کنفرانس مهندسی برق ایران

صفحه اصلی / سی و چهارمین کنفرانس بین المللی مهندسی برق

ProCAVE: A Self-Adaptive, Full-Lifecycle Edge Caching Framework for Video Streaming via Predictive Bandwidth Estimation and Preference-Aware Deep Reinforcement Learning

نویسندگان :

Yeganeh Chatri¹ Behzad Akbari² Foad Ghaderi³ Pejman Goudarzi⁴

1- دانشگاه تربیت مدرس تهران 2- دانشگاه تربیت مدرس تهران 3- دانشگاه تربیت مدرس تهران 4- پژوهشگاه ارتباطات و فناوری اطلاعات

کلمات کلیدی :

HTTP adaptive streaming،Edge caching،Deep reinforcement learning،Bandwidth prediction،Transformer،Quality of experience (QoE)

چکیده :

The growing demand for mobile video streaming requires edge delivery systems that adapt efficiently to rapid network fluctuations and diverse user preferences. Existing approaches such as FlyCache rely on reactive ABR heuristics and loosely coupled cache policies, limiting their responsiveness and coordination under real-world wireless dynamics. We propose \textbf{ProCAVE}(Proactive Caching with Adaptive Video Experience), a self-adaptive DRL-based framework that unifies predictive bandwidth modeling, proactive bitrate selection, and preference-aware cache control. ProCAVE employs: (i) a lightweight Transformer for short-term throughput forecasting; (ii) a PPO-driven ABR agent; and (iii) a DDPG-based continuous cache controller operating on a high-dimensional global state. Experiments using \textit{MovieLens} preference traces and \textit{Ghent 4G} bandwidth measurements show that ProCAVE improves byte hit rate, reduces backhaul load, and enhances QoE compared with FlyCache and other baselines. These results highlight the benefits of predictive, DRL-coordinated control for efficient and user-centric edge video delivery.

لیست مقالات

لیست مقالات بایگانی شده

MAD-TI: Meta-path Aggregated-Graph Attention Network for Drug Target Interaction Prediction

Reza Shami Tanha - Maryam Sadighian - Arash Zabihian - Mohsen Hooshmand - Mohsen Afsharchi

Sparse Autoencoder-Based Extraction of Muscle Synergies for Hand Movement Analysis from Surface EMG Signals

Fariba Biyouki - Asma Jafari Ani

Electroencephalogram-Based Spinal Cord Injury Signals Decoding Using Temporal-Spatial Dense Deep Convolutional Neural Network

Mohammadreza Abbasi Sardari - Hamed Mirzabagherian - Amir Abolfazl Suratgar - Mohammad Bagher Menhaj

GSE-Net: Multi-Scale Feature Extraction for Single-Channel Speech Enhancement

Alireza KayedNezami - Rahil Mahdian Toroghi - Hassan Zareian

An Accelerated Algorithm for Minimum-Time Multi-Agent Motion Planning

الهه نادی - ‌Maryam Babazadeh

Output feedback tube-based MPC for an LPV system using inexact scheduling variables

Nima Naeiji - Ali Akbar Afzalian - Arash Sadeghzadeh

Type-2 Fuzzy Wavelet Control for a Quadruple-Tank System based on Disturbance Rejection

Mohammadreza Esmaeilidehkordi - Alireza Nezamzadeh - Maryam Zekri - Iman Izadi - Farid Sheikholeslam

Design and Determing Two Separate Rotor Axial Flux Permanent Magnet Motor Load and Efficinecy

Siamak Omrani - Ahmad Darabi

Privacy-Preserving Learning using Autoencoder-based Structure

Mohammad Ali Jamshidi - Hadi Veisi - Mohammad Mahdi Mojahedian - Mohammad Reza Aref

The Comparison of MXene and Graphene-Based Antennas for 5G/6G Communications

Javad Shokri Seyyedi - Gholamreza Moradi - Reza Sarraf Shirazi - Sepehr Sahab - Abolfazl Ebrahimpour

بیشتر