FoV-Aware Edge Caching for Adaptive 360° Video Streaming

As the performance gap between memory systems and processors has increased, virtual memory management plays an important role in system performance. Different caching policies have different effects on the system performance. This paper studies an adaptive replacement policy which has low overhead on system and is easy to implement. Simulations show that our algorithm performs better than least-recently-used (LRU) and least-frequently-used (LFU). In addition, it performs similarly to LRU in worst cases.

Virtual reality (VR) has been envisioned as the killer-application in the 5G mobile networks. Among numerous VR services, 360° video streaming is the most promising one. Nevertheless, its wide adoption is hindered by large latency incurred in cloud-based video delivery and insufficient bandwidth resource in Radio Access Network (RAN). Fortunately, the emergence of Multi-access Edge Computing (MEC) become an enabler to fulfill the potential of VR by providing caching and computing resources at network edges. Also, since a user can view only a part of the entire 360° video frame due to the limitation of eye vision, users' Quality of Experience (QoE) can be further enhanced if we can predict his Field of View (FoV). In this paper, we propose a novel MEC-assisted FoV-aware and QoE-driven Adaptive Streaming (MFQAS) scheme for 360° videos. Specifically, we first provide a comprehensive QoE model for 360° video streaming. Second, we adopt AutoRegression Moving Average (ARMA) model in FoV prediction. Finally, we propose a heuristic algorithm to optimize the caching and computing decision at MEC server based on predicted FoV so that users' QoE can be enhanced. The simulation results show that our proposed method can provide much better prediction accuracy and QoE compared with baseline algorithms.

As one of the most important manifestations of virtual reality (VR), 360° panoramic videos in recent years have experienced booming development due to the desire for immersive and interactive experiences. Compared to traditional videos, 360° videos are featured with uncertain user Field of View (FoV), more sensitive delay tolerance, and much higher bandwidth requirement, bringing unprecedented challenges to 360° video streaming. Meanwhile, the development of 5G and mobile edge computing starts to pave the way for high-bandwidth low-latency video streaming. Some preliminary works focus on either individual FoV prediction or multiuser Quality of Experience (QoE) oriented cache strategy design, while how to design a holistic solution toward optimizing the overall user QoE with considerations over fairness and long-term system cost remains a nontrivial problem. In this article, we propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Ebublio</monospace> , a novel intelligent edge caching framework to address the aforementioned challenges in 360° video streaming. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Ebublio</monospace> consists of a collaborative FoV prediction (CFP) module and a long-term tile caching optimization (LTO) module to jointly optimize the long-term user QoE and system cost. The former module integrates the features of video content, user trajectory, and other users’ records for combined prediction. The latter one employs the Lyapunov framework and a subgradient optimization approach toward the optimal caching replacement policy. Our trace-driven evaluation demonstrates the superiority of our framework, with about 42% improvement in FoV prediction, and 36% improvement in QoE at similar traffic consumption.

In accordance with the recent enhancement of display technology, users demand a higher quality of streaming service, which escalates the bandwidth requirement. Considering the recent advent of high FPS (frame per second) 4K and 8K resolution 360° videos, such bandwidth concern further intensifies in 360° Virtual Reality (VR) content streaming even at a larger scale. However, the currently available bandwidth in most of the developed countries can hardly support the bandwidth required to stream such a scale of content. To address the mismatch between the demand on higher quality of streaming service and the saturated network improvement, we propose SALI360 that practically solves the mismatch by utilizing the characteristics of the human vision system (HVS). By pre-rendering a set of regions - where viewers are expected to fixate - on 360° VR content in higher quality than the other regions, SALI360 improves viewers' quality of perception (QoP) while reducing content size with geometry-based 360° content encoding. In our user experiment, we compare the performance of SALI360 to the existing 360° content-encoding techniques based on 20 viewers' head movement and eye gaze traces. To evaluate viewers' QoP, we propose FoL (field of look) that captures viewers' quality perception area in the visual focal field (8°) rather than a wide (around 90°) field of view (FoV). Results of our experimental 360° VR video streaming show that SALI360 achieves 53.3% of PSNR improvement in FoL, while gaining 9.3% of PSNR improvement in FoV. In addition, our subjective study on 93 participants verifies that SALI360 improves viewers' QoP in the 360° VR streaming service.

