Optimal Electric Vehicle Charging Station Placement

Authors: Yanhai Xiong, Jiarui Gan, Bo An, Chunyan Miao, Ana L. C. Bazzan

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that the proposed algorithms significantly outperform baseline methods. In this section, we run experiments on the real data set from Singapore to evaluate our approach.
Researcher Affiliation Academia Yanhai Xiong1, Jiarui Gan2,3, Bo An4, Chunyan Miao4, Ana L. C. Bazzan5 1Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly, NTU, Singapore 2The Key Lab of Intelligent Information Processing, ICT, CAS 3University of Chinese Academy of Sciences, Beijing, China 4School of Computer Engineering, Nanyang Technological University, Singapore 5Universidade Federal do Rio Grande do Sul, Brazil 1,4{yxiong003, boan, ascymiao}@ntu.edu.sg,2ganjr@ics.ict.ac.cn,5bazzan@inf.ufrgs.br
Pseudocode Yes Algorithm 1: OCEAN-C 1 Relax x to be continuous; 2 Solve optimal solution x of P3; 3 bx rounded x ; 4 Compute the optimal solution Obj of P3 with x set as bx; 5 return Obj, bx;
Open Source Code No The paper does not provide any statement or link indicating that the source code for the methodology is openly available.
Open Datasets No The paper describes the creation of a 'real data set from Singapore' by dividing Singapore into zones and estimating parameters based on LTA and DOS statistics, Google Maps, etc. However, it does not provide concrete access information (e.g., a specific link, DOI, or a recognized public dataset name with citation for direct download) for this constructed dataset.
Dataset Splits No The paper does not specify training, validation, or test dataset splits. The problem is formulated as an optimization problem evaluated on a single dataset, not a typical machine learning task with explicit data partitioning for training, validation, and testing.
Hardware Specification Yes all experiments were run on the same data set using a 3.4GHz Intel processor with 16GB of RAM
Software Dependencies Yes employing KNITRO (version 8.0.0) for nonlinear programs.
Experiment Setup Yes Serving rate of chargers is set as µ = 6 and the proportion of EVs that charge during peak hours is set as 1/τ = 1/10. The linear coefficient λ is fixed at 0.2. Unless otherwise mentioned, the above parameters are fixed in all our experiments. Budget is set as 300. The results were averaged over 20 trials. We assume that their charging strategies vary by 10%, i.e., pij ± 10%.