCSP can obtain more utility than linear pricing contracts. Furthermore, the resource pooling could effectively improve the users’ and CCSP's utilities. When the size of the mining pool is large enough, it can achieve an improvement effect of more than 10 times. The effect of pool size and user type distribution on CCSP's utility is also studied.

Industrial Internet of Things (IIoT) and fifth generation (5G) network have fueled the development of Industry 4.0 by providing an unparalleled connectivity and intelligence to ensure timely (or real time) and optimal decision-making. Under this umbrella, the edge intelligence is ready to propel another ripple in the industrial growth by ensuring the next generation of connectivity and performance. With the recent proliferation of blockchain, edge intelligence enters a new era, where each edge trains the local learning model, then interconnecting the whole learning models in a distributed blockchain manner, known as blockchain-assisted federated learning. However, it is quiet challenging task to provide secure edge intelligence in 5G-enabled IIoT environment alongside ensuring latency and throughput. In this article, we propose a proof-of-learning consensus protocol that considers the reputation opinion for edge blockchain to ensure secure and trustworthy edge intelligence in IIoT. This protocol fetches each edge’s reputation opinion by executing a smart contract, and partly adopts the winner’s learning model according to its reputation opinion. By quantitative performance analysis and simulation experiments, the proposed scheme demonstrates the superior performance in contrast to the traditional counterparts.

With the increasing demand for resource scheduling efficiency in Industrial Internet of Things (IIoT), parallel reinforcement learning (PRL) based distributed edge-cloud collaborative resource scheduling scheme has attracted enormous attention. However, the computing and communication capacities, the security degree of massive distributed edge computing servers are different. It is difficult to make a large number of edge servers carry out security and efficiency PRL based edge-cloud collaboration resource scheduling scheme. Thus, in this paper, a large-scale distributed edge-cloud collaborative resource scheduling method based on picture delegated proof of state and suspicious practical byzantine fault tolerance (pDPoSt+sPBFT) consensus algorithm is proposed. To be specific, we first propose a collaborative edge-cloud industrial network architecture to support massive industrial intelligence tasks, then a distributed PRL based resource allocation scheme is utilized. Secondly, in order to improve the efficiency and security of distributed PRL training, we propose a server filtering strategy based on pDPoSt algorithm. Finally, a sPBFT algorithm is proposed to further realize security parameter aggregation of distributed PRL. Experimental results show that the proposed method has good efficiency and security performance compared with the traditional distributed edge-cloud collaborative resource scheduling algorithm. The proposed approach has great potential in complex IIoT scenarios.

As the footing stone of artificial intelligence (AI), ubiquitous computing resource is beginning to receive interest. With this trend, a new form of edge-cloud service market dedicated to collecting, trading, and scheduling computing resources is rising. The computing participants in the service market, as providers and demanders of computing resources, are becoming more diversified and open. As such, the intriguing economic phenomenon and the circulation mechanism have emerged. These bring inherent challenges, such as a volatile market, the ossification of pricing, isolation, and inefficiency. In this article, we propose a novel space-time-request trading framework for the edge-cloud service market, namelyCompCube. To ensure stability,CompCubeadopts the dual-circulation futures-spot trading method, including space-time dynamic pricing in the macro-cycle, request intention conversion, and resource matching in the micro-cycle. Among this, an incomplete information game model is designed to determine the long-term trading pricing in the macro-cycle. Then, to tackle the indicator isolation problem due to the inconsistency between the user's requests and the computing-power provider's (CPP’s) resources, we focus on minimizing the rental cost of computing resources while satisfying diverse service level agreements (SLA) of users. To address this problem, a spatiotemporal scale Lyapunov optimization and an alternating actor-critic algorithm, A2SC, are developed. Besides, in the micro-cycle, a discriminatory double auction helps to determine the computing resource matching results efficiently and impersonally. We evaluate theCompCubeof the A2SC algorithm with realistic datasets. Compared to other baselines, i.e., DYRECEIVE, Price Preferred, and Random, A2SC reduces the average rental cost by 30.45%, 5.74%, and 17.57%, respectively. Furthermore,CompCubecan improve SLA satisfaction, as well as promote resource efficiency and social welfare compared with the traditional methods.

