**1. Introduction**

Since the Industrial Revolution in the eighteenth century, fossil fuels have been used as an energy source, contributing to increase the concentration of CO2 (carbon dioxide) in the atmosphere [1]. An increasing global concentration of CO2 in the atmosphere, from 290.0 parts per million (ppm) in 1870 [2] to 414.0 ppm in 2019 [3], occurred during the period which was marked by the Second and Third Industrial Revolution. This period is characterized by a significant increase in the use of fossil fuels as an energy source. The increased concentration of CO2 in the atmosphere results in temperature rise. The increase in the temperature is the major cause for all other changes on the earth's climate. The rise in temperatures is causing warming of oceans, melting of ice mass, and increase in evaporation. Due to this

increase in CO2 emissions and its consequences, the traditional concept of global development incorporated the environmental development. This incorporation resulted a broader concept referred to as sustainable development, which is based on the inseparability of economic, social, and environmental development [1]. Therefore, nowadays, integrated renewable energy system-based power generation has enormous growth and enhanced technological development due to increasing worldwide electricity demand, environmental concerns, and financial aspects [4].

In this context, renewable energy is at the center of the transition to a less carbon-intensive and more sustainable energy system. Renewable energy has grown rapidly in recent years, accompanied by sharp cost reductions for solar photovoltaics and wind power in particular [5]. Wind energy, a sustainable and a domestic source of energy that can reduce our dependency on fossil fuels, has developed rapidly in recent years. It's mature technology and comparatively low cost make it promising as an important energy source in the next decades [6]. The electricity sector remains the brightest spot for renewables energy with the exponential growth of wind power in recent years in the world [7]. **Figure 1** shows the global cumulative installed wind capacity 2001–2017 (adapted from [8]).

Brazil is a large country with regard to its sizable power system and continental distances, both in terms of grid extension and generating capacity. A prominent feature of its power system is the significance of its hydropower [9], which accounts for 59.90% [10] of the generation in the interconnected system. By the end of 2018, there were a total of 583 plants/wind farms and 14.71 GW of installed capacity, a 15.19% growth compared to December 2017, when the installed capacity was 12.77 GW. With an additional 1.94 GW, wind power now makes up 9.0% of the nation's power matrix, which also shows the percent contribution from all sources of energy to the electric power grid at the end of 2018. It is important to remember that at the end of 2017, wind power accounted for 8.10% of the energy generated [10].

Uruguay surprisingly obtains 94.0% of its electricity from renewable sources [11]. In addition to old hydropower plants, large investments in solar, wind, and biomass have increased the proportion of these sources to 55.0% of the total energy (see that the global average is 12.0% and the European average is approximately 20.0%). In this way, wind power has attracted attention, and various wind farms

**221**

*Study of the Wind Speed Forecasting Applying Computational Intelligence*

ute to its excellent growth with regard to wind and solar energy [13].

have been constructed in Uruguay to harness wind energy. Among the countries of the world, Uruguay ranks fourth in the generation of wind energy, in accordance with [12]. Additionally, Uruguay and Brazil have good relationships, which contrib-

Regarding wind power, the variability of wind speed and wind direction throughout the day makes it difficult to decide whether to drive wind turbines, because wind exhibits temporal variations of several orders of magnitude, e.g., short-duration variations (bursts), hourly variations (owing to land and sea breezes), daily variations (owing to the local microclimate), seasonal variations, and annual variations (owing to climatic changes) [13]. The spatial variation of wind energy is also very large. The soil roughness and topography significantly influence the distribution and velocity of winds. Large fluctuations in wind speed make forecasting the power generated by wind turbines difficult; not to mention that economic losses occur if these turbines are subjected to unfavorable weather

Consequently, it is necessary to develop reliable tools to wind speed forecasting, even in the short-range. The interest in applications of mathematical modeling and numerical simulation of the atmosphere for the estimation of wind potential is increasing and driving a significant market. The use of computational models can help both the identification of locations with high wind potential and, when used operationally in daily integrations, in the short-term energy generation forecast [15]. The mainstream models used by scientific researchers can be divided into several categories [13, 16]: physical forecasting models, conventional statistical forecasting models, artificial intelligence forecasting models, statistical machine learning models, fuzzy logic-based models, spatial-correlation forecasting models,

Computational models can be useful for the identification of locations with high wind potential and, when used operationally in daily integrations, short-term energy generation forecasting [13, 15]. In [13, 17, 18], among others, they obtained good results with small error via mathematical modeling and numerical simulation for short-term prediction using computational intelligence techniques, especially multilayer perceptron neural networks with feed-forward and back-propagation training algorithms. Although the previously cited authors demonstrated the applicability of artificial neural networks (ANN) in the next-step prediction of wind speed, none of them compared the performance of the results of wind speed forecasting 6 h ahead between Colonia Eulacio, Soriano Department, Uruguay (humid subtropical climate region), and Mucuri city, Bahia, Brazil (humid tropical climate region), using meteorological data collected by anemometers and not

This chapter presents two case studies about short-term wind speed forecasting in Brazil and Uruguay. The chapter is organized as follows. In part 2, the air and the wind power are briefly described. Part 3 describes the materials and methods, computational intelligence, and nowcasting. In part 4, the case studies are proposed.

