Hello all,
I am a new user of Python and Machine learning!
Hereunder, I am trying to explain my data and model and then ask my question.
I have a couple of independent variables: Ambient temperature, Solar intensity, PCM melting temperature (PCM is a kind of material that we glue to the back of the PV panel in this experiment) and, Wind speed. My only dependent variable is the power output of a photovoltaic panel.
All independent variables change during a day (from 8 AM to 5 PM) as "Time" passes. For instance, ambient temperature increases from 8 AM to 3 PM and gradually drops from 3 PM to 5 PM.
My question is: can I consider Time (which is defined in an hour -- e.g. 8,9,....,13,14,....,17) as another independent variable to use machine learning techniques (in Python) like linear regression, Bayesian linear regression and SVM in order to predict the behaviour of the system?
I think because time here shows its effects on temperatures and solar intensity directly, I can disregard "time" as another independent variable.
I am quite confused here. Any help and suggestion would be much appreciated.
Thanks a lot.
Dear Mohammad Rezvanpour
You can check the following website:
https://www.analyticsvidhya.com/blog/2018/09/multivariate-time-series-guide-forecasting-modeling-python-codes/
Dear Mohammad Rezvanpour
I found the below page very useful if you work on Matlab. It's easy to understand
https://au.mathworks.com/help/deeplearning/ug/time-series-forecasting-using-deep-learning.html
Mehdi Neshat
Thank you so much, dear Mehdi.
If you have similar resources using Python, I would be much appreciated it share them with me.
Dear Mohammad Rezvanpour
In your case, the hour of the day, also becomes a dependent variable.
Your reasoning may provide encouraging result.
Please find the relevant link for Python implementation
https://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/
regards,
Depends on your objective: whether you want to predict based on other variables, or time.
Maybe you can consider the recursive least squares algorithm (RLS) which allows for (real-time) dynamical application of least squares (LS) regression to a time series of time-stamped continuously acquired data points. RLS is the recursive application of the well-known LS regression algorithm, so that each new data point is taken in account to modify (correct) a previous estimate of the parameters from some linear (or linearized) correlation thought to model the observed system. For RLS with forgetting factor (RLS-FF), acquired data is weighted according to its age, with increased weight given to the most recent data. This is often convenient for adaptive control and/or real-time optimization purposes.
Application example ― While investigating adaptive control and energetic optimization of aerobic fermenters, I have applied the RLS-FF algorithm to estimate the parameters from the KLa correlation, used to predict the O2 gas-liquid mass-transfer, while giving increased weight to most recent data. Estimates were improved by imposing sinusoidal disturbance to air flow and agitation speed (manipulated variables). The proposed (adaptive) control algorithm compared favourably with PID. Simulations assessed the effect of numerically generated white Gaussian noise (2-sigma truncated) and of first order delay. This investigation was reported at (MSc Thesis):
Thesis Controlo do Oxigénio Dissolvido em Fermentadores para Minimi...
Nice idea Carlos Araújo Queiroz
Dear Mohammad Rezvanpour,
If you could somehow find a correlation based (just an idea) FF for the hours you stated in your question, RLS-FF can solve your concern.
I believe your purpose will also get served.
Regards,
Hi, As far I know, time is an independent variable for all the cases in this area, as it is not dependent on any other parameter, except if you make a condition to outing the time for specific temperature or pressure, for example.
- Badges
- Science topic