With the explosive demands for data, content delivery networks are facing ever-increasing challenges to meet end-users quality-of-experience requirements, especially in terms of delay. Content can be migrated from surrogate servers to local caches closer to end-users to address delay challenges. Unfortunately, these local caches have limited capacities, and when they are fully occupied, it may sometimes be necessary to remove their lower-priority content to accommodate higher-priority content. At other times, it may be necessary to return previously removed content to local caches. Downloading this content from surrogate servers is costly from the perspective of network usage, and potentially detrimental to the end-user QoE in terms of delay. In this paper, we consider an edge content delivery network with vehicular nodes and propose a content migration strategy in which local caches offload their contents to neighboring edge caches whenever feasible, instead of removing their contents when they are fully occupied. This process ensures that more contents remain in the vicinity of end-users. However, selecting which contents to migrate and to which neighboring cache to migrate is a complicated problem. This paper proposes a deep reinforcement learning approach to minimize the cost. Our simulation scenarios realized up to a 70% reduction of content access delay cost compared to conventional strategies with and without content migration.
相關內容
Networking：IFIP International Conferences on Networking。
Explanation：國際網絡會議(yi)。
Publisher：IFIP。
SIT：
In surgical computer vision applications, obtaining labeled training data is challenging due to data-privacy concerns and the need for expert annotation. Unpaired image-to-image translation techniques have been explored to automatically generate large annotated datasets by translating synthetic images to the realistic domain. However, preserving the structure and semantic consistency between the input and translated images presents significant challenges, mainly when there is a distributional mismatch in the semantic characteristics of the domains. This study empirically investigates unpaired image translation methods for generating suitable data in surgical applications, explicitly focusing on semantic consistency. We extensively evaluate various state-of-the-art image translation models on two challenging surgical datasets and downstream semantic segmentation tasks. We find that a simple combination of structural-similarity loss and contrastive learning yields the most promising results. Quantitatively, we show that the data generated with this approach yields higher semantic consistency and can be used more effectively as training data.
In the cooperative cellular network, relay-like base stations are connected to the central processor (CP) via rate-limited fronthaul links and the joint processing is performed at the CP, which thus can effectively mitigate the multiuser interference. In this paper, we consider the joint beamforming and compression problem with per-antenna power constraints in the cooperative cellular network. We first establish the equivalence between the considered problem and its semidefinite relaxation (SDR). Then we further derive the partial Lagrangian dual of the SDR problem and show that the objective function of the obtained dual problem is differentiable. Based on the differentiability, we propose two efficient projected gradient ascent algorithms for solving the dual problem, which are projected exact gradient ascent (PEGA) and projected inexact gradient ascent (PIGA). While PEGA is guaranteed to find the global solution of the dual problem (and hence the global solution of the original problem), PIGA is more computationally efficient due to the lower complexity in inexactly computing the gradient. Global optimality and high efficiency of the proposed algorithms are demonstrated via numerical experiments.
By executing offloaded tasks from mobile users, edge computing augments mobile user equipments (UEs) with computing/communications resources from edge nodes (ENs), enabling new services (e.g., real-time gaming). However, despite being more resourceful than UEs, allocating ENs' resources to a given favorable set of users (e.g., closer to ENs) may block other UEs from their services. This is often the case for most existing approaches that only aim to maximize the network social welfare or minimize the total energy consumption but do not consider the computing/battery status of each UE. This work develops an energy-based proportional-fair framework to serve all users with multiple tasks while considering both their service requirements and energy/battery levels in a multi-layer edge network. The resulting problem for offloading tasks and allocating resources toward the tasks is a Mixed-Integer Nonlinear Programming, which is NP-hard. To tackle it, we leverage the fact that the relaxed problem is convex and propose a distributed algorithm, namely the dynamic branch-and-bound Benders decomposition (DBBD). DBBD decomposes the original problem into a master problem (MP) for the offloading decisions and multiple subproblems (SPs) for resource allocation. To quickly eliminate inefficient offloading solutions, MP is integrated with powerful Benders cuts exploiting the ENs' resource constraints. We then develop a dynamic branch-and-bound algorithm (DBB) to efficiently solve MP considering the load balance among ENs. SPs can either be solved for their closed-form solutions or be solved in parallel at ENs, thus reducing the complexity. The numerical results show that DBBD returns the optimal solution in maximizing the proportional fairness among UEs. DBBD has higher fairness indexes, i.e., Jain's index and min-max ratio, in comparison with the existing ones that minimize the total consumed energy.