Nowadays, numerous primary technologies, like ultra-dense networks (UDNs) and Base Stations (BSs) sleeping state, are developed in fifth-generation (5G) networks. Due to the UDNs, the number of BSs in 5G networks is proliferating, along with the energy consumption. Therefore, it is necessary to cut down the energy attrition in 5G networks under the assurance of delay. Till now, some researchers have proved that the association of users and the sleeping states of BSs have a significant effect on energy consumption and latency in 5G networks. However, the traditional solutions associate users and select states nonadaptively without the dual consideration of energy-saving and delay. In view of this, we propose a dual-adaptive delay-aware and energy-saving system (DADEs) in 5G networks. To further optimize the energy and delay of 5G BSs, the model is split into two tandem problems: user association and BS state selection. Meanwhile, a tandem deep reinforcement learning (T-DRL) algorithm is presented to make decisions in these problems for optimizing and balancing performance between delay and energy adaptively. Additionally, the real datasets of 5G users and BSs are used and trained in this paper. Finally, simulation results show that the DADEs saves more than 50% of energy with an adaptive and satisfying latency.

As a promising framework for distributed learning in mobile edge computing scenarios, federated learning (FL) allows multiple mobile devices to train a model collaboratively without transferring raw data and exposing user privacy. However, vanilla FL schemes are still facing to problems in edge computing, where the diversity of tasks and devices causes the non-IID and multi-granularity data with model heterogeneity. It becomes a pressing challenge to jointly training edge devices accompanied by these problems, while vanilla FL only discusses them separately. To this end, we consider tailoring FL to adapt to mobile edge environments, which focus on solving the problems of collaborative training of edge devices with multi-granularity heterogeneous models under different data distributions. In particular, we proposed a distance-based FL for the same type of edge devices that provides personalized models to avoid the negative impact of non-IID data on model aggregation. Further, we design a bi-directional guidance method with a prior attention mechanism, which can transfer knowledge among edge devices with multi-granulairty and multi-scale models. The experimental results show that our proposed mechanisms significantly improve training performance compared to other baselines on IID and non-IID data. Furthermore, the bi-directional guidance significantly improves convergence efficiency and accuracy performance for finer and coarser granularity edge devices, respectively.

With the advancement of the user application service demands, the IoT system tends to offload the tasks to the edge server for execution. Most of the current studies on edge computation offloading ignore the dependencies between components of the application. The few pieces of research on edge computing offloading which focus on the topology of application are primarily applied in single-user scenarios. Unlike previous work, our work mainly solves dependent task offloading with edge computing in multiuser scenarios, which is more in line with reality. In this article, the dependent task offloading problem is modeled as a Markov decision process (MDP) first. Then, we propose an actor–critic mechanism with two embedding layers for directed acyclic graphs (DAGs)-based multiple dependent tasks computation offloading, namely, ACED, by jointly considering the topology of the application and the channel interference between several users. Finally, the results of simulations also show the priorities of the proposed ACED algorithm.

Advances in communications and networking technologies are driving the computing paradigm toward the end-edge-cloud collaborative architecture to leverage ubiquitous data and resources. Opposite to centralized intelligence, Hierarchical Federated Learning (HFL) relieves overwhelmed communication overhead and enjoys the advantages of high bandwidth as well as abundant computing resources while retaining privacy-preserving benefits of Federated Learning (FL). It is difficult to balance system overhead and model performance in the HFL framework, while it could be solved by introducing an incentive mechanism. Although the incentive mechanism can alleviate the above anxiety by compensating relevant participants, some limitations (multi-dimensional properties, incomplete information and unreliable participants) will significantly degrade the performance and efficiency of the designed mechanism. To address the challenges caused by the above limitations, we propose InFEDge, a blockchain-based incentive mechanism in the HFL. The InFEDge considers 1) multi-dimensional individual properties to model system participants and proves the uniqueness of Nash equilibrium with the closed-form solution. Meanwhile, 2) we transform the problem under incomplete information into a contract game where we obtain the optimal solution. Moreover, 3) we also leverage the blockchain to provide economic incentives, prevent unreliable participants’ disturbance and further ensure data privacy by implementing the mechanism in the smart contract to offer a credible, faster, and transparent resource trading system. Experimental evaluations on a proof-of-concept testbed along with real traces demonstrate the superiority of our mechanism. Further, our method solves a real-world user allocation problem for future communications and networking.