Predicting a user’s field-of-view (FoV) accurately can help to significantly reduce the high bandwidth requirements for 360° video streaming, as it enables sending only the tiles corresponding to the predicted FoV. Since many approaches for user head-orientation (i.e., FoV) prediction have been proposed in the literature, ranging from simple linear regression to more complex neural networks, it is difficult to comprehensively decide which method to use. Towards resolving this gap in knowledge, in this work we benchmark user prediction algorithms over an aggregation of multiple datasets and study the implications of this analysis. Our results demonstrate that it is indeed difficult for any prediction algorithm to accurately predict a user’s FoV beyond a very short future time window of approximately 300 ms. We also observe that users’ viewing behavior is dominated by sideways head movement, rather than up-and-down. These findings have implications on network bandwidth, latency, and playback buffering at the client: (1) Extra tiles are needed around the user’s FoV in order to correct for prediction errors; in particular, a rectangular padding achieves lower stall rate than square padding, for the same bandwidth usage; (2) Video playout buffers, network delay, and jitter need to be small in order to avoid stale predictions of the user’s field-of-view, which are only valid 300 ms into the future; (3) Per-video and per-user personalization of the padding can save bandwidth for slow-moving users or videos. We mathematically quantify these tradeoffs and present simulation results to demonstrate these findings and implications. Our results have implications for FoV prediction methods in future 360° streaming systems.

Support vector machines (SVMs) can solve structured multioutput learning problems such as multilabel classification, multiclass classification, and vector regression. SVM training is expensive, especially for large and high-dimensional data sets. The bottleneck of the SVM training often lies in the kernel value computation. In many real-world problems, the same kernel values are used in many iterations during the training, which makes the caching of kernel values potentially useful. The majority of the existing studies simply adopt the least recently used (LRU) replacement strategy for caching kernel values. However, as we analyze in this article, the LRU strategy generally achieves high hit ratio near the final stage of the training but does not work well in the whole training process. Therefore, we propose a new caching strategy called EFU (less frequently used), which replaces the EFU kernel values that enhance least frequently used (LFU). Our experimental results show that EFU often has 20% higher hit ratio than LRU in the training with the Gaussian kernel. To further optimize the strategy, we propose a caching strategy called hybrid caching for the SVM training (HCST), which has a novel mechanism to automatically adapt the better caching strategy in different stages of the training. We have integrated the caching strategy into ThunderSVM, a recent SVM library on many-core processors. Our experiments show that HCST adaptively achieves high hit ratios with little runtime overhead among different problems including multilabel classification, multiclass classification, and regression problems. Compared with other existing caching strategies, HCST achieves 20% more reduction in training time on average.

Recently, commercialization of 360° video streaming service and various studies are being conducted in a mobile environment. It also makes 360° video streaming service through a mobile cloud available. The mobile cloud can easily provide characteristics of the terminal and existing features of the cloud service, such as contents and service of the application, in the mobile environment. Using this function, it is applied to 360° video streaming services in mobile environment. Unlike the conventional filming method which only shows the angle that camera operator intended, 360° videos can display the direction desired by the viewer in real time by recording a view in every direction at the same time. By displaying the real-time 3D image information to the user, the viewer can have more realistic contents and interactive experience. 360° video typically has a resolution of 4 k or more, which causes network load in mobile streaming. The adaptive HTTP streaming service currently provides 360 resolution video streams in proportion to their bandwidth. However, this method is not responsible for the quality of the video. Therefore, we propose a high-quality video streaming method with low network load in mobile environment. 360 video is divided into FoV (field of view) and non-FoV, and the image is transmitted with high quality for FoV and low quality for non-FoV. In this paper, we propose a method of FoV on the background frame (FBF) differentiated from the existing Http adaptive streaming method. It is possible to view high resolution video in a mobile environment while maintaining a regular level of video quality even in a non-viewing area.