In traditional blockchain networks, transaction fees are only allocated to full nodes (i.e., miners) regardless of the contribution of forwarding behaviors of light nodes. However, the lack of forwarding incentive reduces the willingness of light nodes to relay transactions, especially in the energy-constrained Mobile Ad Hoc Network (MANET). This paper proposes a novel dual auction mechanism to allocate transaction fees for forwarding and validation behaviors in the wireless blockchain network. The dual auction mechanism consists of two auction models: the forwarding auction and the validation auction. In the forwarding auction, forwarding nodes use Generalized First Price (GFP) auction to choose transactions to forward. Besides, forwarding nodes adjust the forwarding probability through a no-regret algorithm to improve efficiency. In the validation auction, full nodes select transactions using Vickrey-Clarke-Grove (VCG) mechanism to construct the block. We prove that the designed dual auction mechanism is Incentive Compatibility (IC), Individual Rationality (IR), and Computational Efficiency (CE). Especially, we derive the upper bound of the social welfare difference between the social optimal auction and our proposed one. Extensive simulation results demonstrate that the proposed dual auction mechanism decreases energy and spectrum resource consumption and effectively improves social welfare without sacrificing the throughput and the security of the wireless blockchain network.
Secure multi-party computation (MPC) allows users to offload machine learning inference on untrusted servers without having to share their privacy-sensitive data. Despite their strong security properties, MPC-based private inference has not been widely adopted in the real world due to their high communication overhead. When evaluating ReLU layers, MPC protocols incur a significant amount of communication between the parties, making the end-to-end execution time multiple orders slower than its non-private counterpart. This paper presents HummingBird, an MPC framework that reduces the ReLU communication overhead significantly by using only a subset of the bits to evaluate ReLU on a smaller ring. Based on theoretical analyses, HummingBird identifies bits in the secret share that are not crucial for accuracy and excludes them during ReLU evaluation to reduce communication. With its efficient search engine, HummingBird discards 87--91% of the bits during ReLU and still maintains high accuracy. On a real MPC setup involving multiple servers, HummingBird achieves on average 2.03--2.67x end-to-end speedup without introducing any errors, and up to 8.64x average speedup when some amount of accuracy degradation can be tolerated, due to its up to 8.76x communication reduction.
The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data applications. However, the stateless nature of serverless platforms poses major challenges when supporting stateful I/O intensive workloads such as a lack of native support for stateful execution, state sharing, and inter-function communication. In this paper, we explore the feasibility of performing stateful big data analytics on serverless platforms and improving I/O throughput of functions by using modern storage technologies such as Intel Optane DC Persistent Memory (PMEM). To this end, we propose Marvel, an end-to-end architecture built on top of the popular serverless platform, Apache OpenWhisk and Apache Hadoop. Marvel makes two main contributions: (1) enable stateful function execution on OpenWhisk by maintaining state information in an in-memory caching layer; and (2) provide access to PMEM backed HDFS storage for faster I/O performance. Our evaluation shows that Marvel reduces the overall execution time of big data applications by up to 86.6% compared to current MapReduce implementations on AWS Lambda.
The exclusive or (xor) function is one of the simplest examples that illustrate why nonlinear feedforward networks are superior to linear regression for machine learning applications. We review the xor representation and approximation problems and discuss their solutions in terms of probabilistic logic and associative copula functions. After briefly reviewing the specification of feedforward networks, we compare the dynamics of learned error surfaces with different activation functions such as RELU and tanh through a set of colorful three-dimensional charts. The copula representations extend xor from Boolean to real values, thereby providing a convenient way to demonstrate the concept of cross-validation on in-sample and out-sample data sets. Our approach is pedagogical and is meant to be a machine learning prolegomenon.
Edge computing facilitates low-latency services at the network's edge by distributing computation, communication, and storage resources within the geographic proximity of mobile and Internet-of-Things (IoT) devices. The recent advancement in Unmanned Aerial Vehicles (UAVs) technologies has opened new opportunities for edge computing in military operations, disaster response, or remote areas where traditional terrestrial networks are limited or unavailable. In such environments, UAVs can be deployed as aerial edge servers or relays to facilitate edge computing services. This form of computing is also known as UAV-enabled Edge Computing (UEC), which offers several unique benefits such as mobility, line-of-sight, flexibility, computational capability, and cost-efficiency. However, the resources on UAVs, edge servers, and IoT devices are typically very limited in the context of UEC. Efficient resource management is, therefore, a critical research challenge in UEC. In this article, we present a survey on the existing research in UEC from the resource management perspective. We identify a conceptual architecture, different types of collaborations, wireless communication models, research directions, key techniques and performance indicators for resource management in UEC. We also present a taxonomy of resource management in UEC. Finally, we identify and discuss some open research challenges that can stimulate future research directions for resource management in UEC.
Autonomic computing investigates how systems can achieve (user) specified control outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191