Cache Occupancy Research Articles

Optimization of Embedded System With Edge Computing and Sleep Modes for Balance Between Energy Consumption and Cache Occupancy

Optimization of Embedded System With Edge Computing and Sleep Modes for Balance Between Energy Consumption and Cache Occupancy

Optimal Load-Splitting and Distributed-Caching for Dynamic Content Over the Wireless Edge

In this work, we consider the problem of ‘fresh’ caching at distributed (front-end) local caches of content that is subject to ‘dynamic’ updates at the (back-end) database. We first provide new models and analyses of the average operational cost of a network of distributed edge-caches that utilizes wireless multicast to refresh aging content. We attack the problems of what to cache in each edge-cache and how to split the incoming demand amongst them (also called “load-splitting” in the rest of the paper) in order to minimize the operational cost. While the general form of the problem comes with an NP-hard Knapsack structure, we were able to completely solve the problem by judiciously choosing the number of edge-caches to be deployed over the network This reduces the complex problem to a solvable special case. Interestingly, our findings reveal that the optimal caching policy necessitates unequal load-splitting over the edge-caches even when all conditions are symmetric. Moreover, we find that edge-caches with higher load will generally cache fewer but relatively more popular content. We further investigate the tradeoffs between cost reduction and cache savings when employing equal and optimal load-splitting solutions for demand with Zipf( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$z$</tex-math> </inline-formula> ) popularity distribution. Our analysis reveals that equal load-splitting to edge-caches achieves close-to-optimal for less predictable demand ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$z&lt;2$</tex-math> </inline-formula> ) while also saving in the cache size. On the other hand, for more predictable demand ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$z&gt;2$</tex-math> </inline-formula> ), optimal load-splitting results in substantial cost gains while decreasing the cache occupancy.

A DTN oriented adaptive routing algorithm based on node load

In recent years, Delay Tolerant Networks (DTN) have received more and more attention. At the same time, several existing DTN routing algorithms generally have disadvantages such as poor scalability and inability to perceive changes in the network environment. This paper proposes an AdaptiveSpray routing algorithm. The algorithm can dynamically control the initial maximum message copy number according to the cache occupancy rate of the node itself, and the cache occupancy rate is added as an impact factor to the calculation of the probability of each node meeting the destination node. In the forwarding phase, the node will first compare the meeting probability of itself and the meeting node to the destination node, and then choose different forwarding strategies. The simulation shows that the AdaptiveSpray algorithm proposed in this paper has obvious advantages compared with the existing routing algorithms in terms of message delivery rate and average delay.

XAI-Based Microarchitectural Side-Channel Analysis for Website Fingerprinting Attacks and Defenses

Website Fingerprinting attacks aim to track the visited websites in browsers and infer confidential information about users. Several studies showed that recent advancements in Machine Learning (ML) and Deep Learning (DL) algorithms made it possible to implement website fingerprinting attacks even though various defense techniques are present in the network. Nevertheless, trained models for website detection are not analyzed deeply to identify the leakage sources which are not always visible to both attackers and Cyber Threat Intelligence engineers. This study focuses on explaining ML and DL models in the context of microarchitecture-based website fingerprinting attacks. In the attack model, performance counters and cache occupancy side-channels are implemented on Google Chrome and Tor browsers. After ML and DL models are trained, LIME and saliency map XAI methods are applied to examine the leakage points in the side-channel data. In order to match the leakage samples in the measurements to the network traces, a novel dataset is collected by utilizing Google Chrome and Firefox browser developer tools. Next, the efficiency of explainable methods are analyzed with XAI metrics. Finally, an XAI-based obfuscation defense technique is proposed as a countermeasure against microarchitecture-based website fingerprinting attacks

A Study of an IT-Assisted Higher Education Model Based on Distributed Hardware-Assisted Tracking Intervention.