360-degree videos have gained increasing popularity in recent years with the developments and advances in Virtual Reality (VR) and Augmented Reality (AR) technologies. In such applications, a user only watches a video scene within a field of view (FoV) centered in a certain direction. Predicting the future FoV in a long time horizon (more than seconds ahead) can help save bandwidth resources in on-demand video streaming while minimizing video freezing in networks with significant bandwidth variations. In this work, we treat the FoV prediction as a sequence learning problem, and propose to predict the target user's future FoV not only based on the user's own past FoV center trajectory but also other users' future FoV locations. We propose multiple prediction models based on two different FoV representations: one using FoV center trajectories and another using equirectangular heatmaps that represent the FoV center distributions. Extensive evaluations with two public datasets demonstrate that the proposed models can significantly outperform benchmark models, and other users' FoVs are very helpful for improving long-term predictions.

360º video is an essential component of VR/AR/MR systems that provides immersive experience to the users. However, 360º video is associated with high bandwidth requirements. The required bandwidth can be reduced by exploiting the fact that users are interested in viewing only a part of the video scene and that users request viewports that overlap with each other. Motivated by the findings of our recent works where the benefits of caching video tiles at edge servers instead of caching entire 360º videos were shown, in this paper, we introduce the concept of virtual viewports that have the same number of tiles with the original viewports. The tiles forming these viewports are the most popular ones for each video and are determined by the users' requests. Then, we propose a proactive caching scheme that assumes unknown videos' and viewports' popularity. Our scheme determines which videos to cache as well as which is the optimal virtual viewport per video. Virtual viewports permit to lower the dimensionality of the cache optimization problem. To solve the problem, we first formulate the content placement of 360º videos in edge cache networks as a Markov Decision Process (MDP), and then we determine the optimal caching placement using the Deep Q-Network (DQN) algorithm. The proposed solution aims at maximizing the overall quality of the 360º videos delivered to the end-users by caching the most popular 360º videos at base quality along with a virtual viewport in high quality. We extensively evaluate the performance of the proposed system and compare it with that of known systems such as Least Frequently Used (LFU), Least Recently Used (LRU), First-In-First-Out (FIFO), over both synthetic and real 360º video traces. The results reveal the large benefits coming from proactive caching of virtual viewports instead of the original ones in terms of the overall quality of the rendered viewports, the cache hit ratio, and the servicing cost.

Recent state-of-the-art Virtual Reality (VR) Head-Mounted Displays (HMD) provide wide Field of Views (FoV) which were not possible in the past. Due to this development, HMD FoVs are now approaching a level that parallels natural human eyesight. Previous efforts have shown that reduced FoVs affect user perception of distance in a given environment, but none have investigated VR HMDs with wide FoVs. Therefore, in this paper we directly investigate the effect of HMD FoV on distance estimation in virtual environments. We performed a user study with 14 participants who performed a blind throwing task wearing a Pimax 5K Plus HMD, in which we virtually restricted the FoV to 200°, 110°, and 60°. We found a significant difference in perceived distance between the 200° and 60° FoVs, as well as between the 110° and 60° FoVs. However, no significant difference was observed between 200° and 110°. Our results indicate that users tend to underestimate distance with the narrower FoV.

Streaming of live 360-degree video allows users to follow a live event from any view point and has already been deployed on some commercial platforms. However, the current systems can only stream the video at relatively low-quality because the entire 360-degree video is delivered to the users under limited bandwidth. Streaming video falling into user field of view (FoV) can improve bandwidth efficiency of 360-degree video delivery. In this paper, we propose to use the idea of flocking to simultaneously improve the accuracy of user FoV prediction and video delivery efficiency for live 360-degree video streaming. By assigning variable playback latencies to users in a streaming session based on their network conditions, a streaming flock is formed and led by strong users with low playback latencies in the front of the flock. We propose a long short-term memory (LSTM) based collaborative FoV prediction scheme where the FoV traces of users in the front of the flock are utilized to predict the FoV of users behind them. Given a predicted FoV, we develop an optimal rate allocation strategy to maximize the perceptual quality. By conducting experiments using real-world user FoV traces and LTE/5G network bandwidth traces, we evaluate the gains of the proposed strategies over several benchmarks. Our experimental results demonstrate that the proposed streaming system can increase the overall quality dramatically by about 10 dB compared with heuristic FoV prediction strategy. In addition, the network-aware flocking formation can further reduce the video freeze without influencing video quality.