Recently, the term ‘Internet of Things’ (IoT) has garnered great attention. As a trusted, dependable, and decentralized approach, blockchain has already been used in IoT. However, the existing blockchain has a number of drawbacks that prevent it from being used as a generic platform for IoT. The nodes in IoT are heavily resource-limited, especially computing and networking resources. Unfortunately, they are necessary for the blockchain to solve complicated puzzles and propagate blocks. In this paper, we propose agent mining and cloud mining approaches to solve the above problem in the blockchain-enabled IoT. To be specific, miners act as mining agents for nodes in IoT, offload mining tasks to cloud computing servers, and use networking resources dynamically. Furthermore, in order to enhance the performance, the access selection of users, computing resources allocation, and networking resources allocation are formulated as a joint optimization problem. We then propose a dueling deep reinforcement learning approach to address this problem. Numerical results justify the effectiveness of our proposed scheme.

Energy Internet (EI) is developing and booming rapidly with the increase of distributed energy resources, which is beneficial to address the severe condition of industrial energy. However, there are inevitable credit crises and utility optimization challenges in EI that need to be settled. In this article, we propose a blockchain-assisted software defined energy Internet (BSDEI), where a distributed energy market smart contract is designed to ensure transactions executed reliably and participants’ accounts dealt accurately. In order to jointly optimize the utilities of operators, retailers, and industrial prosumers in BSDEI, we formulate the whole trading process as a three-stage Stackelberg game, with the proof of existence and uniqueness for the Stackelberg equilibrium. Then, we design a hierarchical distributed policy gradient algorithm to solve the Stackelberg game under incomplete information. We implement a blockchain-based industrial energy trading system using a middleware platform. The smart contract is deployed on the consortium blockchain, providing website interfaces for participants to operate. Furthermore, we conduct experiments for analyzing economic benefits. Our system prototype demonstrates the feasibility of BSDEI and the algorithm exceeds about 18% in total mean reward than comparing algorithms.

In microgrid, peer-to-peer (P2P) electricity trading has quickly ascended to the spotlight and gained enormous popularity. However, there are inevitable credit problems and system security problems. Besides, the current model in the electricity trading system cannot balance the utilities of multiple trading entities. In this paper, we propose a blockchain-based distributed P2P electricity trading system. We define elecoins as currency in circulation within our trading system. In order to jointly optimize the utilities of both parties in the elecoins trading, we formulate the elecoins purchasing problem as a hierarchical Stackelberg game. Then, we design a distributed multi-agent utility-balanced reinforcement learning (DMA-UBRL) algorithm to search the Nash equilibrium. Finally, we factually build a blockchain system with a blockchain explorer and deploy an electricity trading smart contract (ETSC) on Ethereum, with a website interface for operating. The numerical results and the implemented realistic system show the advantages of our work.

As a compelling collaborative machine learning framework in the big data era, federated learning allows multiple participants to jointly train a model without revealing their private data. To further leverage the ubiquitous resources in end-edge-cloud systems, hierarchical federated learning (HFL) focuses on the layered feature to relieve the excessive communication overhead and the risk of data leakage. For end devices are often considered as self-interested and reluctant to join in model training, encouraging them to participate becomes an emerging and challenging issue, which deeply impacts training performance and has not been well considered yet. This paper proposes an incentive mechanism for HFL in end-edge-cloud systems, which motivates end devices to contribute data for model training. The hierarchical training process in end-edge-cloud systems is modeled as a multi-layer Stackelberg game where sub-games are interconnected through the utility functions. We derive the Nash equilibrium strategies and closed-form solutions to guide players. Due to fully grasping the inner interest relationship among players, the proposed mechanism could exchange the low costs for the high model performance. Simulations demonstrate the effectiveness of the proposed mechanism and reveal stakeholder's dependencies on the allocation of data resources.

With the rapid development of the Internet of Things (IoT), more and more smart devices are connected to the Internet, implementing Deep Neural Network (DNN) models on edges for collaborative inference via device-edge synergy has become a feasible method for improving application performance in many scenarios. However, when faced with the task stream scenario with latency guarantee such as video surveillance and industrial production line, we need adaptive edge intelligence to make adjustments in real-time according to the changes of the task stream. There are many adaptive edge intelligence technologies in the existing works, such as early-exit mechanism and model selection, but they don’t take the requirements of the task stream scenario into consideration. In this paper, we propose a device-edge collaborative inference system based on the early-exit mechanism to solve the problem of adaptive edge intelligence in the task stream scenario. Then, we design an offline dynamic programming (DP) algorithm and an online deep reinforcement learning (DRL) algorithm to dynamically select the exit point and partition point of the branchy model in the task stream, which aims to balance the number of tasks accomplished and task inference accuracy in the system. Experimental results show that the DRL algorithm can achieve performance close to that of the DP algorithm in the task stream scenario.

