An official website of the United States government
The adoption of battery electric trucks (BETs) as a replacement for diesel trucks has potential to significantly reduce greenhouse gas emissions from the freight transportation sector. However, BETs have shorter driving range and lower payload capacity, which need to be taken into account when dispatching them. This article addresses the energy-efficient dispatching of BET fleets, considering backhauls and time windows. To optimize vehicle utilization, customers are categorized into two groups: linehaul customers requiring deliveries, where the deliveries need to be made following the last-in-first-out principle, and backhaul customers requiring pickups. The objective is to determine a set of energy-efficient routes that integrate both linehaul and backhaul customers while considering factors such as limited driving range, payload capacity of BETs, and the possibility of en route recharging. We formulate the problem as a mixed-integer linear programming model and propose an algorithm that combines adaptive large neighborhood search and simulated annealing metaheuristics to solve it. The effectiveness of the proposed strategy is demonstrated through extensive experiments using a real-world case study from a logistics company in Southern California. The results indicate that the proposed strategy leads to a significant reduction in total energy consumption compared to the baseline strategy, ranging from 11% to 40%, while maintaining reasonable computational time. In addition, the proposed strategy provides solutions that are better than or comparable with those obtained by other metaheuristics. This research contributes to the development of sustainable transportation solutions in the freight sector by providing a novel approach for dispatching BET fleets. The findings emphasize the potential of deploying BETs to achieve energy savings and advance the goal of green logistics.
more »
« less
Comparative Assessment of Machine Learning Techniques for Modeling Energy Consumption of Heavy-Duty Battery Electric Trucks
Efforts to decarbonize the heavy-duty vehicle sector have generated vast interest in transitioning from conventional diesel trucks to battery electric trucks (BETs). As a result, understanding energy consumption characteristics of BETs has become important for a variety of applications, for instance, assessing the feasibility of deploying BETs in place of conventional diesel trucks, predicting the state-of-charge (SOC) of BETs after specific duty cycles, and managing BET charging needs at the home base or en-route. For these applications, mesoscopic energy consumption models offer a good balance between the amount and fidelity of the input data needed, such as average traffic speed and road grade on a link-by-link basis, and the model performance. As a common intelligent transportation system (ITS) application, this paper presents a comparative assessment of mesoscopic energy consumption models for BETs developed using three different machine learning techniques. The results show that the random forest (RF) regression outperforms the extreme gradient boosting (XGBoost), the light gradient boosting machine (LightGBM), as well as the conventional linear regression as evidenced by the resulting model having a higher coefficient of determination (R2) value than that of its counterparts. When applied to the simulated dataset, the RF regression can capture the behaviors of BET energy consumption well where the R2 value of the resulting model is 0.94.
more »
« less
- Award ID(s):
- 2152258
- PAR ID:
- 10511109
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-7066-9
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Location:
- Riverside, CA, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Even though heavy-duty battery electric trucks (BETs) have become commercially available, their range limitation still hinders widespread adoption. Drayage has been regarded as a suitable application for early BETs due to typically having limited daily mileage. However, drayage operation can vary widely and some form of range extension may still be needed for BETs operating in this application. In this paper, wireless charging at port terminals is proposed for this purpose. Potential wireless charging zones at port terminals are identified, and efficacy of wireless charging to extend BET range in drayage operation is verified by simulating the activity of20 BETs from a drayage operator serving the ports of Los Angeles and Long Beach, using a microscopic BET energy consumption model. Furthermore, an optimization problem is formulated for optimal wireless charging zone planning from the port authority's perspective, considering subsets of the identified zones, and charging power options to choose from, for different budget ranges. In this context, zone planning means determining which areas of the port terminals should be selected for installing wireless charging systems, and what level of charging power should be for each selected zone's system. For each budget range, the optimization problem is solved using genetic algorithm to determine an optimal zone plan that provides the maximum amount of energy through wireless charging per unit cost of installation. The results show that wireless charging can aid improving activity completion of the simulated fleet by 5%, and further optimizing the zone plan can achieve similar performance with lower cost.more » « less
-
The emergence of battery electric trucks (BETs) in recent years has shown great promise in reducing greenhouse gas (GHG) emissions in urban freight logistics. However, designing a customer-oriented dispatching strategy for a BET fleet is more complex than traditional vehicle routing problems (VRP) due to several constraints, such as limited driving range, potential need for en route recharging, and long recharging times. Also, in practice, the uncertain travel times in urban transportation network may lead to the violation of scheduled customer time windows and impact overall energy consumption. To better utilize the BET fleet, this paper introduces a robust BET dispatching problem with backhauls and time windows under travel time uncertainty, which aims to minimize the overall fleet energy consumption while also minimizing the risk of violating customer time window. A mathematical optimization model based on novel route-related sets is developed, and an adaptive large neighborhood search (ALNS) metaheuristic algorithm is used to find robust dispatching solutions. Based on real-world data from a truck fleet in San Bernardino County, California, a simulation study is conducted to demonstrate the robustness of the solutions obtained by the proposed method. Moreover, a sensitivity analysis with respect to uncertainty parameters is performed to assess the trade-off between the overall fleet energy consumption and the robustness of the solutions.more » « less
-
Given the urgency of climate change, development of fast and reliable methods is essential to understand urban building energy use in the sector that accounts for 40% of total energy use in USA. Although machine learning (ML) methods may offer promise and are less difficult to develop, discrepancy in methods, results, and recommendations have emerged that requires attention. Existing research also shows inconsistencies related to integrating climate change models into energy modeling. To address these challenges, four models: random forest (RF), extreme gradient boosting (XGBoost), single regression tree, and multiple linear regression (MLR), were developed using the Commercial Building Energy Consumption Survey dataset to predict energy use intensity (EUI) under projected heating and cooling degree days by the Intergovernmental Panel on Climate Change (IPCC) across the USA during the 21st century. The RF model provided better performance and reduced the mean absolute error by 4%, 11%, and 12% compared to XGBoost, single regression tree, and MLR, respectively. Moreover, using the RF model for climate change analysis showed that office buildings’ EUI will increase between 8.9% to 63.1% compared to 2012 baseline for different geographic regions between 2030 and 2080. One region is projected to experience an EUI reduction of almost 1.5%. Finally, good data enhance the predicting ability of ML therefore, comprehensive regional building datasets are crucial to assess counteraction of building energy use in the face of climate change at finer spatial scale.more » « less
-
The abundant availability of crop waste and forestry residues in Texas provides great potential for producing renewable diesel in the local towns of Texas. This study aims to evaluate the environmental impacts of renewable diesel use in Texas transportation and the potential of renewable diesel production in Texas. The GREET model was used to customize the life cycle pathway of renewable diesel and evaluate its environmental impacts. The models of renewable diesel produced from forestry residue and corn stover were built to calculate life cycle gas emissions of combination short-haul heavy-duty trucks fueled with renewable diesel. Life cycle GHG emissions of renewable diesel are much lower than those of low-sulfur diesel. However, with respect to renewable diesel derived from corn stover, life cycle PM10 and PM2.5 emissions were almost double those of low-sulfur diesel in 2024, and both emissions will be reduced by 37–38% in 2035. The life cycle emission trends of SOx, black carbon, and primary organic carbon are very similar to those of PM10 and PM2.5. The total cost of ownership (TCO) of heavy-duty trucks using renewable diesel produced from forestry residues or corn stover would be 10.3–14.8% higher than those consuming regular low-sulfur diesel in Texas.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/FISTS60717.2024.10485539
