Towards Optimal Solar Tracking: A Dynamic Programming Approach
Authors: Athanasios Aris Panagopoulos, Georgios Chalkiadakis, Nicholas Jennings
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our simulations show that the proposed methods can increase the power output of a PVS considerably, when compared to standard solar tracking techniques. The evaluation results of the experiments are collectively reported in Table 1. |
| Researcher Affiliation | Academia | Athanasios Aris Panagopoulos Georgios Chalkiadakis Nicholas R. Jennings Electronics and Computer Science, Electronic and Computer Engineering, Electronics and Computer Science, University of Southampton, UK Technical University of Crete, Greece University of Southampton, UK |
| Pseudocode | Yes | Algorithm 1 Alternating Policy Iteration for ST and Algorithm 2 Slope Policy Iteration |
| Open Source Code | No | The paper mentions a web tool RENES (www.intelligence.tuc.gr/renes) which is used in their work, but it does not state that the code for the proposed STPI method or other techniques described in this paper is publicly available, nor does it provide a link to such code. |
| Open Datasets | Yes | For the purposes of our research, archival weather data was accumulated from the weather underground website (www.wunderground.com) regarding four different days at our location of interest. Specifically, we accumulated archival weather data for the 20/03/2011 equinox, the 22/09/2012 equinox, the solstice of 21/06/2012, and the solstice of 21/12/2008. |
| Dataset Splits | No | The paper describes using archival weather data and fictional data for simulations, but it does not specify any training, validation, or test dataset splits in the context of model training or evaluation, as typically seen in machine learning experiments. |
| Hardware Specification | No | The paper specifies details of the simulated photovoltaic system (e.g., 'typical 72m2 system', 'system weight was set to 2500kg'), but it does not provide any specific details about the computer hardware (e.g., CPU, GPU models, memory) used to run the simulations or experiments. |
| Software Dependencies | No | The paper does not provide specific details about ancillary software, such as programming languages, libraries, frameworks, or solvers, along with their version numbers, that would be necessary to replicate the experiments. |
| Experiment Setup | Yes | We modeled a typical 72m2 system (i.e., w = 6.0m, l = 12.0m, d = 0.20m) with 270 of azimuthal motion range, and 63 of elevation motion range. The system weight was set to 2500kg. The modeled system was limited to provide a step-size of θ = 1.8 at each axis... The time δ required for a minimum displacement θ to occur, was set to 1s, and the interval between two consecutive controller interactions was set to = 5min. As the efficiency of the motors and gears depends on the speed and load at all times (Burt et al. 2008), we used a mean efficiency of 30% for both... |