Loading...
Please wait, while we are loading the content...
Enabling Eco-Routing in Transportation via Spatial Big Data
| Content Provider | Semantic Scholar |
|---|---|
| Author | Evans, Michael R. |
| Copyright Year | 2012 |
| Abstract | Research Overview & Potential Significance: My research is broadly the area of spatial computing: finding interesting patterns in geospatial datasets such as satellite imagery, climate data or GPS tracking data [9]. One subfield of spatial computing is routing and navigation services, examples including Google Maps and the Global Positioning System (GPS), technology that society already benefits from immensely. Scientists use GPS to track endangered species to better understand behavior, and farmers use GPS for precision agriculture to increase crop yields while reducing costs. We've reached the point where a hiker in Germany, a biker in Minneapolis, and a taxi driver in Manhattan know precisely where they are, their nearby points of interest, and how to reach their destinations. My work is focused on building a representative model to characterize how individuals move about their day, incorporating information such as routine traffic patterns. The focus is not on dense or frequent patterns, but routine patterns (schedules and routes) of individuals to help suggest better alternatives based on some criteria (e.g., fuel savings). Instead of simply identifying congested routes, we can suggest departure times for a person's favorite routes to work to reduce the chances they hit traffic, and therefore reducing gas consumption via idling. Increasingly, however, the size, variety, and update rate of datasets exceed the capacity of commonly used spatial computing and spatial database technologies to learn, manage, and process the data with reasonable effort. Such data is known as Spatial Big Data (SBD). I believe that harnessing SBD represents the next generation of routing services. SBD has transformative potential. A 2011 McKinsey Global Institute report estimates savings of “about $600 billion annually by 2020” in terms of fuel and time saved [8] by helping vehicles avoid congestion and reduce idling at red lights or left turns. Preliminary evidence for the transformative potential includes the experience of UPS, which saves millions of gallons of fuel by simply avoiding left turns when selecting routes [7]. In recent years, consumer GPS products have been evaluating the potential of this approach via these simple consumptionreduction techniques. Immense savings in fuel-cost and greenhouse gas (GHG) emissions are possible if other fleet owners and consumers avoided left-turns and hot spots of idling, low fuel-efficiency, and congestion. Finding these hot spots of idling and congestion requires new approaches and methods beyond simply reducing left-hand turns. My research is motivated by 'eco-routing': identifying routes which reduce fuel consumption and GHG emissions as compared to traditional routing services (e.g., Google Maps) which reduce total distance driven or time spent driving. It has the potential to significantly reduce US consumption of petroleum, the dominant source of energy for transportation. It may even reduce the gap between domestic petroleum consumption and production, helping bring the nation closer to the goal of energy independence. I began my research in 2010 with my first publication on storing spatio-temporal networks in database systems [3]. Spatio-temporal networks are specialized graphs that model road networks and the connections between locations with travel times (e.g., locations are represented as nodes in the graph, and they are connected by lines (edges) indicating how |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.spatial.cs.umn.edu/eco-routing/files/evans_ddf.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