This paper presents an in-depth study and analysis of the model of higher education using distributed hardware tracking intervention of information technology. The MEC-based dynamic adaptive video stream caching technology model is proposed. The model dynamically adjusts the bit rate by referring to the broadband estimation and cache occupancy data to ensure users have a smooth experience effect. Simulation results show that the model has fewer transcoding times and generates lower latency than the traditional model, which is suitable for dual-teacher classroom scenarios and further improves the quality of the user's video viewing experience. The model uses an edge cloud collaborative architecture to migrate the rendering technology to an edge server closer to the user side, enabling real-time interaction, computation, and rendering, reducing the time of data transmission as well as computation time. According to the blended learning-based adaptive intervention model, three rounds of teaching practice are conducted to validate the effectiveness of the intervention model in terms of both student process performance and outcome performance, thereby improving learning adaptability and improving learning effect. Teachers' teaching has a significant impact on learning motivation (β = 0.311, p < 0.01), which in turn affects learning adaptability. Teachers use scientific teaching methods to stimulate students' learning motivation, mobilize enthusiasm, and improve learning adaptability. Under the communication topology of the system as a directed graph, a multi-intelligent system dynamic model with grouping is established; i.e., the intragroup intelligence has the same dynamics but is different between groups, and all system dynamics are unknown. The proposed novel policy iterative algorithm is used to learn the optimal control protocol and achieve optimal consistency control. The effectiveness of the algorithm is demonstrated by the simulation experimental results. The simulation results show that the model has lower latency and energy consumption compared to the cloud rendering model, which is suitable for the safety education classroom scenario and solves the outstanding problems of network connection rate and cloud service latency.

An Adaptive Routing Algorithm Based on Relation Tree in DTN.

It is found that nodes in Delay Tolerant Networks (DTN) exhibit stable social attributes similar to those of people. In this paper, an adaptive routing algorithm based on Relation Tree (AR-RT) for DTN is proposed. Each node constructs its own Relation Tree based on the historical encounter frequency, and will adopt different forwarding strategies based on the Relation Tree in the forwarding phase, so as to achieve more targeted forwarding. To further improve the scalability of the algorithm, the source node dynamically controls the initial maximum number of message copies according to its own cache occupancy, which enables the node to make negative feedback to network environment changes. Simulation results show that the AR-RT algorithm proposed in this paper has significant advantages over existing routing algorithms in terms of average delay, average hop count, and message delivery rate.

An IoT-Based Water Level Detection System Enabling Fuzzy Logic Control and Optical Fiber Sensor

The usage of wireless sensors has become widespread for the collection of data for various Internet of Things (IoT) products. Specific wireless sensors use optical fiber technology as transmission media and lightwave signals as carriers, showing the advantages of antielectromagnetic interference, high sensitivity, and strong reliability. Hence, their application in IoT systems becomes a research hotspot. In this article, multiple optical fiber sensors are constructed as an IoT detection system, and a Transmission Control Protocol (TCP)/Internet Protocol (IP) communication stack is used for the sensor module. Furthermore, design of gateway module, data server, and monitoring module is established in order to run the data server in the Windows system and communicate across the network segments. Furthermore, the optical fiber sensor is connected to the development board with WiFi, meanwhile considering the optical fiber wireless network’s congestion problem. The fuzzy logic concept is introduced from the perspective of cache occupancy, and a fiber sensor’s network congestion control algorithm is proposed. In the experiment, the IoT detection system with multiple optical fiber sensors is used for water level detection, and the sensor’s real-time data detected by the User Interface (UI) are consistent with the feedback results. The proposed method is also compared with the SenTCP algorithm and the CODA algorithm, and it was observed that the proposed network congestion control algorithm based on the fuzzy logic can improve network throughput and reduce the network data packet loss.

Estimation of Node Cache Occupancy in Satellite Storage Network

The satellite network with cache function becomes the future development trend. How to efficiently use the node cache of the satellite network has become a research hotspot. A theoretical problem that needs to be solved in the latest research on effective utilization of cache is the estimation of cache occupancy. Based on the martingale encapsulation theory, combined with the channel conditions, access protocols, and queuing strategies in the satellite storage network, a satellite node occupancy estimation method and theoretical bounds are proposed in a two-layer satellite network of GEO and LEO. The accuracy of the martingale encapsulation method in estimating the cache occupancy is estimated by simulations. The simulation results show that our method is precise. The cache occupancy estimation method we proposed provides a theoretical basis for the optimal allocation of satellite cache resources.

