Managing Overstaying Electric Vehicles in Park-and-Charge Facilities
Authors: Arpita Biswas, Ragavendran Gopalakrishnan, Partha Dutta
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experimental validation, based on charging data from London, shows that an appropriate penalty can increase both utilization and revenue while significantly reducing overstaying. ... 5 Experimental Results For simulating the behavior of electric vehicles we study real-world data for the city of London |
| Researcher Affiliation | Industry | Arpita Biswas, Ragavendran Gopalakrishnan, Partha Dutta Xerox Research Centre India {Arpita.Biswas, Ragavendran.Gopalakrishnan,Partha.Dutta}@xerox.com |
| Pseudocode | Yes | Algorithm 1 UCB-PC 1: Input: A finite set A of penalty rates 2: TRi stores the total observed revenue for A[i] 3: Ki stores the number of days A[i] is imposed 4: for t 1 to |A| do 5: Choose penalty rate A[t] on tth day; Observe revenue earned r; 6: Set TRt r; Set Kt 1; 7: Find i = arg maxi 8: for t |A| + 1, |A| + 2, . . . do 9: Choose penalty rate A[i ] on tth day; Observe revenue earned r; 10: Update TRi TRi + r; Update Ki Ki + 1; 11: Update ˆ Ri 12: Find i = arg maxi for (t + 1)th day; |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | We study real-world data for the city of London, obtained from [www.gov.uk, 2013], which consists of 9961 charging events, including usage data of charge points and the duration of stay for EVs. |
| Dataset Splits | No | The paper mentions collecting and using data but does not specify dataset splits (e.g., percentages or counts for training, validation, or testing subsets) in the conventional machine learning sense for model training. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments or simulations. |
| Software Dependencies | No | The paper mentions 'Mathematica' for fitting distributions but does not provide a specific version number, nor does it list other software dependencies with version numbers. |
| Experiment Setup | Yes | We assume that the penalty threshold Cmax is a discrete random variable that takes values $4, $8, $10, $20 with probabilities 0.4, 0.3, 0.2, 0.1 respectively. We also assume a linear pricing function during charging, with rate c = $2 per hour. We simulate vehicles arriving to a parking area with 10 charging slots for a 6 hour time period, assuming that the arrivals follow a Poisson distribution with rate 10 per hour. |