Recently, the neural network has become a popular technology for pedestrian inertial navigation to avoid the errors caused by the integral part of traditional inertial navigation system and also performs better than Pedestrian Dead Reckoning(PDR). However, researchers who leverage the neural network all discard the magnetic information due to the instability of magnetic field. On account of low-cost inertial measurement unit(IMU), relying on the gyroscope and the accelerometer only will inevitably produce horizontal angular deviation. This small angular deviation will be magnified as the trajectory length increases, and finally, cause positioning drift. Through many experiments and analyses, we discovered that there is a correlation between the magnetic information and the pedestrian’s body direction under a stable magnetic field. Based on the discovery, MAGINS, a neural network inertial navigation system corrected by magnetic information was designed. A data set of motion information including IMU data and real positions was created and utilized to train a network model as the basis of our system. For the sake of the stable and available magnetic information, we designed an algorithm to quantitatively detect the stability of the magnetic field. The heading of navigation can be corrected according to the stability and the correlation mentioned above. The experiment result shows that MAGINS can detect the stability of the magnetic field precisely, and correct the heading properly since the magnetic information will not produce accumulated errors. The positioning effect of MAGINS is better than other pedestrian inertial navigation systems only based on neural network.

With the exponential growth in the number of Internet-of-Things (IoT) devices, the cloud-centric computing paradigm can hardly meet the increasingly high requirements for low latency, high bandwidth, ease of availability, and more intelligent services. Therefore, a distributed and decentralized computing architecture is imperative, where edge-centric computing, such as fog computing and mist computing, has been recently proposed. Edge-centric computing resources can be managed locally and personally rather than being administered by a remote centralized third party. However, security and privacy issues are the main challenges due to the absence of trust between the IoT devices and edge computing nodes (ECNs). A blockchain, as a decentralized, trustless, and immutable public ledger, can well solve the trust-absence issue. In this article, we first elaborate on the security and privacy issues of edge-computing-enabled IoT, and then present the key characteristics of blockchains, which make blockchains well suited for the edge-centric IoT scenarios. Furthermore, we propose a general framework for blockchain-based edge-computing-enabled IoT scenarios that specifies the step-by-step procedure of a single transaction between an IoT end and an ECN. In addition, we design a smart contract within a private blockchain network that exploits the state-of-the-art machine learning algorithm, asynchronous advantage actor-critic (A3C), to allocate the edge computing resources, which exemplifies how artificial intelligence (AI) can be combined with blockchains. We further discuss the benefits of the convergence of AI and blockchains. Finally, simulation results are presented.

Recently, the term “Internet of Things” (IoT) has elicited escalating attention. The flexibility, agility, and ubiquitous accessibility have encouraged the integration between machine learning (ML) with IoT. However, there are many challenges that present the key inhibitors in moving ML to the public solution, such as centralized training, poor training efficiency, and heavy computing capabilities requirements. Therefore, bringing learning intelligence to edge IoT nodes has been spotlighted for some researches. Meanwhile, how to govern the use of learning results efficiently, reliably, scalably, and safely is hampered by the heterogeneity and nonconfidence among IoT nodes. In this article, we propose a blockchain-based collective Q-learning (CQL) approach to address the above issues, where lightweight IoT nodes are used to train parts of learning layers, then employing blockchain to share learning results in a verifiable and permanent manner. We further improve the traditional Proof of Work (PoW). Instead of solving a meaningless puzzle, we regard the learning process in the IoT node as a piece of work. Accordingly, the winner is the IoT node with the minimum reduced percentage of the learning loss function, referred to as the Proof-of-Learning (PoL) consensus protocol. Specifically, in order to show how the CQL approach works, we use it to address a networking integrated cloud-edge-end resource allocation in IoT. The experimental results reveal the superior performance of the proposed scheme.

