An Estimated-Travel-Time Data Scraping and Analysis Framework for Time-Dependent Route Planning

Generally, a courier company needs to employ fleet of vehicles travel through number locations in order provide efficient parcel delivery services. The route planning these can be formulated as vehicle routing problem (VRP). Most existing VRP algorithms assume that the traveling durations between are time invariant; thus, they normally use only set estimated times (ETTs) plan vehicles’ routes; however, this is not realistic because traffic pattern city varies over time. One solution tackle different sets ETTs for periods, and data collectively called time-dependent (TD-ETTs). This paper focuses on low-cost robust effectively scrape, process, clean, analyze TD-ETT from free web-mapping services gain knowledge periods. To achieve abovementioned goal, our proposed framework contains four phases, namely, (i) Full Data Scraping, (ii) Pre-Processing Analysis, (iii) Fast (iv) Patching Maintenance. In experiment, we used above obtain across 68 Penang, Malaysia, six months. We then fed algorithm evaluation. found performance approach comparable with using expensive paid data.