Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power

Leva, Sonia; Dolara, Alberto; Grimaccia, Francesco; Mussetta, Marco; Ogliari, Emanuele

doi:10.1016/j.matcom.2015.05.010

Cited by 261 publications

(113 citation statements)

References 18 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…Most of the research about power production forecasts for solar power plants has worked with longer time horizons than what is required for our problem. These predictions often use machine learning methods, such as neural networks, together with past data in form of past weather data [6], numerical weather predictions [7], [8], or satellite images [9]. However, these predictions are not useful to compensate short-term fluctuations.…”

Section: A Related Workmentioning

confidence: 99%

Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy

Spiess

Berkenkamp

Krause

et al. 2019

2019 18th European Control Conference (ECC)

View full text Add to dashboard Cite

The energy output of photovoltaic (PV) power plants depends on the environment and thus fluctuates over time. As a result, PV power can cause instability in the power grid, in particular when increasingly used. Limiting the rate of change of the power output is a common way to mitigate these fluctuations, often with the help of large batteries. A reactive controller that uses these batteries to compensate ramps works in practice, but causes stress on the battery due to a high energy throughput. In this paper, we present a deep learning approach that uses images of the sky to compensate power fluctuations predictively and reduces battery stress. In particular, we show that the optimal control policy can be computed using information that is only available in hindsight. Based on this, we use imitation learning to train a neural network that approximates this hindsight-optimal policy, but uses only currently available sky images and sensor data. We evaluate our method on a large dataset of measurements and images from a real power plant and show that the trained policy reduces stress on the battery.

show abstract

Section: A Related Workmentioning

confidence: 99%

Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy

Spiess

Berkenkamp

Krause

et al. 2019

2019 18th European Control Conference (ECC)

View full text Add to dashboard Cite

show abstract

“…An important issue that arises is how to avoid missing values and outliers. A suitable pre-processing procedure, which has already been developed and described in detail in [39], is applied here.…”

Section: Case Studymentioning

confidence: 99%

Comparison of Training Approaches for Photovoltaic Forecasts by Means of Machine Learning

et al. 2018

Self Cite

View full text Add to dashboard Cite

Abstract:The relevance of forecasting in renewable energy sources (RES) applications is increasing, due to their intrinsic variability. In recent years, several machine learning and hybrid techniques have been employed to perform day-ahead photovoltaic (PV) output power forecasts. In this paper, the authors present a comparison of the artificial neural network's main characteristics used in a hybrid method, focusing in particular on the training approach. In particular, the influence of different data-set composition affecting the forecast outcome have been inspected by increasing the training dataset size and by varying the training and validation shares, in order to assess the most effective training method of this machine learning approach, based on commonly used and a newly-defined performance indexes for the prediction error. The results will be validated over a one-year time range of experimentally measured data. Novel error metrics are proposed and compared with traditional ones, showing the best approach for the different cases of either a newly deployed PV plant or an already-existing PV facility.

show abstract

“…Leva et al [41] in their paper formed ANN for photovoltaic plant energy forecasting and analyzed in term of its sensitivity with respect to the input data sets. The analysis of the results was based on experimental activities carried out on a real photovoltaic power plant accompanied by clear sky model.…”

Section: Literature Reviewmentioning

confidence: 99%

Electrical Characterization of a Photovoltaic Module Through Artificial Neural Network: A Review

Galphade¹

2017

IJECEC

View full text Add to dashboard Cite

show abstract

Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power

Abstract: 7In this paper an artificial neural network for photovoltaic plant energy fore-8 casting is proposed and analyzed in term of its sensitivity with respect to the 9 input data sets.

Cited by 261 publications

References 18 publications

Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy

Learning to Compensate Photovoltaic Power Fluctuations from Images of the Sky by Imitating an Optimal Policy

Comparison of Training Approaches for Photovoltaic Forecasts by Means of Machine Learning

Electrical Characterization of a Photovoltaic Module Through Artificial Neural Network: A Review

Contact Info

Product

Resources

About