Recently, integrated with the advanced communication technologies (e.g., 5G) and artificial intelligence (AI), mobile-edge intelligence (MEI) is regarded as the promising method to deal with the emerging challenges. Specifically, Device-to-Device (D2D) communications have been put forward to reduce the traffic pressure while extending cellular network capacity. However, the stability of the social network is important for the design of efficient and reliable traffic offloading strategy, which is often absent from the related work. Besides, most existing studies merely model the relation between a node pair as a binary or continuous value, neglecting the rich information between users. Moreover, many traditional models are conducted based on small-scale data sets or online Internet services, severely confining their applications in the D2D scenario. Thus, it is necessary to understand the network structure and select the key users to address the aforementioned challenges. In this article, we first propose a network representation model, named MPPT, to regard the multidimensional relations as a probability in a third-order (3-D) tensor space. Then, a mobile D2D social community is derived by integrating an edge base station (BS) and the nearby D2D users, and develop an anchored user selection algorithm to maintain the stability of multiple D2D social communities by choosing and retaining critical users adaptively under the limited network resources. Finally, we devise a probability-based onion layers anchored$(k,r)$-core (P-OLAK) algorithm to identify the anchor users. The large-scale data sets-based experimental results show the superiorities of the proposed methods.

The revolutions of computing and communication have opened up demands for the high quality of service (QoS), such as high data transmission, high reliability, and low latency. These new opportunities have spawned numerous studies on edge computing and artificial intelligence (AI), even the cooperation between them, referred to as edge intelligence. However, there are a number of handicaps that prevent edge intelligence from being used as a generic platform. The most intractable one is the heterogeneity and un-credibility among edges, hindering the way of sharing the learning results reliably, flexibly, and efficiently. In this paper, we propose a blockchain-assisted edge intelligence (B-EI) approach to solve the problem. The edge learning nodes train their local intelligence, followed by the improved blockchain to share the local intelligence, constructing edge intelligence among the heterogeneous and uncredible edges. Specifically, the improved blockchain employs a novel learning-measured consensus protocol, named Proof of Learning. The edges, also acted as the blockchain nodes, compete to have more superior local intelligence, instead of solving a hashed result. The superior local intelligence is then shared and distributed with other edges. It is not only beneficial to achieve edge intelligence, but also efficient to employ the computation resource, by replacing the hashing as the intelligence training. In order to show the potential benefits, we then use the proposed B-EI approach to solve a joint resource assignment problem. Simulation results show that our scheme outperforms the other state-of-art solutions, in terms of training episodes, and resource utility.

Recently, the emergence of blockchain has stirred great interests in the field of Internet of Things (IoT). However, numerous non-trivial problems in the current blockchain system prevent it from being used as a generic platform for large-scale services and applications in IoT. One notable drawback is the scalability problem. Lots of projects and researches have been done to solve this problem. Nevertheless, they do not consider different users' conditions, only using a single consensus protocol as the best fit one, as well as the IoT system is heavily constrained by computing and networking resources. In this article, we study a permissioned blockchain-based IoT architecture. In order to improve the scalability of the blockchain system and meet the needs of different users, we propose a service-oriented permissioned blockchain, where different consensus protocols are launched according to users' quality of service (QoS) requirements. Specially, we quantify a few popular consensus protocols. Additionally, we select block producers, which need a great number of computation resources, as well as dynamically allocate network bandwidth to the blockchain system. We formulate consensus protocols selection, block producers selection, and network bandwidth allocation as a joint optimization problem. We then use a dueling deep reinforcement learning approach to solve the problem. Simulation results demonstrate the effectiveness of our proposed scheme.

With the developments of communication technologies and smart manufacturing, Industrial Internet of Things (IIoT) has emerged. Software-defined networking (SDN), a promising paradigm shift, has provided a viable way to manage IIoT dynamically, called software-defined IIoT (SDIIoT). In SDIIoT, lots of data and flows are generated by industrial devices, where a physically distributed but logically centralized control plane is necessary. However, one of the most intractable problems is how to reach consensus among multiple controllers under complex industrial environments. In this paper, we propose a blockchain (BC)-based consensus protocol in SDIIoT, along with detailed consensus steps and theoretical analysis, where BC works as a trusted third party to collect and synchronize network-wide views between different SDN controllers. Specially, it is a permissioned BC. In order to improve the throughput of this BC-based SDIIoT, we jointly consider the trust features of BC nodes and controllers, as well as the computational capability of the BC system. Accordingly, we formulate view change, access selection, and computational resources allocation as a joint optimization problem. We describe this problem as a Markov decision process by defining state space, action space, and reward function. Due to the fact that it is difficult to solve this joint problem by traditional methods, we propose a novel dueling deep Q-learning approach. Simulation results are presented to show the effectiveness of our proposed scheme.