Multiple Cache Research Articles

Cooperative Edge Caching With Location-Based and Popular Contents for Vehicular Networks

In this article, we propose a cooperative edge caching scheme, which allows vehicles to fetch one content from multiple caching servers cooperatively. In specific, we consider two types of vehicular content requests, i.e., location-based and popular contents, with different delay requirements. Both types of contents are encoded according to fountain code and cooperatively cached at multiple servers. The proposed scheme can be optimized by finding an optimal cooperative content placement that determines the placing locations and proportions for all contents. To this end, we first analyze the upper bound proportion of content caching at a single server, which is determined by both the downloading rate and the association duration when the vehicle drives through the server's coverage. For both types of contents, the respective theoretical analysis of transmission delay and service cost (including content caching and transmission cost) are provided. We then formulate an optimization problem of cooperative content placement to minimize the overall transmission delay and service cost. As the problem is a multi-objective multi-dimensional multi-choice knapsack problem, which is proved to be NP-hard, we devise an ant colony optimization-based algorithm to solve the problem and achieve a near-optimal solution. Simulation results are provided to validate the performance of the proposed algorithm, including its convergence and optimality of caching, while guaranteeing low transmission delay and service cost.

Automated stereo-garage with multiple cache parking spaces—Structure, system and scheduling performance

Stereo garage is kind of large capacity parking equipment to alleviate the parking problem. In order to reduce the construction cost and improve the garage performance, this paper introduces an automated stereo-garage with multiple cache parking spaces. The structure of the garage is simplified into a stacker and several storage units, and multiple cache parking spaces are set up. Two scheduling strategies are designed to improve the efficiency of the garage and reduce the process time consumption of customers, respectively. The running time under these two strategies is expressed mathematically, followed by the input data of the garage and its analyzed statistical regularity. Subsequently, operation processes of the garage during busy periods are simulated, and its service performance is analyzed by means of queuing theory. Results and comparisons show the superiority of the proposed garage system, and combined scheduling recommendations are provided for improving the overall working performance of the equipment.

An efficient cache flat storage organization for multithreaded workloads for low power processors

The cache hierarchy of current multicores typically consists of three levels, ranging from the faster and smaller L1 level to the slower and larger L3 level. This approach has been demonstrated to be effective in high performance processors, since it reduces the average memory access time. However, when implemented in devices where energy efficiency becomes critical, like low power or embedded processors, conventional cache hierarchies may present some concerns. These concerns, which incur a waste of area and energy, are multiple cache lookups, block replication, block migration and private cache space overprovisioning. To deal with these issues, in this work we propose FOS-Mt, a new cache organization aimed at addressing energy savings in current multicores for multithreaded applications. FOS-Mt’s cache hierarchy consists of only two levels: the L1 cache level located in the core pipeline, and a single and flattened second level which conforms an aggregated cache space which is accessible by all the execution cores. This level is sliced into multiple small buffers, which are dynamically assigned to any of the running thread when they are expected to improve the system performance. Those buffers that are not allocated to any core are powered off to save energy. Experimental results show that FOS-Mt significantly reduces both static and dynamic energy consumption over other conventional cache organizations like NUCA or shared caches with the same storage capacity. Compared to the widely known cache decay approach, FOS-Mt achieves an improvement in the energy delay product by 19.3% on average. Moreover, despite the fact that FOS-Mt is an energy-aware architecture, performance is scarcely affected, since it is kept similar to that one achieved by conventional and cache decay approaches.

Latency Analysis for Distributed Coded Storage Systems

Modern communication and computation systems often consist of large networks of unreliable nodes. Still, it is well known that such systems can provide aggregate reliability via redundancy. While duplication may increase the load on a system, it can lead to significant performance improvement when combined with the judicious management of extra system resources. Prime examples of this abstract paradigm include multi-path routing across communication networks, content access from multiple caches in delivery networks, and master/slave computations on compute clusters. Several recent contributions in the area establish bounds on the performance of redundant systems, characterizing the latency-redundancy tradeoff under specific load profiles. Following a similar line of research, this paper introduces new analytical bounds and approximation techniques for the latency-redundancy tradeoff for a range of system loads and a class of symmetric redundancy schemes, under the assumption of Poisson arrivals, exponential service-rates, and fork-join scheduling policy. The proposed approach can be employed to efficiently approximate the latency distribution of a queueing system at equilibrium. Various metrics can subsequently be derived for this system, including the mean and variance of the sojourn time, and the tail decay rate of the stationary distribution. This paper also establishes the stability region in terms of arrival rates for redundant systems with certain symmetries. Finally, it offers selection guidelines for design parameters to provide latency guarantees based on the proposed approximations. Findings are substantiated by numerical results.