Design of Optoelectronic Hybrid Switching High Performance Computing Internet

Optoelectronic hybrid network technology is mixed with pure electric packet switching network, which can improve network capacity and reduce power consumption. However, the long configuration time and complex management of optical circuit switch affect the performance of optoelectronic hybrid network. Therefore, a new optoelectronic hybrid network architecture (BET) is designed. The network architecture consists of Ethernet electric packet switching network and optical wavelength routing network. The signal receiving and dispatching of optical routing network is realized by circular arrayed waveguide grating router. Based on the characteristics of wavelength cycling routing, there is no need to adjust the routing of optical signals to the destination port, that is, there is no need to configure the optical wavelength routing network. At the same time, an intelligent node dynamic reconfiguration (RG) algorithm is designed to improve the resource utilization of optical nodes. In this method, the network link utilization, cache occupancy, and network load are taken into account to adjust the distribution of optical nodes in the optoelectronic hybrid network. In the process of the experiment, by changing the message length, it is found that the optical wavelength routing network can achieve large capacity and new-type transmission and effectively reduce the delay at the same time; on the optoelectronic hybrid network, with the help of Hadoop platform, distributed cluster is built and used to transmit an XML data encoding (ED code), solve the finite state transducers (FST) and encode them. Compared with the traditional electric packet switching network, the transmission delay of ED code is greatly reduced after the introduction of optical circuit switch, and the efficiency of FST solution and coding calculation is improved by at least 30%.

Phase-Aware Cache Partitioning to Target Both Turnaround Time and System Performance

The Last Level Cache (LLC) plays a key role in the system performance of current multi-cores by reducing the number of long latency main memory accesses. The inter-application interference at this shared resource, however, can lead the system to undesired situations regarding performance and fairness. Recent approaches have successfully addressed fairness and turnaround time (TT) in commercial processors. Nevertheless, these approaches must face sustaining system performance, which is challenging. This work makes two main contributions. LLC behaviors regarding cache performance, data reuse and cache occupancy, that adversely impact on the final performance are identified. Second, based on these behaviors, we propose the Critical-Phase Aware Partitioning Approach (CPA), which reduces TT while sustaining (and even improving) IPC by making an effective use of the LLC space. Experimental results show that CPA outperforms CA, Dunn and KPart state-of-the-art approaches, and improves TT (over 40 percent in some workloads) over Linux default behavior while sustaining or even improving IPC by more than 3 percent in several mixes.

Optoelectronic Hybrid Network Architecture and Its Performance Analysis

Optoelectrical hybrid network technology is introduced into a network based on pure electrical packet switching, which increases network capacity and reduces power consumption. However, the problems of long configuration time and complex management of optical circuit switches affect the performance of hybrid optoelectrical networks. A new type of hybrid optoelectronic network architecture (HOEP) cooperated by Ethernet packet switching network and optical wavelength routing network was designed in the study. The optical routing network transmitted and received optical signals by using a circular array waveguide grating router, and transmitted the optical signal carrying data to the target port based on the characteristics of wavelength cyclic routing. The entire process only needed to modulate the data signal, and did not need to configure the optical wavelength routing network. At the same time, in order to further improve the resource utilization of optical nodes, a kind of intelligent node dynamic reconstruction (RC) algorithm was designed. Combining with network link utilization, cache occupancy, and network load value, this method could dynamically adjust the usage distribution of optical nodes for reconstruction. During the experiment, the RC algorithm was applied to the HOEP network architecture. Compared with other typical network architectures, the HOEP network proposed in the study can effectively reduce the network cost, power consumption, and improve network throughput. Moreover, the introduction of RC algorithm and network equipment can make the cost remain within the controllable range, while it can further increase the network throughput and reduce the power consumption of the HOEP network, thereby meeting the dynamic demand for network bandwidth with larger data traffic.

