Forecasting Solar Power Generation Using Fuzzy Logic

Electrical Electronics Engineering

Forecasting solar power generation using fuzzy logic involves employing a computational approach that leverages fuzzy set theory to model and predict solar energy output. Fuzzy logic, a mathematical framework for dealing with uncertainty, allows for the creation of models that can accommodate the various factors influencing solar power generation, such as weather conditions, time of day, and geographical location. By integrating fuzzy logic into forecasting methodologies, analysts can develop more robust and adaptable models capable of capturing the intricate relationships between input variables and solar energy production. This approach facilitates the optimization of solar power utilization, aiding in efficient resource management and enhancing the reliability of renewable energy systems in diverse environmental contexts.

ABSTRACT

Accurate forecasting of solar resource is a key issue for a successful integration of the solar power plants into the grid. This paper proposes the fuzzy logic approach as alternative to classical statistics, aiming to forecast hourly global solar irradiation. Hourly clearness index, defined as the ratio of hourly global solar irradiation at the ground and at the top of the atmosphere, is the quantity directly processed by the fuzzy algorithms. It takes into account all random meteorological influences, being a measure of the atmospheric transparency. Thus, clearness index isolates the stochastic component of the solar irradiation data series. Four new autoregressive-fuzzy models are studied in this paper. The models are mainly differentiated by the number of the input variables and attributes. The results show that a model which includes seasonal terms is the most performing. The model can be applied in sites where measurement of hourly global solar irradiation is currently performed, only a re-estimation of the parameters being necessary. Overall results demonstrate that the fuzzy models have the strength to translate the information enclosed in past measurements into an actual prediction with acceptable accuracy

TABLE OF CONTENTS

COVER PAGE

TITLE PAGE

APPROVAL PAGE

DEDICATION

ACKNOWLEDGEMENT

ABSTRACT

CHAPTER ONE

INTRODUCTION

1.1 BACKGROUND OF THE STUDY

PROBLEM STATEMENT
AIM AND OBJECTIVE OF THE STUDY
SCOPE OF THE STUDY
SIGNIFICANCE OF THE STUDY

CHAPTER TWO

LITERATURE REVIEW

OVERVIEW OF SOLAR POWER
REVIEW OF THE STUDY
PV POWER FORECASTING SPATIAL AND TIME HORIZONS
THE SPATIAL SCALE FOR PV POWER FORECASTING
PV POWER FORECASTING APPROACHES AND METHODS
REVIEW OF RELATED STUDIES

CHAPTER THREE

METHODOLOGY

STUDY OF AREA
RESEARCH DESIGN
INSTRUMENT USED
FUZZY ALGORITHM FORMATION

CHAPTER FOUR

4.0 RESULTS AND DISCUSSION

RESULT
DISCUSSION

CHAPTER FIVE

CONCLUSION

REFERENCES

CHAPTER ONE

1.0 INTRODUCTION

1.1 BACKGROUND OF THE STUDY

The weight of solar electricity in the energy mix experienced an impressive augment in the last decade, and this trend is expected to continue. To date, there are two challenges standing against the growing share of PV systems in the energy mix. The first challenge refers to the price of the electricity which is still high in comparison to that of power plants based on fossil fuels. Many efforts are spent all over the world to reduce the costs associated to solar electricity production. The second challenge stems from the intrinsic nature of solar energy which is stochastic fluctuating in time owing to irregular weather pattern. Therefore, in order to reduce the costs of integrating the solar plants in the existing power grid, forecasting the energy generated by the solar plants is a key issue. Currently, there are several ongoing research projects in the world, testing different procedures for accurately forecast the PV output power. For example, COST Action ES1002 “Weather Intelligence for Renewable Energies” has the main objective to improve the forecast of the output power of solar power plants [Lee et al, 2017].

There are two methods currently used to perform the forecast: (1) Statistical modeling of the PV plant output power time series and (2) Modeling the output power, using as entries forecasts of radiometric quantities (solar irradiance/irradiation) and weather parameters (air temperature, cloud cover).

The accuracy of forecasting the output power of a solar plant is closely related to the accuracy of forecasting of solar resource. Depending on the time horizon, different forecasting methods are considered [Antonanzas et al, 2016]. In nowcasting (horizon time less than 3 hours) the forecasts are based on the extrapolations of real-time measurements [Antonanzas et al, 2016]. The most popular methods are: Autoregressive Integrated Moving Average (ARIMA) and artificial neural network.

This paper is focused on the practice of hourly solar irradiation forecasting by using the fuzzy logic approach.

Fuzzy logic has been introduced in 1965 by Lotfy A. Zadeh [2016]. Basically it replace the binary 0/1 logic with a multi-valued logic. Because the fuzzy approach is quite different from classical approaches, a short introduction is given in Appendix A.

Although fuzzy logic has been adopted as a standard method in various applications [Barbieri et al, 2017] its use is still incipient in modeling solar radiation at the Earth surface. There are several works dealing with the estimation of the solar irradiation via fuzzy approach. Up to now, only a few attempts related to solar resource forecasting were published. In Ref. [Rahman et al, 2017], our group reported a fuzzy model for forecasting daily global solar irradiation. Here we report an extension of this study by dropping the forecasting time horizon to one hour. Four auto-regressive fuzzy models constructed in an innovative manner are proposed and assessed.

1.2 PROBLEM STATEMENT

Lack of predictability of solar power remains one major hindrance to the introduction of large-scale solar energy production. Comprehensive solar forecasting technologies are required to manage the intermittent nature of solar energy supply. However, one of the most challenging aspects of solar forecasting is the requirement for very short-term forecasting due to cloud movement, ambient temperature variation and humidity levels, which result in rapid ramp up and ramp down rates. To solve this problem an improved solar forecasting method was used. This paper proposes an improved solar forecasting algorithm based on fuzzy logic pre-processing.

1.3 AIM AND OBJECTIVES OF THE STUDY

The aim of this work is to carry out a brief study on the application of Artificial Intelligence (AI) method in solar energy production forecasting. The objectives are:

To use an improved method to achieve high predictability of solar power generator
To obtain large-scale solar energy production

To develop a more accurate model for solar forecasting in order to better prepare the power system operator to manage the fluctuations in the solar PV power output.

To study the Application of Fuzzy Logic to Forecast Hourly Solar Irradiation

1.4 SCOPE OF THE STUDY

The scope of this work focused on the use of machine language in predicting solar energy generation. Artificial intelligence or machine learning techniques are widely researched as an alternative solution for estimating processes associated with non-linear functions. A fuzzy logic pre- processing stage is included to tune the relationship functions of various weather data in order to improve the accuracy of the solar forecast. In order to further improve the forecasting accuracy, an error correction factor based on output is included to the input layer.

Using a fuzzy logic is an improvement of solar forecasting method which pre-processing to classify cloud cover index based on relative humidity, rainfall and the time of the day.

1.5 SIGNIFICANCE OF THE STUDY

Carrying out this research work gives u knowledge of global solar irradiance at a particular location. This study has also exposed us to factors that hinder solar power generation such as rainfall, cloud movement, cloud formation and dissipation which result in rapid ramp up and ramp down rates.