Food caching by a marine apex predator, the leopard seal (Hydrurga leptonyx)

The foraging behaviors of apex predators can fundamentally alter ecosystems through cascading predator–prey interactions. Food caching is a widely studied, taxonomically diverse behavior that can modify competitive relationships and affect population viability. We address predictions that food caching would not be observed in the marine environment by summarizing recent caching reports from two marine mammal and one marine reptile species. We also provide multiple caching observations from disparate locations for a fourth marine predator, the leopard seal (Hydrurga leptonyx (de Blainville, 1820)). Drawing from consistent patterns in the terrestrial literature, we suggest the unusual diversity of caching strategies observed in leopard seals is due to high variability in their polar marine habitat. We hypothesize that caching is present across the spectrum of leopard seal social dominance; however, prevalence is likely to increase in smaller, less-dominant animals that hoard to gain competitive advantage. Given the importance of this behavior, we draw attention to the high probability of observing food caching behavior in other marine species.

Multi-Tier Caching Analysis in CDN-Based Over-the-Top Video Streaming Systems

Internet video traffic has been been rapidly increasing and is further expected to increase with the emerging 5G applications such as higher definition videos, IoT and augmented/virtual reality applications. As end-users consume video in massive amounts and in an increasing number of ways, the content distribution network (CDN) should be efficiently managed to improve the system efficiency. The streaming service can include multiple caching tiers, at the distributed servers and the edge routers, and efficient content management at these locations affect the quality of experience (QoE) of the end users. In this paper, we propose a model for video streaming systems, typically composed of a centralized origin server, several CDN sites, and edge-caches located closer to the end user. We comprehensively consider different systems design factors including the limited caching space at the CDN sites, allocation of CDN for a video request, choice of different ports (or paths) from the CDN and the central storage, bandwidth allocation, the edge-cache capacity, and the caching policy. We focus on minimizing a performance metric, stall duration tail probability (SDTP), and present a novel and efficient algorithm accounting for the multiple design flexibilities. The theoretical bounds with respect to the SDTP metric are also analyzed and presented. The implementation on a virtualized cloud system managed by Openstack demonstrate that the proposed algorithms can significantly improve the SDTP metric, compared to the baseline strategies.

Efficient Algorithms for Coded Multicasting in Heterogeneous Caching Networks.

Coded multicasting has been shown to be a promising approach to significantly improve the performance of content delivery networks with multiple caches downstream of a common multicast link. However, the schemes that have been shown to achieve order-optimal performance require content items to be partitioned into several packets that grows exponentially with the number of caches, leading to codes of exponential complexity that jeopardize their promising performance benefits. In this paper, we address this crucial performance-complexity tradeoff in a heterogeneous caching network setting, where edge caches with possibly different storage capacity collect multiple content requests that may follow distinct demand distributions. We extend the asymptotic (in the number of packets per file) analysis of shared link caching networks to heterogeneous network settings, and present novel coded multicast schemes, based on local graph coloring, that exhibit polynomial-time complexity in all the system parameters, while preserving the asymptotically proven multiplicative caching gain even for finite file packetization. We further demonstrate that the packetization order (the number of packets each file is split into) can be traded-off with the number of requests collected by each cache, while preserving the same multiplicative caching gain. Simulation results confirm the superiority of the proposed schemes and illustrate the interesting request aggregation vs. packetization order tradeoff within several practical settings. Our results provide a compelling step towards the practical achievability of the promising multiplicative caching gain in next generation access networks.

Collaborative joint caching and transcoding in mobile edge networks

Video streaming has become a leading consumer of network resources in the last decade. Despite considerable developments, video content providers still face major challenges, which include minimizing data transfer from Content Delivery Network (CDN) or origin servers, CDN cost, and video startup delays. Recent edge computing technologies, such as Mobile Edge Computing (MEC) introduces new opportunities for Radio Access Networks (RANs) by providing computing and storage resources at the Mobile Base Stations (MBSs). Caching and processing videos at the edge networks relieve excessive data transfers over the backhaul links and minimize the viewers perceived delay. Collaborative caching and processing strategies have been proposed to efficiently utilize the edge resources, where neighboring MEC servers share the cached videos. However, such strategies introduce new challenges due to excessive backhaul links utilization for video sharing and limited resources. We propose a collaborative joint caching and processing strategy using the X2 network interface for sharing video data among multiple caches. Our design aims to minimize: (a) backhaul links usage for sharing video data, (b) network usage in transferring data from the CDN, (c) the viewer perceived delay, and (d) CDN cost. We also propose to fetch the higher bitrate version video from the origin/CDN servers and transcode it to the requested version on the fly to effectively use the Adaptive Bit Rate (ABR) streaming and online transcoding. This joint caching and processing approach is formulated as a minimization problem, subject to storage, processing, and bandwidth constraints. We also propose an online greedy algorithm that controls video transcoding, sharing using the X2 or backhaul links, and manages video caching and removing at the edge caches. Simulation results prove a better performance of our proposed algorithm compared to the recent edge caching approaches in terms of cost, average delay, cache removal, and cache hit ratio for different configurations.

