User-centric interdependent urban systems: using time-of-day electricity usage data to predict morning roadway congestion

摘要

Urban systems are interdependent as individuals' daily activities engageusing those urban systems at certain time of day and locations. There may existclear spatial and temporal correlations among usage patterns across all urbansystems. This paper explores such a correlation among energy usage and roadwaycongestion. We propose a general framework to predict congestion starting timeand congestion duration in the morning using the time-of-day electricity usedata from anonymous households with no personally identifiable information. Weshow that using time-of-day electricity data from midnight to early morningfrom 322 households in the City of Austin, can make reliable prediction ofcongestion starting time of several highway segments, at the time as early as2am. This predictor significantly outperforms a time-series predictor that usesonly real-time travel time data up to 6am. We found that 8 out of the 10typical electricity use patterns have statistically significant affects onmorning congestion on highways in Austin. Some patterns have negative effects,represented by an early spike of electricity use followed by a drastic dropthat could imply early departure from home. Others have positive effects,represented by a late night spike of electricity use possible implying latenight activities that can lead to late morning departure from home.