Neighbor-Based Optimized Logistic Regression Machine Learning Model For
Electric Vehicle Occupancy Detection
- URL: http://arxiv.org/abs/2204.13702v1
- Date: Thu, 28 Apr 2022 01:05:32 GMT
- Title: Neighbor-Based Optimized Logistic Regression Machine Learning Model For
Electric Vehicle Occupancy Detection
- Authors: Sayan Shaw, Keaton Chia, Jan Kleissl
- Abstract summary: The model was trained on data from 57 EV charging stations around the University of California San Diego campus.
The model achieved an 88.43% average accuracy and 92.23% maximum accuracy in predicting occupancy.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents an optimized logistic regression machine learning model
that predicts the occupancy of an Electric Vehicle (EV) charging station given
the occupancy of neighboring stations. The model was optimized for the time of
day. Trained on data from 57 EV charging stations around the University of
California San Diego campus, the model achieved an 88.43% average accuracy and
92.23% maximum accuracy in predicting occupancy, outperforming a persistence
model benchmark.
Related papers
- Urban Traffic Forecasting with Integrated Travel Time and Data Availability in a Conformal Graph Neural Network Framework [0.6554326244334868]
We propose a novel framework to incorporate travel times between stations into a weighted adjacency matrix of a Graph Neural Network architecture.
To handle uncertainty, we utilize the Adaptive Conformal Prediction (ACP) method that adjusts prediction intervals based on real-time validation residuals.
Experiments show that the proposed model outperformed the next-best model by approximately 24% in MAE and 8% in RMSE.
arXiv Detail & Related papers (2024-07-17T01:11:07Z) - Planning with Adaptive World Models for Autonomous Driving [50.4439896514353]
Motion planners (MPs) are crucial for safe navigation in complex urban environments.
nuPlan, a recently released MP benchmark, addresses this limitation by augmenting real-world driving logs with closed-loop simulation logic.
We present AdaptiveDriver, a model-predictive control (MPC) based planner that unrolls different world models conditioned on BehaviorNet's predictions.
arXiv Detail & Related papers (2024-06-15T18:53:45Z) - Valeo4Cast: A Modular Approach to End-to-End Forecasting [93.86257326005726]
We individually build and train detection, tracking, and forecasting modules.
We then only use consecutive finetuning steps to integrate the modules better and alleviate compounding errors.
Our solution ranks first in the Argoverse 2 end-to-end Forecasting Challenge held at CVPR 2024 Workshop on Autonomous Driving.
arXiv Detail & Related papers (2024-06-12T11:50:51Z) - Reusing Pretrained Models by Multi-linear Operators for Efficient
Training [65.64075958382034]
Training large models from scratch usually costs a substantial amount of resources.
Recent studies such as bert2BERT and LiGO have reused small pretrained models to initialize a large model.
We propose a method that linearly correlates each weight of the target model to all the weights of the pretrained model.
arXiv Detail & Related papers (2023-10-16T06:16:47Z) - Fast-ELECTRA for Efficient Pre-training [83.29484808667532]
ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model.
We propose Fast-ELECTRA, which leverages an existing language model as the auxiliary model.
Our approach rivals the performance of state-of-the-art ELECTRA-style pre-training methods, while significantly eliminating the computation and memory cost brought by the joint training of the auxiliary model.
arXiv Detail & Related papers (2023-10-11T09:55:46Z) - Pre-training on Synthetic Driving Data for Trajectory Prediction [64.16991399882477]
We aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability.
We take advantage of graph representations of HD-map and apply vector transformations to reshape the maps.
We employ a rule-based model to generate trajectories based on augmented scenes.
arXiv Detail & Related papers (2023-09-18T19:49:22Z) - Data-Efficient Modeling for Precise Power Consumption Estimation of
Quadrotor Operations Using Ensemble Learning [3.722516004544342]
Electric Take-Off and Landing (eVTOL) aircraft is considered as the major aircraft type in the emerging urban air mobility.
In this study, a framework for power consumption modeling of eVTOL aircraft was established.
We employed an ensemble learning method, namely stacking, to develop a data-driven model using flight records of three different types of quadrotors.
arXiv Detail & Related papers (2022-05-23T02:16:43Z) - DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with
Gradient-Disentangled Embedding Sharing [117.41016786835452]
This paper presents a new pre-trained language model, DeBERTaV3, which improves the original DeBERTa model.
vanilla embedding sharing in ELECTRA hurts training efficiency and model performance.
We propose a new gradient-disentangled embedding sharing method that avoids the tug-of-war dynamics.
arXiv Detail & Related papers (2021-11-18T06:48:00Z) - Deep Information Fusion for Electric Vehicle Charging Station Occupancy
Forecasting [0.966840768820136]
This paper introduces a novel Deep Fusion of Dynamic and Static Information model (DFDS)
We exploit static information, such as the mean occupation concerning the time of day, to learn the specific charging station patterns.
Our model efficiently fuses dynamic and static information to facilitate accurate forecasting.
arXiv Detail & Related papers (2021-08-27T15:30:45Z) - Multistep Electric Vehicle Charging Station Occupancy Prediction using
Mixed LSTM Neural Networks [1.3706331473063877]
We propose a new mixed long short-term memory neural network incorporating both historical charging state sequences and time-related features for discrete charging occupancy state prediction.
The model is compared to a number of state-of-the-art machine learning and deep learning approaches based on the EV charging data obtained from the open data portal of Dundee, UK.
The results show that the proposed method produces very accurate predictions (99.99% and 81.87% for 1 step (10 minutes) and 6 step (1 hour) ahead, respectively, and outperforms the benchmark approaches significantly.
arXiv Detail & Related papers (2021-06-09T11:10:14Z) - An electric vehicle charging station access equilibrium model with M/D/C
queueing [0.0]
We propose an EV-to-charging station user equilibrium (UE) assignment model with a M/D/C queue approximation as a nondifferentiable nonlinear program.
The model is applied to the large-scale case study of New York City Department of Citywide Administrative Services (NYC DCAS) fleet and EV charging station configuration as of July 8, 2020.
Results suggest a policy based on selecting locations with high utilization ratio instead of with high queue delay.
arXiv Detail & Related papers (2021-02-11T05:23:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.