A Computing and Content Delivery Network in the Smart City: Scenario, Framework, and Analysis

Mass services and applications have been reviewed as prominent characteristics of the smart city. However, a traditional mobile communication network cannot provide a considerable communication environment in this complicated network. Moreover, the requirement for different types of services and applications is quite discrepant, and QoE or users' satisfaction cannot be calculated by a unified standard. Meanwhile, the cache and computing resources have been treated with great importance by researchers and the industrial community for this complex network. In this article, we first deal with this issue and propose a novel network framework based on content delivery and computing deployment in order to make the network smart and clever. Resource intelligence based on various network services aims at a global optimal goal of computing, caching, and communication resources in the smart city to achieve high user QoE and low waiting time. Then we introduce an optimal resource allocation strategy including multiple cache and computational capability for user devices, MEC cloud, and macrocell cloud. Experimental results illustrate the effectiveness of the strategy we propose and reveal the relationship between waiting time and some key parameters in the network.

Probabilistic Caching Based on Maximum Distance Separable Code in a User-Centric Clustered Cache-Aided Wireless Network

We investigate how the maximum-distance separable (MDS) coding can be incorporated into probabilistic caching to utilize the limited storage space efficiently. In a user-centric clustered wireless network, each caching helper node probabilistically caches a segment of MDS coded sequence of each file. The segment size is optimized to maximize the cache hit probability or successful file retrieval probability. We reveal that the best way of storing files is determined by the condition whether the average amount of MDS coded information stored for the requested file within a user’s cluster exceeds the amount required for file retrieval or not. In terms of the cache hit probability maximization, if the condition is not fulfilled, it is proved that storing the complete file with a low probability is optimal. Otherwise, storing either a segment as small as possible with a high probability or a complete file with a low probability, according to a given environment, is shown to be desirable. We also analyze the successful retrieval probability, which accounts for both a cache hit event and successful transmissions from multiple caching helper nodes. Since the successful retrieval probability is in an intractable form, to find the desirable segment size, the theoretically driven algorithms with low search complexity are developed.

An Improved Method to Deploy Cache Servers in Software Defined Network-based Information Centric Networking for Big Data

Big data involves a large amount of data generation, storage, transfer from one place to another, and analysis to extract meaningful information. Information centric networking (ICN) is an infrastructure that transfers big data from one node to another node, and provides in-network caches. For software defined network-based ICN approach, a recently proposed centralized cache server architecture deploys single cache server based on path-stretch value. Despite the advantages of centralized cache in ICN, single cache server for a large network has scalability issue. Moreover, it only considers the path-stretch ratio for cache server deployment. Consequently, the traffic can not be reduced optimally. To resolve such issues, we propose to deploy multiple cache servers based on joint optimization of multiple parameters, namely: (i) closeness centrality; (ii) betweenness centrality; (iii) path-stretch values; and (iv) load balancing in the network. Our proposed approach first computes the locations and the number of cache servers based on the network topology information in an offline manner and the cache servers are placed at their corresponding locations in the network. Next, the controller installs flow rules at the switches such that the switches can forward the request for content to one of its nearest cache server. Upon reaching a content request, if the content request matches with the contents stored at the cache server, the content is delivered to the requesting node; otherwise, the request is forwarded to the controller. In the next step, controller computes the path such that the content provider first sends the content to the cache server. Finally, a copy of the content is forwarded to the requesting node. Simulation results confirmed that the proposed approach performs better in terms of traffic overhead and average end-to-end delay as compared to an existing state-of-the-art approach.

