Sources of renewables, such as wind and solar, have stood out as alternatives to meet the growing demand for energy in a clean and sustainable way.
However, although they represent a great opportunity, the intermittent nature of these energy sources also brings challenges to the sector.
To address this issue, techniques of Artificial Intelligence (IA) are applied to mitigate these challenges and add even more value to these energy sources.
The evolution of wind and solar energy sources
The growth in demand for energy, combined with the risk of global warming, has motivated several countries around the world to seek clean and renewable energy sources as alternatives to compose your energy matrix.
According to the International Energy Agency (IEA), the share of renewable energy sources in the global energy matrix It should exceed 40% by 2040, against the current 25% participation.
Wind and photovoltaic solar energy sources have gained prominence among renewable energy sources, showing significant growth in recent years. In 2018, the global installed wind power capacity reached the mark of 600 GW, presenting a 9.8% growth compared to 2017.
The installed capacity of photovoltaic solar energy, on the other hand, reached 512 GW, 27% higher than the previous year. Together, the two renewable energy sources are responsible for 7% of the world's electricity production.
Renewable energies in Brazil
In Brazil, the majority of energy comes from hydroelectric dams which, although they also use a renewable energy source, generate a dangerous dependence in the face of the droughts that have hit various regions of the country in recent years.
Thus, the use of wind and solar energy also It's gaining space here, currently representing around 9% and 1.2%, respectively, of the country's installed electrical capacity.
Government incentives boosted the installation of wind and solar farms in various regions of the country, and, according to the National Electric Energy Agency (ANEEL), the installed electrical capacity from these sources already exceeds the 16 GW mark.
To measure this number, the Itaipu hydroelectric power plant, one of the largest in the world, has a capacity of 14 GW. With the fall in the production costs of wind and solar energy sources, the expectation is that in the coming years the participation of these energy sources in the composition of the national electricity matrix will be even more significant.
The intermittent nature of wind and solar energy sources
Wind and solar energy sources will play an important role in meeting the growing energy demand in the coming years in a clean and sustainable way. However, the growth of energy generation through these sources must also bring challenges to the sector, especially since they are not always available.
The power generation capacity of a wind or solar power plant is intrinsically dependent on local environmental conditions and these may vary seasonally or even throughout the day, making it difficult to predict energy generation capacity at any given time.
The generation and energy consumption of the electrical system must be balanced, that is, there must be a control between the generation and the demand of electrical energy. Both a lack of energy or its excess can bring system problems, damage equipment, impair energy quality, or even lead to a drop in supply.
In addition, the low reliability in the amount of energy available at a given time requires operators to have an alternative energy source that can be activated quickly to meet the demand of the system. This backup is normally done by others most reliable energy sources, such as fossil fuels, which can increase system operating costs, in addition to harming the environment.
Artificial Intelligence can make energy production more predictable
We have presented the challenges of renewable energy so far, but some companies invest in technological innovations to mitigate these problems.
Recently, Google, through DeepMind, a subsidiary of the company that operates with artificial intelligence, announced that it is applying machine learning techniques to forecast the power generation capacity of the company's wind farms located in the central region of the United States.
Historical wind turbine data and weather forecasts were used by DeepMind to train a neural network capable of predicting the power generated throughout the day by the power plant's turbines with 36 hours in advance. Based on these forecasts, models were used to create recommendations.
This predictability adds value to system operators, who can properly plan how to meet system demand. According to Google, the preliminary results obtained indicate a valuation of approximately 20% of wind energy generated in relation to the base scenario.
The NCAR (National Center of Atmospheric Research) in Colorado, in the United States, has also been working with the use of artificial intelligence to forecast wind energy generated by wind farms in the state. In this case, machine learning algorithms are applied combining with information from meteorological stations and satellites.
The Future of Renewable Energy
The reliability of data to generate renewable energy allows operators to increase the share of renewable energy in their operation. Xcel Energy, one of the largest energy operators in the Colorado region, expanded the amount of energy used from renewable sources to more than 30%.
NCAR together with Xcel are now working on predicting for the generation of solar energy, but the project is even more challenging. The solution will use data from satellites, sky images, pollution monitors, and public solar panels to infer the amount of solar energy generated.
Especially for Brazil, which has enormous potential for the generation of wind and solar energy, initiatives like this can add enormous value to the electricity sector,Further boosting the use of these energy sources.
The utilities sector is one of Venturus' focuses of action, creating solutions for the challenges of this market. See the our areas of expertise and contact our specialists!
