Showing papers on "Smart Cache published in 2019"

A Reinforcement Learning Based Smart Cache Strategy for Cache-Aided Ultra-Dense Network

Abstract: The integration of caching and ultra-dense network (UDN) can not only improve the efficiency of content retrieval by reducing duplicate content transmissions but also improve the network throughput and system energy efficiency (EE) of the UDN. In this paper, we focus on energy consumption aspects of cache-aided UDN (CUDN) and develop a novel caching strategy to improve the system EE. Different from the existing researches, we consider a more realistic scenario where the popularity of the cache content is dynamic and unknown. The proposed caching strategy is a deep reinforcement learning (DRL)-based approach that uses a deep Q-network to approximate the Q action-value function. We optimize the structure and corresponding parameters of the deep Q-network according to the latest findings in the field of DRL and deep learning (DL) to improve the performance of this caching strategy. The simulation results show that the performance in terms of EE of the CUDN can be significantly improved by using our proposed caching strategy.

Fundamental Structure of Optimal Cache Placement for Coded Caching with Nonuniform Demands

Abstract: This paper studies the caching system of multiple cache-enabled users with random demands. Under nonuniform file popularity, we thoroughly characterize the optimal uncoded cache placement structure for the coded caching scheme (CCS). Formulating the cache placement as an optimization problem to minimize the average delivery rate, we identify the file group structure in the optimal solution. We show that, regardless of the file popularity distribution, there are \emph{at most three file groups} in the optimal cache placement{, where files within a group have the same cache placement}. We further characterize the complete structure of the optimal cache placement and obtain the closed-form solution in each of the three file group structures. A simple algorithm is developed to obtain the final optimal cache placement by comparing a set of candidate closed-form solutions computed in parallel. We provide insight into the file groups formed by the optimal cache placement. The optimal placement solution also indicates that coding between file groups may be explored during delivery, in contrast to the existing suboptimal file grouping schemes. Using the file group structure in the optimal cache placement for the CCS, we propose a new information-theoretic converse bound for coded caching that is tighter than the existing best one. Moreover, we characterize the file subpacketization in the CCS with the optimal cache placement solution and show that the maximum subpacketization level in the worst case scales as $\mathcal{O}(2^K/\sqrt{K})$ for $K$ users.

Cooperative caching for multimedia data in mobile P2P networks

Abstract: In this paper, we propose a cooperative caching scheme for multimedia data via clusters based on peers connectivity in mobile P2P networks In the proposed scheme, a cluster is organized for cache sharing among mobile peers with long-term connectivity, and metadata are disseminated to neighbor peers for efficient multimedia data search performance It reduces data duplication and uses cache space efficiently through integrative cache management of peers inside the cluster The proposed scheme reduces data replacement time in the event of changes in topology or cache data replacement using the concept of temporal cache It performs data recovery and cluster adjustment through cluster management in the event of an abrupt disconnection of a peer In this scheme, metadata of popular multimedia data are disseminated to neighbor peers for efficient data searching In a data search, queries are processed in the order of local cache, metadata, the cluster to which it belongs, and neighbor clusters, in accordance with cooperative caching strategy Performance evaluation results show that the proposed scheme has a higher cache hit ratio, and lower cost for data replacement and query processing than existing schemes

Smart-Cache: Optimising Memory Accesses for Arbitrary Boundaries and Stencils on FPGAs

Abstract: A key requirement for high performance on FPGAs is to maintain continuous data streaming from the DRAM. An impediment in many computations, especially in the scientific computing domain, is irregular stencils and boundary conditions, requiring memory accesses that are random, redundant, or both. To address this problem, we present Smache, a novel smart-caching framework that uses FPGA on-chip memory resources for optimising access for arbitrary stencil shapes and boundary conditions. We propose a combination of stream and static buffers, and it is the latter that allows arbitrarily large offsets in stencils. The architecture is complemented by a formal model for determining buffer configuration. We propose a hybrid use of the block and distributed RAM on the FPGA. The design is validated for a 2D grid, 4-point stencil with circular boundaries.

A Case for Two-stage Inference with Knowledge Caching

Abstract: Real-world intelligent services employing deep learning technology typically take a two-tier system architecture -- a dumb front-end device and smart back-end cloud servers. The front-end device simply forwards a human query while the back-end servers run a complex deep model to resolve the query and respond to the front-end device. While simple and effective, the current architecture not only increases the load at servers but also runs the risk of harming user privacy. In this paper, we present knowledge caching, which exploits the front-end device as a smart cache of a generalized deep model. The cache locally resolves a subset of popular or privacy-sensitive queries while it forwards the rest of them to back-end cloud servers. We discuss the feasibility of knowledge caching as well as technical challenges around deep model specialization and compression. We show our prototype two-stage inference system that populates a front-end cache with 10 voice commands out of 35 commands. We demonstrate that our specialization and compression techniques reduce the cached model size by 17.4x from the original model with 1.8x improvement on the inference accuracy.

A Smart Cache Strategy for Tag-Based Browsing of Digital Collections

Abstract: Tag-based browsing is a common interaction technique in business, the culture industry and many other domains. According to this technique, digital resources have a set of descriptive tags associated, which can be used to perform an exploratory search, letting users focus on interesting resources. For this purpose, a set of tags is collected sequentially, and, at each stage, the set of resources described by all the selected tags is filtered. This browsing style can be implemented using inverted indexes. However, this implementation requires a considerable amount of set operations during navigation, which can have a negative impact on user experience. In this paper we propose addressing this shortcoming by using a cache that makes it possible to identify equivalent browsing states (i.e., states yielding the same set of filtered resources), which in turn will avoid redundant computations. The technique proposed will be compared with more basic implementations using a real-world web-based collection in the field of digital humanities.

Energy-aware cache hierarchy assessment targeting HEVC encoder execution

Abstract: This article presents a framework for assessing the behavior and energy impact of cache hierarchies when encoding HEVC on general-purpose processors. The memory energy estimation framework estimates energy consumption of cache hierarchies based on mathematical models combined with memory access profiling tools. The energy analysis of several cache hierarchies targeting HEVC encoders with different input parameters is also carried out. This article provides relevant information on the energy consumption of HEVC encoders by taking into account the different tradeoffs between energy efficiency, coding efficiency, and other important cache memory design parameters, such as miss rates and access latency. The first analysis explores cache performance for different specifications, such as capacity, line size. Results show that most of the energy is spent on reading operations (almost 73% on the first level cache), indicating that HEVC encoders could benefit from memory technologies with low reading energy costs. This analysis also pointed that increasing the capacity affects more the energy performance of the first level cache, which represents 34.78% (on average) more energy consumption than the last level cache. Based on this investigation, we report the most suited cache specifications for HEVC encoders for each video resolution. The second analysis discusses the impact of HEVC input parameters in cache performance, demonstrating that it is possible to save up to 30% of energy with a small increase of 2% in BD-BR. A comparative analysis between HM (HEVC model) and x265 (H.265 video codec) HEVC software models is presented, demonstrating that x265 is faster (speedup to 648x), and more cache efficient providing less memory energy (31.38% on average) compared to the HM implementation. The results obtained with the proposed framework indicate that the management of video encoding parameters combined with application-tuned cache specifications has a high potential to reduce energy consumption of video coding systems while keeping video quality.