Website Fingerprinting Through the Cache Occupancy Channel and its Real World Practicality

Website fingerprinting attacks use statistical analysis on network traffic to compromise user privacy. The classical attack model used to evaluate website fingerprinting attacks assumes an on-path adversary , who observes traffic traveling between the user's computer and the network. In this article we investigate a different attack model, in which the adversary sends JavaScript code to the target user's computer. This code mounts a cache side-channel attack to identify other websites being browsed. Using machine learning techniques to classify traces of cache activity, we achieve high classification accuracy in both the open-world and the closed-world models. Our attack is more resistant than network-based fingerprinting to the effects of response caching, and resilient both to network-based defenses and to side-channel countermeasures. We carry out a real-world evaluation of several aspects of our attack, exploring the impact of the changes in websites and browsers over time, as well as of the attacker's ability to guess the software and hardware configuration of the target user's computer. To protect against cache-based website fingerprinting, new defense mechanisms must be introduced to privacy-sensitive browsers and websites. We investigate one such mechanism, and show that it reduces the effectiveness of the attack and completely eliminates it when used in the Tor Browser.

Cache pressure-aware caching scheme for content-centric networking

Content centric networking (CCN) is a new networking paradigm to meet the growing demand for content access in the future. Because of its important role in accelerating content retrieval and reducing network transmission load, in-network caching has become one of the core technologies in CCN and has attracted wide attention. The existing caching schemes often lack sufficient consideration of node cache status and the temporal validity of user requests, and thus the cache efficiency of the network is greatly reduced. In this paper, a cache pressure-aware caching scheme is proposed, which comprehensively takes into account various factors such as content popularity, cache occupancy rate, cache replacement rate, and the validity period of the Interest packet to achieve reasonable cache placement and replacement. Simulation results show that the proposed scheme effectively improves the cache hit rate and the resource utilization while decreasing the average response hops.

Efficient caching strategy in content‐centric networking for vehicular ad‐hoc network applications

Recently, content-centric networking (CCN) has been proposed as a promising solution for content distribution in vehicular ad-hoc networks (VANETs) owing to its named-data routing and in-network caching characteristics. In this network, the caching strategies are performed in the intermediate nodes, and even in the vehicular storage space. However, the typically existing caching strategies have indicated the low stored contents efficiency due to the peculiarities of VANET environment, like cache redundancy, high mobility, rapidly changing topology, and limited vehicular storage space. In this study, the authors proposed an efficient caching strategy in vehicle-to-vehicle scenario through CCN, which considers the requirements of different types of applications, the crucial features of data, and the peculiarities of the vehicular network (e.g. content popularity, cache occupancy, the stability link of the vehicles, and user's preference). Each vehicle makes its caching decision independently to improve the cache space and efficient use of the stored contents corresponding to the requirements of different application types. Simulation results validate that the proposed strategy outperforms other caching strategies in terms of reducing data retrieval delay, increasing cache hit ratio, and improving the cache performance on the vehicles.

DPSAF: Forward Prediction Based Dynamic Packet Scheduling and Adjusting With Feedback for Multipath TCP in Lossy Heterogeneous Networks

As multihomed terminals are equipped with multiple interfaces and allowed to access heterogeneous networks, transferring data simultaneously through all the available paths becomes possible and also brings many benefits. Multipath TCP (MPTCP) has been proposed to distribute an application stream over different TCP connections. However, due to the disparate latencies of different paths, the problem of existing out-of-order packets usually occurs at the receiver. Large number of these packets exhaust the limited receiving buffer and make the receive window be stalled, which greatly degrade the throughput. Thus, an efficient scheduling mechanism will play an important role to keep in-order delivery. However, almost all of the previous intelligent scheduling mechanisms ignored packet losses, and didn't consider window changes of the congestion control algorithm and utilize the feedback information, which cannot perform well in the lossy heterogeneous networks. In this paper we propose a new scheduling algorithm: Forward Prediction based Dynamic Packet Scheduling and Adjusting with Feedback (DPSAF). DPSAF first utilizes maximum likelihood estimation in TCP modeling to estimate the data amount sent on other paths simultaneously, which takes packet loss rate and time offset into consideration, then gets feedback information from SACK options and fixes the scheduling value. From the simulation, we can see that our mechanism obviously improves throughput and reduces cache occupancy at receiver in lossy heterogeneous networks.

