To transcode or not? A machine learning based edge video caching and transcoding strategy

Bukhari, Syed M. A. H.; Baccour, Emna; Bilal, Kashif; Shuja, Junaid; Erbad, Aiman; Bilal, Muhammad

doi:10.1016/j.compeleceng.2023.108741

Cited by 8 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we consider the future, the ongoing investigation and incorporation of machine learning models into video caching systems are crucial for achieving unparalleled levels of efficiency, customization, and protection in content delivery. This will guarantee that the digital streaming industry continues to flourish and develop in accordance with user requirements and societal principles [5], [7], [8], [10].…”

Section: Related Workmentioning

confidence: 98%

“…The interplay between different machine learning applications, such as optimizing network edge caching and developing content engagement methods, will play a crucial role in determining the future of streaming services as we deal with the intricacies of video content delivery and consumption [5], [9], [20]. The incorporation of these technologies not only holds the potential to improve the productivity and efficacy of content delivery networks, but also to enhance the user experience by providing tailored, captivating, and top-notch content offers.…”

Section: Related Workmentioning

confidence: 99%

“…Reinforcement Learning (RL), a subset of Machine Learning (ML), is particularly well-suited for the everchanging and intricate nature of Video-on-Demand (VoD) services. It offers the potential for ongoing enhancement in caching tactics by employing a sequential and adaptive decisionmaking process [1], [2], [3], [4], [5]. The main difficulty lies in balancing the goals of enhancing cache hit rates and minimizing latency with the necessity of ensuring user data privacy and security.…”

Section: Introductionmentioning

confidence: 99%

“…Conventional caching algorithms, like Least Recently Used (LRU) and Least Frequently Used (LFU), have a drawback in that they are fixed and cannot anticipate or adjust to the changing patterns of content popularity. On the other hand, a reinforcement learning (RL)-based system has the ability to continuously improve caching decisions in real-time by analyzing user interactions, content access patterns, and network circumstances [4], [5], [6], [7], [8]. This proactive caching strategy not only reduces the delay and amount of data transferred but also enhances the overall effectiveness of content delivery networks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimal Video Caching at The Edge of Network by Using Machine Learning

Ullah,

Xiaopeng,

Khan

2024

Preprint

View full text Add to dashboard Cite

Efficiently managing network resources in the dynamic field of video-on-demand (VoD) services is a significant challenge. This requires creative methods to optimize video caching strategies. This study examines the use of machine learning (ML), particularly reinforcement learning (RL), into edge network designs to improve video caching procedures. The decentralized, adaptable, and learning characteristics of machine learning offer a powerful method for effectively managing caching in real-time. This technique leads to reduced latency, optimized bandwidth utilization, and improved cache hit rates. Conventional caching algorithms frequently fail to adjust to the changing needs and popularity of material that is inherent in Video on Demand (VoD) services. Our study presents an innovative reinforcement learning (RL) caching method that is specifically developed to automatically adapt caching choices using real-time data analysis, thus guaranteeing an effective content delivery network. We created and evaluated three separate machine learning models: Convolutional Neural Networks (CNN) for extracting features, Deep Q-Networks (DQN) for generating decisions, and a hybrid model that combines the advantages of both CNN and DQN to achieve improved performance. By conducting thorough simulations and implementing our models in real-world deployment scenarios, we have shown substantial improvements compared to traditional caching methods in terms of scalability, adaptability to evolving user patterns, and overall network efficiency. This innovative method not only simplifies the transfer of content in Video on Demand (VoD) systems, but also establishes a new standard for integrating Artificial Intelligence (AI) technologies in network optimization. It effectively tackles present and future obstacles in the digital streaming industry.

show abstract