In one of my jobs early in my supply chain analytics career, I did a rotation in Transportation planning and analytics for a leading workspace solutions manufacturer. The project I was assigned to pertained to optimizing inbound shipments from suppliers who were within trucking distance from our manufacturing plants. One key lever of this initiative was Transportation route optimization.
Many of our raw material suppliers were shipping small volume (2-3 pallets) frequently to our plants, leveraging modes like LTL, expedited cargo etc. so the idea was to plan these inbound as multi stop FTLs, thereby cutting the inbound logistics cost significantly. As you can assume, the key lever in this entire plan/architecture was Transportation route optimization.
The outcome: Resistance to change led to slow and difficult implementation
The year was 2008 and the American economy had just hit the trough of recession. If you can recall, the Manufacturing sector in MidWest was hard hit. Companies were laying off in numbers, across departments. It was a difficult year and any efficiency improvement initiative focused on manufacturing or transportation was being viewed as an effort towards workforce reduction.
One of the biggest challenge with the conventional approach of transportation optimization is that for drivers and fleet manager, who are averse to change, it is easy to blow holes in the solution.
A traditional fleet or route optimization solution incorporates few basic inputs only in the optimization process and creates routes based on those criteria. While those aspects are absolutely essential inputs for route or fleet optimization, unfortunately, the world is not Black or White. There are multitude of factors that may impact daily routes of your fleet that are not incorporated in classic route optimization solutions.
When we started the implementation pilot for the program, looking at the GPS data, we were able to see that majority of drivers were not following the prescribed routes. We started interviewing these drivers on a daily basis and received inputs like:
(1) Supplier not ready when they get there, leading to delay and that forced them to skip few pickups.
(2) The pickup details specific to dimensions were not provided accurately by the supplier (ex: Supplier had 4 pallets instead of 2 entered on the portal)
(3) Traffic events
(4) Vehicle breakdowns
(5) Weather related issues
(6) Last minute or urgent pickup requests that drivers need to accommodate. In such circumstances, drivers were using their own tribal knowledge to accommodate those on their route. This accommodation however is not always optimal.
What we could have done better during the planning and/or implementation? Answer is -Nothing. This is precisely the reason why I am not an advocate of a majority of popular off the shelf VRP tools out there in the market. There are so few input variables in these tools and the architecture, as shown below, does not allow for the possibility of incorporating some of the issues identified above.
Are these off the shelf solutions useful at all?
Yes they are, but in my mind, only for strategic level analysis. These solutions may be good for initiatives like fleet optimization, driver headcount reduction, transportation network optimization, or to do a high level evaluation of the impact of network redesign on last mile transportation. However, as far as periodic route optimization goes, my suggestion will be to leverage a customized solution, if you have the resources to do so. I find it very frustrating when I see companies leveraging an off the shelf tool for periodic route optimization in today’s age of big data .
What will a customized solution look like though?
The Big data age solution: Intelligent dynamic route optimization
The IoT era allows us to harness real data data generated by various sources and this data combined with other real time data points related to traffic, weather, customer preferences etc. can allow creation of dynamic routes-routes that evolve in real time and optimize as the real time data comes into the system. An example is shown in the illustration below-a last minute urgent pickup request comes in and the ML algorithm recalculates the route.
Computing power, availability of data and connectivity technologies have opened door for developing Intelligent route optimization solutions. At a very high level, this solutions are created pairing real time data generated from various sources with machine learning to optimize routes in real time. Examples of data points that the ML algorithm can look at are truck speed, GPS location, route traffic, weather, destination, customer requests for changes to delivery time etc. The key aspects of a solution like this will be:
- Self learning system
- Optimal fleet selection
- Optimal delivery assignments powered by artificial intelligence
- Considers real-world and on the ground fuziness
- On the road driver app
The overall impact of optimizing delivery routes can transform your business and help manage them efficiently with complete transparency. Prominent benefits of intelligent route optimization are –
- Boost in delivery efficiency with increased rider productivity
- Reduced fuel consumption through overall reduction in delivery transit
- Maximum vehicle utilization for efficient long-haul FTL/LTL dispatches across primary & secondary leg of supply chain
- Dynamic route clusters with minimal overlaps
- Supplanting manual decision making for assigning delivery routes leading to reduced errors
- Multiple delivery plans in a single master plan with flexible time slots (breaks for lunch etc)