Photovoltaic Design for Smart Cities and Demand Forecasting Using a Truncated Conjugate Gradient Algorithm

Abstract

Worldwide, global warming is a very important concern. This refers to climate change caused by human activities, which affect the environment. Climate change presents a serious threat to the natural world. This is likely to affect our future unless action is taken to avoid such phenomena. In addition, without ambitious mitigation efforts, global temperature rises will occur in this century. In recent years, countries all over the world have had their own vision directed toward renewable energy, which is a clean option to will help to avoid the results of global warming. One of these energy sources is solar energy. The idea of solar energy has been raised to improve sustainability in individual countries and in the energy sector. Various countries have made decisions to develop renewable energy projects. Solar energy plans have become important in recent years. Integration of variable energy resources into an electricity grid can use solar photovoltaics as a main resource. These variable energy resources, as new resources, are currently envisioned to be either wind or solar photovoltaics. However, the output of these types of resources can be highly variable and depend on weather fluctuations such as wind speed and cloud cover. Since photovoltaic power generation is highly dependent on weather conditions, photovoltaic power generation operates differently in different regions. In particular, solar irradiance affects photovoltaic power generation. This means that solar power forecasting becomes an important tool for optimal economic management of the electric power network. In this chapter, an artificial intelligence technique is recommended to calculate the number of solar power panels required to satisfy a given estimated daily electricity load for five countries: the Kingdom of Bahrain, Egypt, India, Thailand, and the UK. Such artificial intelligence techniques play an important role in modeling and prediction in renewable energy engineering. The main focus of this chapter is the design of photovoltaic solar power plants, which help to reduce carbon dioxide emissions where they are connected to the national electricity grid in order to feed the grid with the extra electricity they generate. In this case, the power plant becomes more efficient than a combined cycle plant. At the same time, modeling and prediction in renewable energy engineering helps engineers to make predictions regarding future required loads.