Real-Time Predictive Optimization for Energy Management in a Hybrid Electric Vehicle

Authors: Alexander Styler, Illah Nourbakhsh

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this work, we propose and evaluate a novel, real-time optimization strategy that leverages predictions from prior data in a simulated hybrid battery-supercapacitor energy management task. [...] Using thousands of miles of real-world data collected from both petrol and electric vehicles, we evaluate the performance of our optimization strategy with respect to our cost function. [...] We test performance on a simulated prototype hybrid electric vehicle (EV), using real-world power data from drivers.
Researcher Affiliation Academia The provided text for analysis does not explicitly state the institutional affiliations for the authors Alexander Styler and Illah Nourbakhsh. Only their names are listed. The acknowledgments section mentions various organizations (BMW, Bosch, Bombardier, Google, Charge Car team, CREATE Lab), but these are not stated as the authors' affiliations.
Pseudocode Yes The paper includes a clearly labeled algorithm block: 'Algorithm 1 High-Level Control Algorithm.'
Open Source Code No The paper does not provide any explicit statements about releasing source code for the methodology described, nor does it include links to a code repository.
Open Datasets Yes The paper states: 'Validation and explanation of this model and data can be found in our previous work (Styler et al. 2011).' This provides a formal citation to the dataset's origin and details.
Dataset Splits Yes The paper explicitly states the use of cross-validation: 'The performance results shown so far were calculated using a batch leave-one-out cross validation (LOOCV) test. For each trip tested, every other trip in the dataset is used as training data.'
Hardware Specification No The paper mentions that the approach 'can be done faster than real-time on even modest hardware' but does not provide any specific details about the CPU, GPU, or other hardware used for running the experiments or simulations.
Software Dependencies No The paper describes the algorithms and their implementation conceptually but does not provide specific version numbers for any software dependencies, programming languages, or libraries used for the experiments.
Experiment Setup Yes The paper provides specific experimental setup details, including: 'The frequency of control decisions for the simulation is set to 1Hz', the 'fixed 50Wh capacitor size' for initial tests and 'fixed k = 7' for sensitivity analysis, the features used for prediction ('GPS Bearing Time Day Speed Acceleration Energy Used'), and the specific cost function 'c(x, u, t) = u^2 / V_t^2'.