The air in motion—what we commonly call wind—is invisible, yet we see evidence of it nearly everywhere we look. It transports heat, moisture, dust, insects, bacteria, and pollen from one area to another [20]. Inserted in this context, [21] explain that the winds are generated by pressure differences that arise because of unequal heating of the earth's surface. The earth's winds blow in an unending attempt to balance these

climatic data from global circulation models shown in [19].

Conclusions are proposed in part 5.

**2. The air and wind power**

*DOI: http://dx.doi.org/10.5772/intechopen.89758*

conditions [14].

and hybrid models.

**Figure 1.** *Wind power global capacity 2001–2017 (adapted from [8]).*

#### *Study of the Wind Speed Forecasting Applying Computational Intelligence DOI: http://dx.doi.org/10.5772/intechopen.89758*

*Aerodynamics*

increase in CO2 emissions and its consequences, the traditional concept of global development incorporated the environmental development. This incorporation resulted a broader concept referred to as sustainable development, which is based on the inseparability of economic, social, and environmental development [1]. Therefore, nowadays, integrated renewable energy system-based power generation has enormous growth and enhanced technological development due to increasing worldwide electricity demand, environmental concerns, and financial aspects [4]. In this context, renewable energy is at the center of the transition to a less carbon-intensive and more sustainable energy system. Renewable energy has grown rapidly in recent years, accompanied by sharp cost reductions for solar photovoltaics and wind power in particular [5]. Wind energy, a sustainable and a domestic source of energy that can reduce our dependency on fossil fuels, has developed rapidly in recent years. It's mature technology and comparatively low cost make it promising as an important energy source in the next decades [6]. The electricity sector remains the brightest spot for renewables energy with the exponential growth of wind power in recent years in the world [7]. **Figure 1** shows the global

cumulative installed wind capacity 2001–2017 (adapted from [8]).

end of 2017, wind power accounted for 8.10% of the energy generated [10].

Uruguay surprisingly obtains 94.0% of its electricity from renewable sources [11]. In addition to old hydropower plants, large investments in solar, wind, and biomass have increased the proportion of these sources to 55.0% of the total energy (see that the global average is 12.0% and the European average is approximately 20.0%). In this way, wind power has attracted attention, and various wind farms

Brazil is a large country with regard to its sizable power system and continental distances, both in terms of grid extension and generating capacity. A prominent feature of its power system is the significance of its hydropower [9], which accounts for 59.90% [10] of the generation in the interconnected system. By the end of 2018, there were a total of 583 plants/wind farms and 14.71 GW of installed capacity, a 15.19% growth compared to December 2017, when the installed capacity was 12.77 GW. With an additional 1.94 GW, wind power now makes up 9.0% of the nation's power matrix, which also shows the percent contribution from all sources of energy to the electric power grid at the end of 2018. It is important to remember that at the

**220**

**Figure 1.**

*Wind power global capacity 2001–2017 (adapted from [8]).*

have been constructed in Uruguay to harness wind energy. Among the countries of the world, Uruguay ranks fourth in the generation of wind energy, in accordance with [12]. Additionally, Uruguay and Brazil have good relationships, which contribute to its excellent growth with regard to wind and solar energy [13].

Regarding wind power, the variability of wind speed and wind direction throughout the day makes it difficult to decide whether to drive wind turbines, because wind exhibits temporal variations of several orders of magnitude, e.g., short-duration variations (bursts), hourly variations (owing to land and sea breezes), daily variations (owing to the local microclimate), seasonal variations, and annual variations (owing to climatic changes) [13]. The spatial variation of wind energy is also very large. The soil roughness and topography significantly influence the distribution and velocity of winds. Large fluctuations in wind speed make forecasting the power generated by wind turbines difficult; not to mention that economic losses occur if these turbines are subjected to unfavorable weather conditions [14].

Consequently, it is necessary to develop reliable tools to wind speed forecasting, even in the short-range. The interest in applications of mathematical modeling and numerical simulation of the atmosphere for the estimation of wind potential is increasing and driving a significant market. The use of computational models can help both the identification of locations with high wind potential and, when used operationally in daily integrations, in the short-term energy generation forecast [15]. The mainstream models used by scientific researchers can be divided into several categories [13, 16]: physical forecasting models, conventional statistical forecasting models, artificial intelligence forecasting models, statistical machine learning models, fuzzy logic-based models, spatial-correlation forecasting models, and hybrid models.

Computational models can be useful for the identification of locations with high wind potential and, when used operationally in daily integrations, short-term energy generation forecasting [13, 15]. In [13, 17, 18], among others, they obtained good results with small error via mathematical modeling and numerical simulation for short-term prediction using computational intelligence techniques, especially multilayer perceptron neural networks with feed-forward and back-propagation training algorithms. Although the previously cited authors demonstrated the applicability of artificial neural networks (ANN) in the next-step prediction of wind speed, none of them compared the performance of the results of wind speed forecasting 6 h ahead between Colonia Eulacio, Soriano Department, Uruguay (humid subtropical climate region), and Mucuri city, Bahia, Brazil (humid tropical climate region), using meteorological data collected by anemometers and not climatic data from global circulation models shown in [19].

This chapter presents two case studies about short-term wind speed forecasting in Brazil and Uruguay. The chapter is organized as follows. In part 2, the air and the wind power are briefly described. Part 3 describes the materials and methods, computational intelligence, and nowcasting. In part 4, the case studies are proposed. Conclusions are proposed in part 5.
