Existing memory reclamation policies on mobile devices may be no longer valid because they have negative effects on the response time of running applications. In this paper, we propose SWAM, a new integrated memory management technique that complements the shortcomings of both the swapping and killing mechanism in mobile devices and improves the application responsiveness. SWAM consists of (1) Adaptive Swap that performs swapping adaptively into memory or storage device while managing the swap space dynamically, (2) OOM Cleaner that reclaims shared object pages in the swap space to secure available memory and storage space, and (3) EOOM Killer that terminates processes in the worst case while prioritizing the lowest initialization cost applications as victim processes first. Experimental results demonstrate that SWAM significantly reduces the number of applications killed by OOMK (6.5x lower), and improves application launch time (36% faster) and response time (41% faster), compared to the conventional schemes.

Recently, realistic services like virtual reality and augmented reality have gained popularity. These realistic services require deterministic transmission with end-to-end low latency and high reliability for practical applications. However, for these real-time services to be deterministic, the network core should provide the requisite level of network. To deliver differentiated services to each real-time service, network service providers can classify applications based on traffic. However, due to the presence of personal information in headers, application classification based on encrypted application data is necessary. Initially, we collected application traffic from four well-known applications and preprocessed this data to extract encrypted application data and convert it into model input. We proposed a lightweight transformer model consisting of an encoder, a global average pooling layer, and a dense layer to categorize applications based on the encrypted payload in a packet. To enhance the performance of the proposed model, we determined hyperparameters using several performance evaluations. We evaluated performance with 1D-CNN and ET-BERT. The proposed transformer model demonstrated good performance in the performance evaluation, with a classification accuracy and F1 score of 96% and 95%, respectively. The time complexity of the proposed transformer model was higher than that of 1D-CNN but performed better in application classification. The proposed transformer model had lower time complexity and higher classification performance than ET-BERT.

With the evolution of cellular networks and wireless-local-area-network-based communication technologies, services for smart device users have appeared. With the popularity of 4G and 5G, smart device users can now consume larger bandwidths than before. Consequently, the demand for various services, such as streaming, online games, and video conferences, has increased. For improved quality of experience (QoE), streaming services utilize adaptive bitrate (ABR) algorithms to handle network bandwidth variations. ABR algorithms use network bandwidth history for future network bandwidth prediction, allowing them to perform efficiently when network bandwidth fluctuations are minor. However, in environments with frequent network bandwidth changes, such as wireless networks, the QoE of video streaming often degrades because of inaccurate predictions of future network bandwidth. To address this issue, we utilize the gated recurrent unit, a time series prediction model, to predict the network bandwidth accurately. We then propose a buffer-based ABR streaming technique that selects optimized video-quality settings on the basis of the predicted bandwidth. The proposed algorithm was evaluated on a dataset provided by Zeondo by categorizing instances of user mobility into walking, bus, and train scenarios. The proposed algorithm improved the QoE by approximately 11% compared with the existing buffer-based ABR algorithm in various environments.

Today, research trends clearly confirm the fact that machine learning technologies open up new opportunities in various computing environments, such as Internet of Things, mobile, and enterprise. Unfortunately, the prior efforts rarely focused on designing system-level input/output stacks (e.g., page cache, file system, block input/output, and storage devices). In this paper, we propose a new page replacement algorithm, called ML-CLOCK, that embeds single-layer perceptron neural network algorithms to enable an intelligent eviction policy. In addition, ML-CLOCK employs preference rules that consider the features of the underlying storage media (e.g., asymmetric read and write costs and efficient write patterns). For evaluation, we implemented a prototype of ML-CLOCK based on trace-driven simulation and compared it with the traditional four replacement algorithms and one flash-friendly algorithm. Our experimental results on the trace-driven environments clearly confirm that ML-CLOCK can improve the hit ratio by up to 72% and reduces the elapsed time by up to 2.16x compared with least frequently used replacement algorithms.

Recently, the technologies of on-device AI have been accelerated with the development of new hardware and software platforms. Therefore, many researchers and engineers focus on how to enable ML technologies on mobile devices with limited hardware resources. In this paper, we revisit on-device ML designed to support ML technologies on mobile devices and describe the three challenges when using on-device ML in detail. Then, we propose a new data management policy, called Overlay-ML, which efficiently solves two challenges that we discovered. Especially, we designed Overlay-ML to work in the application space with two key ideas. The first key idea is to extend the limited memory space using the usable space of the underlying storage device. The second key idea is to provide data transparency, which hides where the data is stored so that running ML models think the data is stored in the same place. For evaluation, we implemented an image detection application based on TensorFlow Lite which is a well-known on-device ML framework, and modified it to enable the features of Overlay-ML. All evaluation was performed on two state-of-the-art smartphones that are high-end embedded devices. Our evaluation results clearly show Overlay-ML can effectively prevent unexpected termination by Android OS and present a good loss value in real-world workload.

A crash-consistency mechanism of database application (hereinafter DBMS for short) imposes an enormous burden on the journaling process of the file system (e.g., JBD2) in that it employs regular files on the file system to persistently preserve the application's journal data with synchronous system calls. Unfortunately, much of the previous research is impractical in real-world scenarios because they require changing a lot of source lines of code in multiple software layers of the software stack or using special hardware (e.g., the transactional flash storage or NVM technologies). In this paper, we propose a new journal mode of DBMS, called S-WAL, which compresses the raw data journaled by the database to alleviate both the redundant journaling operations and harmful write amplification. We believe that S-WAL is a practical way to support application-level crash consistency on the existing mobile devices because only a few lines of DBMS code need to be changed, without the need to employ special hardware. We demonstrate the effectiveness of S-WAL by running four popular mobile applications on the latest smartphone. Our evaluation results show that S-WAL considerably outperforms existing journal modes of DBMS in all cases. In the best case, S-WAL reduces the elapsed time by up to 7.5× more than the PERSIST mode and by up to 51% more than the traditional WAL mode.