Bandwidth Allocation Based on Personality Traits on Smartphone Usage and Channel Condition

Abstract

How to allocate resources in the era of Big Data in telecommunications becomes a new issue. Smartphone data could be a function of personality, as the smartphone supports interpersonal interaction, and the data collected from the smartphone usage often contains rich customer opinion and behavioral information. A bandwidth allocation method based on smartphone users' personality traits and channel condition is studied in a unified mathematical framework in this paper. Personalizing bandwidth allocation could be done by analyzing smartphone users' personality traits, resulting in business intelligence, a smarter and more efficient usage of the limited bandwidth, while taking channel fading conditions into account. Using the diagnostic inference, the service provider could calculate the user's probability of having each personality trait stand on its data usage. One step further, its bandwidth usage of the following period can be predicted using predictive inference. For our proposed bandwidth allocation scheme, both the outage capacity and outage probability are studied in fading channel. Therefore, the service providers shall better allocate the limited bandwidth, provide more personal service to each user, and adjust the bandwidth allocation further on account of the real channel condition.