Advancing throughput of HEP analysis work-flows using caching concepts

High throughput and short turnaround cycles are core requirements for efficient processing of data-intense end-user analyses in High Energy Physics (HEP). Together with the tremendously increasing amount of data to be processed, this leads to enormous challenges for HEP storage systems, networks and the data distribution to computing resources for end-user analyses. Bringing data close to the computing resource is a very promising approach to solve throughput limitations and improve the overall performance. However, achieving data locality by placing multiple conventional caches inside a distributed computing infrastructure leads to redundant data placement and inefficient usage of the limited cache volume. The solution is a coordinated placement of critical data on computing resources, which enables matching each process of an analysis work-flow to its most suitable worker node in terms of data locality and, thus, reduces the overall processing time. This coordinated distributed caching concept was realized at KIT by developing the coordination service NaviX that connects an XRootD cache proxy infrastructure with an HTCondor batch system. We give an overview about the coordinated distributed caching concept and experiences collected on prototype system based on NaviX.

Single or Multiple Frames Content Delivery for Next-Generation Networks?

This paper addresses the four enabling technologies, namely multi-user sparse code multiple access (SCMA), content caching, energy harvesting, and physical layer security for proposing an energy and spectral efficient resource allocation algorithm for the access and backhaul links in heterogeneous cellular networks. Although each of the above mentioned issues could be a topic of research, in a real situation, we would face a complicated scenario where they should be considered jointly, and hence, our target is to consider these technologies jointly in a unified framework. Moreover, we propose two novel content delivery scenarios: 1) single frame content delivery (SFCD), and 2) multiple frames content delivery (MFCD), where the time duration of serving user requests is divided into several frames. In the first scenario, the requested content by each user is served over one frame. However, in the second scenario, the requested content by each user can be delivered over several frames. We formulate the resource allocation for the proposed scenarios as optimization problems where our main aim is to maximize the energy efficiency of access links subject to the transmit power and rate constraints of access and backhaul links, caching and energy harvesting constraints, and SCMA codebook allocation limitations. Due to the practical limitations, we assume that the channel state information values between eavesdroppers and base stations are uncertain and design the network for the worst case scenario. Since the corresponding optimization problems are mixed integer non-linear and nonconvex programming, NP-hard, and intractable, we propose an iterative algorithm based on the well-known alternate and successive convex approximation methods. In addition, the proposed algorithms are studied from the computational complexity, convergence, and performance perspectives. Moreover, the proposed caching scheme outperforms the existing traditional caching schemes like random caching and most popular caching. We also study the effect of joint and disjoint considerations of enabling technologies for the performance of next-generation networks. On the one hand, our proposed caching strategy increases slightly the computational complexity by 3%, 1.1%, and 2% compared to no caching, SFCD, and disjoint solution, respectively. On the other hand, the proposed caching scheme achieves a performance gain of 43%, 9.4%, and 51.3% compared to the three state-of-the-art schemes.

Global Dead-Block Management for Task-Parallel Programs

Task-parallel programs inefficiently utilize the cache hierarchy due to the presence of dead blocks in caches. Dead blocks may occupy cache space in multiple cache levels for a long time without providing any utility until they are finally evicted. Existing dead-block prediction schemes take decisions locally for each cache level and do not efficiently manage the entire cache hierarchy. This article introduces runtime-orchestrated global dead-block management , in which static and dynamic information about tasks available to the runtime system is used to effectively detect and manage dead blocks across the cache hierarchy. In the proposed global management schemes, static information (e.g., when tasks start/finish, and what data regions tasks produce/consume) is combined with dynamic information to detect when/where blocks become dead. When memory regions are deemed dead at some cache level(s), all the associated cache blocks are evicted from the corresponding level(s). We extend the cache controllers at both private and shared cache levels to use the aforementioned information to evict dead blocks. The article does an extensive evaluation of both inclusive and non-inclusive cache hierarchies and shows that the proposed global schemes outperform existing local dead-block management schemes.

Coverage Performance of NOMA in Wireless Caching Networks

In order to keep a balance between the transmission delay of backhaul and the spectrum efficiency of access links, the coverage performance of wireless networks with non-orthogonal multiple access (NOMA) and content caching is studied. First, an explicit expression for the coverage probability of a typical user is presented by using stochastic geometry and order statistics. This expression can provide useful insights in order to improve the coverage performance of NOMA communications. Second, a closed-form expression for the average coverage probability is derived. Finally, simulation results are provided to validate the accuracy of the analytical framework and demonstrate the performance gain, due to NOMA.

