Adaptive in-drive updating of vehicle energy consumption prediction
A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller adapted to obtain a pre-drive energy consumption prediction for the route, via an energy consumption predictor. An in-drive updating module is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed. The controller is adapted to obtain an actual energy consumption for segments in the completed portion of the route. The controller is adapted to obtain at least one modification factor based on a comparison of the actual energy consumption and the pre-drive energy consumption prediction for the segments in the completed portion of the route. The pre-drive energy consumption prediction for the remaining portion of the route is adjusted based on the modification factor.
1. A system for adaptive in-drive updating for a vehicle travelling on a route, the system comprising:
a controller adapted to obtain a pre-drive energy consumption prediction for the route via an energy consumption predictor, the controller having a processor and tangible, non-transitory memory;
an in-drive updating module selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed, the route being divided into a number of segments, execution of the in-drive updating module causing the controller to:
obtain an actual energy consumption for the segments in the completed portion of the route;
obtain at least one modification factor based in part on a damping coefficient, a respective weighting factor for the segments, a sum of the actual energy consumption in the segments, and the sum of the pre-drive energy consumption prediction for the segments in the completed portion of the route, the respective weighting factor being between zero and one, inclusive; and
adjust the pre-drive energy consumption prediction for the segments in the remaining portion of the route based on the at least one modification factor, including multiplying the at least one modification factor by the pre-drive energy consumption prediction for the segments in the remaining portion;
wherein the at least one modification factor (Mi) is applied at an ith segment at a beginning of the remaining portion and obtained as:
Mi
=
[
d
+
∑
j
=
1
i
w_ja
_j
]
[
d
+
∑
j
=
1
i
w_jp
_j
]
,
where d is the damping coefficient, w_j is the respective weighting factor, a_j is the actual energy consumption in one of the segments of the completed portion and p_j is the pre-drive energy consumption prediction in one of the segments of the completed portion; and
wherein operation of the vehicle on the remaining portion of the route is modified based on the adjusted pre-drive energy consumption prediction for the segments in the remaining portion of the route.
2. The system of claim 1 , wherein the in-drive updating module incorporates a machine learning model to adjust the pre-drive energy consumption prediction.
3. The system of claim 1 , wherein adjusting the pre-drive energy consumption prediction includes adding the at least one modification factor to the pre-drive energy consumption prediction for the segments in the remaining portion.
4. The system of claim 1 , wherein the controller is programmed to update the pre-drive energy consumption prediction in a future segment in the remaining portion of the route based on similarity of a characteristic feature in the future segment to the characteristic feature in a past segment in the completed portion.
5. The system of claim 4 , wherein the characteristic feature is a speed of the vehicle.
6. The system of claim 4 , wherein the characteristic feature is a geographical classification of the route.
7. The system of claim 1 , wherein the energy consumption predictor incorporates multiple modules, and the controller is programmed to sequentially update the multiple modules.
8. The system of claim 7 , wherein the multiple modules include a speed prediction module, a driving consumption prediction module and an HVAC consumption prediction module.
9. A method of adaptive in-drive updating for a vehicle travelling on a route divided into a number of segments, the vehicle having a controller with a processor and tangible, non-transitory memory, the method comprising:
obtaining a pre-drive energy consumption prediction for the segments in the route, via an energy consumption predictor;
executing an in-drive updating module, via the controller, at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed;
obtaining an actual energy consumption for the segments in the completed portion of the route;
obtaining at least one modification factor based in part on a damping coefficient, a respective weighting factor for the segments, a sum of the actual energy consumption and the pre-drive energy consumption prediction for the segments in the completed portion of the route, via the controller, the respective weighting factor being between zero and one, inclusive; and
adjusting the pre-drive energy consumption prediction for the segments in the remaining portion of the route based on the at least one modification factor, including multiplying the at least one modification factor by the pre-drive energy consumption prediction for the segments in the remaining portion;
applying the at least one modification factor (Mi) at an ith segment at a beginning of the remaining portion such that
Mi
=
[
d
+
∑
j
=
1
i
w_j
a_j
]
[
d
+
∑
j
=
1
i
w_j
p_j
]
,
where d is the damping coefficient, w_j is the respective weighting factor, a_j is the actual energy consumption in one of the segments of the completed portion and p_j is the pre-drive energy consumption prediction in one of the segments of the completed portion; and
controlling operation of the vehicle on the remaining portion of the route based on the adjusted pre-drive energy consumption prediction for the segments in the remaining portion of the route.
10. The method of claim 9 , further comprising:
incorporating a machine learning model in the in-drive updating module to adjust the pre-drive energy consumption prediction.
11. The method of claim 9 , further comprising:
updating the pre-drive energy consumption prediction in a future segment in the remaining portion of the route based on similarity of a characteristic feature in the future segment to a past segment in the completed portion.