Enterprise motor carriers operating 250+ power units face increasing pressure to extract maximum utilization from assets while maintaining service levels. This installment of the Applied AI for Enterprise Motor Carriers Systems Playbook examines the integration of real-time telematics ingestion, mixed-integer linear programming (MILP) for dispatch optimization, and automated straight-through billing pipelines. These three capabilities form the technical core of modern carrier operations platforms.
Strong Tower Consulting has guided numerous asset-based carriers through the design and implementation of these systems since our founding in Minnesota in 2008 by Scott Elliott. The architectures presented here are derived from production environments running Truckmate, McLeod, and TMW Suites, integrated with ELD providers, fuel card platforms, and EDI transaction sets.
Real-Time Telematics Ingestion Architecture
Modern carrier systems require sub-minute ingestion of GPS, engine telemetry, and driver status events. A robust pipeline begins with an event-driven streaming platform capable of handling 10,000+ events per second across a national fleet.
The reference architecture uses Apache Kafka as the backbone, with dedicated topics for each ELD vendor (e.g., eld-samsara, eld-omnitracs, eld-keeptruckin). A fleet of containerized microservices performs initial validation, enrichment with static master data (driver, tractor, trailer), and writes to both an operational data store and a time-series database optimized for spatial-temporal queries.
Key SQL Server schema components include:
TelematicsRaw- landing table for unprocessed payloadsTelematicsEvents- normalized fact table with geometry datatype for locationAssetStatus- current state materialized view updated via triggers
MILP Dispatch Optimization Engine
Dispatch optimization for enterprise carriers is fundamentally a vehicle routing problem with time windows (VRPTW) subject to hours-of-service constraints, equipment compatibility, and driver preferences. We formulate this as a mixed-integer linear program solved nightly and re-optimized in real time as exceptions occur.
The objective function minimizes total cost:
Minimize: ∑(c_travel * x_ij + c_detention * d_k + c_fuel * f_ij) + penalty terms for service failures
Decision variables include binary assignment of loads to driver-tractor combinations and continuous variables for arrival times. Constraints incorporate:
- EDI 204 load acceptance and tender details
- Driver HOS remaining time derived from telematics
- Compatible equipment matching via carrier rate matrix rules
- Fuel surcharge calculations based on current diesel prices and route
Solvers such as Gurobi or CPLEX are called via a .NET service layer. For carriers running McLeod or TMW, the optimized plan is written back to the dispatch board through published APIs or direct database updates to the load and driver tables.
Straight-Through Billing Pipeline
Exception-based billing represents one of the highest-ROI automation opportunities. The straight-through processing (STP) pipeline ingests EDI 214 status updates, cross-references them with telematics stop events, calculates accessorials (detention, layover, fuel surcharges), and generates EDI 210 invoices without human touch.
| Carrier Type | Power Units | Monthly Loads | Touchless % | Avg Days to Invoice |
|---|---|---|---|---|
| Regional Dry Van | 275 | 4,800 | 68% | 2.4 |
| National Reefer | 620 | 11,200 | 57% | 3.1 |
| Flatbed / Specialized | 410 | 6,900 | 49% | 4.7 |
The pipeline applies business rules for fuel surcharge recovery, lumper fees, and detention based on validated stop duration from telematics. When exceptions are detected (missing status, disputed detention time), the load is routed to an exception queue with full context for rapid resolution. Approved invoices flow directly to the accounting system via transportation accounting integration.
Exception Management and Event Streaming
Real-time exception management ties the three pillars together. A complex event processing (CEP) engine monitors the telematics and EDI streams for conditions such as:
- Arrival more than 30 minutes outside the appointment window
- HOS violation risk within next 90 minutes
- Missing EDI 214 after confirmed GPS arrival
When triggered, the system can automatically re-run a constrained MILP optimization for affected loads or create a driver settlement adjustment for detention. All actions are logged with full audit trail for both operational visibility and driver settlement reconciliation.
Implementation Roadmap for Enterprise Carriers
Carriers should approach these capabilities in three phases:
- Foundation: Unified telematics ingestion and normalized operational data store
- Optimization: MILP dispatch engine with nightly batch and real-time re-optimization
- Automation: Straight-through billing with exception management and full EDI 204/214/210 lifecycle
Each phase delivers measurable ROI. Telematics normalization alone typically improves asset utilization by 4-7%. MILP optimization routinely adds 6-11% to loaded miles. Straight-through billing reduces DSO by 8-14 days while cutting billing labor by more than half.
Frequently Asked Questions
How do you integrate telematics from multiple ELD providers into a single Truckmate or McLeod instance?
We deploy a vendor-agnostic ingestion service that normalizes all incoming payloads to a common schema before writing to the TMS. This includes mapping location events to the McLeod stop table and driver status to the dispatch board. The architecture maintains a master lookup of equipment and driver identifiers across all systems.
What solver and hardware configuration is required for MILP dispatch optimization on a 600-truck fleet?
For nightly optimization of 600+ trucks and 1,200+ loads, a Gurobi solver running on a dedicated 16-core server with 64GB RAM typically completes in under 12 minutes. Real-time re-optimization for exceptions uses a warm-start feature and completes in 30-90 seconds. We have also successfully used open-source CBC for smaller fleets.
How does the straight-through billing pipeline handle fuel surcharge and detention calculations?
The pipeline joins real-time telematics stop duration with the carrier rate matrix stored in SQL. Fuel surcharges are calculated using the U.S. national average diesel price updated daily and the specific fuel table attached to each customer. Detention is computed from arrival and departure events, applying free time and rate tiers defined in the tariff engine.
Can this architecture support both company drivers and owner-operators with escrow settlement?
Yes. The driver settlement and escrow accounting engine is designed to handle both payroll for company drivers and per-load settlements for owner-operators. The system automatically generates settlement statements that incorporate line-haul, fuel surcharge, accessorials, and escrow deductions based on the same validated telematics and EDI data used for customer billing.
Strong Tower Consulting, LLC and Exspeedite LLC are separately organized sister companies under common ownership. Our independent systems architecture and technology advisory services help motor carriers design and implement these advanced capabilities without vendor lock-in.
Get a Systems AssessmentCall 763-244-1373 to speak with our team.