Cache Exclusivity and Sharing

A problem on multicore systems is cache sharing, where the cache occupancy of a program depends on the cache usage of peer programs. Exclusive cache hierarchy as used on AMD processors is an effective solution to allow processor cores to have a large private cache while still benefitting from shared cache. The shared cache stores the “victims” (i.e., data evicted from private caches). The performance depends on how victims of co-run programs interact in shared cache. This article presents a new metric called the victim footprint (VFP). It is measured once per program in its solo execution and can then be combined to compute the performance of any exclusive cache hierarchy, replacing parallel testing with theoretical analysis. The work evaluates the VFP by using it to analyze cache sharing by parallel mixes of sequential programs, comparing the accuracy of the theory to hardware counter results, and measuring the benefit of exclusivity-aware analysis and optimization.

Managing the Performance/Error Tradeoff of Floating-point Intensive Applications

Modern embedded systems are becoming more reliant on real-valued arithmetic as they employ mathematically complex vision algorithms and sensor signal processing. Double-precision floating point is the most commonly used precision in computer vision algorithm implementations. A single-precision floating point can provide a performance boost due to less memory transfers, less cache occupancy, and relatively faster mathematical operations on some architectures. However, adopting it can result in loss of accuracy. Identifying which parts of the program can run in single-precision floating point with low impact on error is a manual and tedious process. In this paper, we propose an automatic approach to identify parts of the program that have a low impact on error using shadow-value analysis. Our approach provides the user with a performance/error tradeoff, using which the user can decide how much accuracy can be sacrificed in return for performance improvement. We illustrate the impact of the approach using a well known implementation of Apriltag detection used in robotics vision. We demonstrate that an average 1.3x speedup can be achieved with no impact on tag detection, and a 1.7x speedup with only 4% false negatives.

Hardware support for protective and collaborative cache sharing

Shared caches are generally optimized to maximize the overall throughput, fairness, or both, among multiple competing programs. In shared environments and compute clouds, users are often unrelated to each other. In such circumstances, an overall gain in throughput does not justify an individual loss. This paper explores cache management policies that allow conservative sharing to protect the cache occupancy for individual programs, yet enable full cache utilization whenever there is an opportunity to do so. We propose a hardware-based mechanism called cache rationing. Each program is assigned a portion of the shared cache as its ration. The hardware support protects the ration so it cannot be taken away by peer programs while in use. However, a program can exceed its pre-allocated ration, but only if another program has unused space in its allocated portion of ration. We show that rationing provides good resource protection and full cache utilization of the shared cache for a variety of co-runs.

Maximizing Cache Hit Ratios by Variance Reduction

TTL cache models provide an attractive unified approximation framework for caching policies like LRU and FIFO, whose exact analysis is notoriously hard. In this paper, we advance the understanding of TTL models by explicitly considering stochastic capacity constraints. We find in particular that reducing the variance of the cache occupancy is instrumental to optimize the cache hit ratio in an online setting. To enforce such a desired low variance, we propose a novel extension of the TTL model by rewarding popular objects with longer TTLs. An attractive feature of the proposed model is that it remains closed under an exact network analysis.

HIT RATE MAXIMIZATION BY LOGICAL CACHE PARTITIONING IN A MULTI-CORE ENVIRONMENT

It is imperative for any level of cache memory in a multi-core architecture to have a well defined, dynamic replacement algorithm in place to ensure consistent superlative performance. The most prevalently used LRU replacement policy does not acquaint itself dynamically to the changes in the workload. As a result, it can lead to sub-optimal performance for certain applications whose workloads exhibit frequently fluctuating patterns. To overcome the limitation of this conventional LRU approach, our paper proposes a novel counter-based replacement technique which logically partitions the cache elements into four zones based on their ‘likeliness’ to be referenced by the processor in the near future. Categorizing the elements into different zones is achieved with the help of a 3-bit counter that is associated with every cache line. On a cache hit, the corresponding element is promoted from one zone to another zone. Replacement candidates are chosen from the zones in the ascending order of their ‘likeliness factor’ (i.e.,) the first search space for the victim would be the never likely to be referenced zone, followed by the subsequent zones till the most likely to be referenced zone is reached. Periodic zone demotion of elements also occurs to make sure that stale data does not pollute the cache. Experimental results obtained by using the PARSEC benchmarks have shown almost 7% improvement in the overall number of hits and 3% improvement in the average cache occupancy percentage when compared to LRU algorithm.