Prediction-Based Time-Dependent Smart Data Pricing and its Application to Price-Oriented Scheduling

• Main Authors: Fang-Ying Liao, 廖芳瑩
• Other Authors: 鐘嘉德
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/rzb7v4

碩士 === 國立臺灣大學 === 電信工程學研究所 === 106 === Internet Service Providers (ISPs) adopt Time-Dependent SDP (TDP) to motivate users to change their Internet access behavior from peak hours to off-peak hours. In previous work, future network status was affected by assuming user''s Internet access behavior. They assume that any behavior can be postponed due to prices. In the real situation, real-time applications cannot be delayed, and non real-time applications can be delayed. Therefore, we propose prediction-based TDP which is the combination of the prediction mechanism and TDP. We predict real-time Internet usage in the future, and apply TDP to decide prices for non real-time Internet based on predicted values. Considering the adaptation issue for users, we propose a scheduling application. According to prices and user''s waiting time, the application provides users with suggestions about when to access Internet, so that users can pay less for non real-time Internet usage.