“It’s an exciting time in the development of connected trucking technology,” says Lloyd Palum, chief technology officer at Vnomics Corp. “Embedded and cloud computing solutions, along with mobile data, are a powerful combination for improving fleet operations.”
Palum, who leads a team of software platform developers at Vnomics, a provider of advanced analytics solutions focused on improving driver and vehicle performance, notes that machine learning and cloud computing capabilities are gaining industry recognition and acceptance for their ability to provide valuable transportation analytics and insights that enable fleets to improve operational efficiencies.
“It is common knowledge to trucking companies that not all routes are equally profitable,” Palum says. “Having analytics to assess true operating costs on a route-by-route basis, and to gather data so pricing models more accurately reflect those operational costs, is a competitive advantage in an industry where margins are tight and competition is high.”
Statistical control
Accurate data from vehicles captured during actual operation is the key to achieving a high level of statistical control when measuring the effects of a given technology or approach on fuel efficiency. To effectively and accurately determine driver fuel efficiency, actual fuel usage should be precisely measured in real time, Palum notes. That actual usage can then be compared to the potential fuel economy the vehicle could achieve under current conditions to provide a normalized metric of fuel use.
“With that level of visibility, fleets can make informed and calculated decisions leading to improved profitability and competitiveness,” Palum says, “but it takes sophisticated vehicle specific learning approaches to rate each driver and vehicle under current operating conditions. With the right data analytics, shortcomings can be eliminated in favor of balanced and normalized scoring that takes into account what minimum fuel usage was possible on a given vehicle, considering all external factors and measuring what was actually achieved in relation to that potential.”
A different approach
Measuring and tracking the actual and potential fuel efficiency of a new technology or operating practice for commercial assets is a different approach to data analytics, Palum points out. To effectively reveal the possible improvement in a vehicle or driver’s performance a process for providing a level of insight that indicates exactly how fuel is used is required.
“This approach is a unique way of measuring fuel use in a mobile asset,” Palum explains further. “Each driver may not drive the same. Loads and routes, along with weather and traffic conditions, may not be the same. Precise vehicle measurement taking into account all of these conditions as they are happening is the key to determining the fuel savings potential for a given technology or operating practice.”
A precise solution for measuring actual fuel economy provides answers to several important questions, Palum relates. These questions include:
• Exactly how much fuel was really used by a driver or vehicle?
• Who are the most efficient drivers and who could benefit from additional training?
• Which are the most efficient and least efficient trucks in the fleet?
• What driver actions and vehicle configurations are the biggest contributors to fuel waste?
• How do new technology additions or operating practices impact fuel performance?
Comprehensive data
“Profitability in transportation is inextricably linked to fuel efficiency,” Palum says. “With a wide and growing range of technologies that promise to improve fuel economy readily available from suppliers, the need for accurate and comprehensive data about their actual performance is essential.
“Fleets that have been able to assess fuel costs on the basis of vehicle parameters, the drivers that are operating them and the routes being run,” Palum concludes, “have insight into which business is profitable and which is not.”