To satisfy rapidly increasing multimedia service requests from mobile users, content caching at the network edges (e.g., base stations) has been regarded as a promising technique in future mobile networks. In this paper, by virtue of Deep Reinforcement Learning (DRL) with respect to solving complicated control problems, we propose a framework on Double Deep Q-Network for cooperative edge caching in mobile networks. Particularly, we aim at minimizing the long-term average content fetching delay of mobile users without requiring any priori knowledge of content popularity distribution. Trace-driven simulation results show that our proposed framework outperforms some existing caching algorithms, including Least Recently Used (LRU), Least Frequently Used (LFU) and First-In First-Out (FIFO) caching strategies by 7%, 11% and 9% improvements, respectively. Besides, our proposed work is further shown that only average 4% performance loss exists compared to an omniscient oracle algorithm.

Access to the internet and WWW is growing extensively, which results in heavy network traffic. To reduce the network traffic proxy server is used. Proxy server reduces the load of server. If the cache replacement algorithm of proxy server's cache is efficient then proxy server will be helpful to reduce the network traffic in more efficient manner. In this paper we are considering proxy server cache to be Level 1 (L1) cache and storage cache of proxy server to be Level 2 (L2) cache. For collecting the real trace CC proxy server is used in an organization. Log of proxy server gives the information of various URLs accessed by various clients with time. For performing experiments various URLs were given a numeric identity. This paper proposes an efficient replacement algorithm on L1 for proxy server. The replacement algorithms taken into consideration are Least Recently Used (LRU), Least Frequently Used (LFU), First In First Out (FIFO). Access Pattern of L1 and L2 are different as if the desired page is not on L1 then it accesses to L2. Thus L1 is having better temporal locality than L2. Thus the replacement algorithm which is giving efficient results for L1 may not be suitable for L2. This paper also proposes a preeminent pair of replacement algorithms for L1 and L2 cache for proxy server.

The buffer cache plays an essential role in smoothing the gap between the upper level computational components and the lower level storage devices. A good buffer cache management scheme should be beneficial to not only the computational components, but also the storage components by reducing disk I/Os. Existing cache replacement algorithms are well optimized for disks in normal mode, but inefficient under faulty scenarios, such as a parity-based disk array with faulty disk(s). To address this issue, we propose a novel penalty-aware buffer cache replacement strategy, named Victim Disk(s) First (VDF) cache, to improve the reliability and performance of a storage system consisting of a buffer cache and disk arrays. VDF cache gives higher priority to cache the blocks on the faulty disks when the disk array fails, thus reducing the I/Os addressed directly to the faulty disks. To verify the effectiveness of the VDF cache, we have integrated VDF into the popular cache algorithms least frequently used (LFU) and least recently used (LRU), named VDF-LFU and VDF-LRU, respectively. We have conducted intensive simulations as well as a prototype implementation for disk arrays to tolerate one disk failure (RAID-5) and two disk failures (RAID-6). The simulation results have shown that VDF-LFU can reduce disk I/Os to surviving disks by up to 42.3 percent in RAID-5 and 50.7 percent in RAID-6, and VDF-LRU can reduce those by up to 36.2 percent in RAID-5 and 48.9 percent in RAID-6. Our measurement results also show that VDF-LFU can speed up the online recovery by up to 46.3 percent in RAID-5 and 47.2 percent in RAID-6 under spare-rebuilding mode, or improve the maximum system service rate by up to 47.7 percent in RAID-5 under degraded mode without a reconstruction workload. Similarly, VDF-LRU can speed up the online recovery by up to 34.6 percent in RAID-5 and 38.2 percent in RAID-6, or improve the system service rate by up to 28.4 percent in RAID-5.

Human field of regard, field of view, and attention bias