Simple and efficient transmission strategies for Device-to-Device caching networks

For device-to-device (D2D) caching networks, we propose simple transmission strategies in order to minimize the outage probability and maximize the average. We first propose a blanket transmission scheme where multiple caching server devices (CSDs) simultaneously transmit the same content to a RD without any information exchange and signal processing at the CSDs. We also propose an opportunistic transmission scheme where we select a single CSD that has the largest channel gain from a request device (RD), and the selected CSD then transmits the requested content to RD. We derive the outage probabilities and average throughputs and we extend the results to the case of the D2D caching network in the presence of multiple RDs. We also analyze and compare the performances of the proposed transmission strategies according to the threshold rate and transmit signal-to-noise ratio (SNR).

Milking the Cache Cow With Fairness in Mind

Information-centric networking (ICN) is a popular research topic. At its heart is the concept of in-network caching. Various algorithms have been proposed for optimizing ICN caching, many of which rely on collaborative principles, i.e. multiple caches interacting to decide what to store. Past work has assumed altruistic nodes that will sacrifice their own performance for the global optimum. We argue that this assumption is insufficient and oversimplifies the reality. We address this problem by modeling the in-network caching problem as a Nash bargaining game. We develop optimal and heuristic caching solutions that consider both performance and fairness. We argue that only algorithms that are fair to all parties involved in caching will encourage engagement and cooperation. Through extensive simulations, we show our heuristic solution, FairCache, ensures that all collaborative caches achieve performance gains without undermining the performance of others.

Fog Caching and a Trace-Based Analysis of its Offload Effect

Many years of research on Content Delivery Networks (CDNs) offers a number of effective methods for caching of content replicas or forwarding requests. However, recently CDNs have aggressively started migrating to clouds. Clouds present a new kind of distribution environment as each location can support multiple caching options varying in the level of persistence of stored content. A subclass of clouds located at network edge is referred to as fog clouds. Fog clouds help by allowing CDNs to offload popular content to network edge, closer to end users. However, due to the fact that fog clouds are extremely heterogeneous and vary wildly in network and caching performance, traditional caching technology is no longer applicable. This paper proposes a multi-level caching technology specific to fog clouds. To deal with the heterogeneity problem and, at the same time, avoid centralized control, this paper proposes a function that allows CDN services to discover local caching facilities dynamically, at runtime. Using a combination of synthetic models and real measurement dataset, this paper analyzes efficiency of offload both at the local level of individual fog locations and at the global level of the entire CDN infrastructure. Local analysis shows that the new method can reduce inter-cloud traffic by between 16 and 18 times while retaining less than 30% of total content in a local cache. Global analysis further shows that, based on existing measurement datasets, centralized optimization is preferred to distributed coordination among services.

Lazy Irrevocability for Best-Effort Transactional Memory Systems

IBM and Intel now offer commercial systems with Transactional Memory (TM), a programming paradigm whose aim is to facilitate concurrent programming while maximizing parallelism. These TM systems are implemented in hardware and provide a software fallback path to overcome the hardware implementation limitations. They are known as best-effort hardware TM (BE-HTM) systems. The software fallback path must be provided by the user to ensure forward progress, which adds programming complexity to the TM paradigm. We propose a new type of irrevocability (a transactional mode that marks transactions as non-abortable) to deal with BE-HTM limitations in a more efficient manner, and to liberate the user from having to program a fallback path. It is based on the concept of lazy subscription used in the context of software fallback paths, where the fallback lock is checked at the end of the transaction instead of at the beginning. We propose a hardware lazy irrevocability mechanism that does not involve changes in the coherence protocol. It solves the unsafe execution problem of premature commits associated with lazy subscription fallbacks, and can be triggered by the user via an ISA extension, for the sake of versatility. It is compared with its software counterpart, which we propose as an enhanced lazy single global lock with escaped spinning at the end of the transaction. We also propose the lazy irrevocability with anticipation, a mechanism that cannot be implemented in software, which significantly improves the performance of codes with multiple cache evictions of transactional data. The evaluation of the proposals is carried out with the Simics/GEMS simulator along with the STAMP benchmark suite, and we obtain speedups from 14 to 28 percent over the fallback path approaches.

Coded Caching With Nonuniform Demands

We consider a network consisting of a file server connected through a shared link to a number of users, each equipped with a cache. Knowing the popularity distribution of the files, the goal is to optimally populate the caches, such as to minimize the expected load of the shared link. For a single cache, it is well known that storing the most popular files is optimal in this setting. However, we show here that this is no longer the case for multiple caches. Indeed, caching only the most popular files can be highly suboptimal. Instead, a fundamentally different approach is needed, in which the cache contents are used as side information for coded communication over the shared link. We propose such a coded caching scheme and prove that it is close to optimal.