Solar Power Plant Optimization

The objective of this chapter is to optimize the photovoltaic power plant considering the effects of variable shading on time and weather. For that purpose, an optimization scheme based on the simulator from Sanchez Reinoso, Milone, and Buitrago (2013) and on evolutionary computation techniques is proposed. Regarding the latter, the representation used and the proposed initialization mechanism are explained. Afterwards, the proposed algorithms that allow carrying out crossover and mutation operations for the problem are detailed. In addition, the designed fitness function is presented. Lastly, experiments are conducted with the proposed optimization methodology and the results obtained are discussed.

Comprehensive Methods for Dealing with Uncertainty in Assessing Sustainability Part 1

Integrated Value Method for Sustainability Evaluation (MIVES) is a deterministic method based on requirement trees, value functions, and the Analytic Hierarchy Process. It allows integrating environmental, social, and economic sustainability indicators in a global index. The value functions make it possible to consider non-linearity in the assessment. MIVES takes into account the relative weight of the various model indicators. Deterministic models can cause significant problems in terms of adequately managing project sustainability. A method not only has to estimate the sustainability index at the end of the project. It also has to evaluate the degree of uncertainty that may make it difficult to achieve the sustainability objective. Uncertainty can affect indicators, weights, and value function shapes. This chapter presents a method for sustainability assessment, taking into account uncertainty. It is based on MIVES and the Monte Carlo simulation technique. An example of potential application is proposed, related to power plants.

Classification of Failures in Photovoltaic Systems using Data Mining Techniques

Data mining techniques have been used on data collected from a photovoltaic system to predict its generation and performance. Nevertheless, up to date, this computing approach has needed the simultaneous measurement of environmental parameters that are collected by an array of sensors. This chapter presents the application of several computing learning techniques to electrical data in order to detect and classify the occurrence of failures (i.e. shadows, bad weather conditions, etc.) without using environmental data. The results of a 222kWp (CdTe) case study show how the application of computing learning algorithms can be used to improve the management and performance of photovoltaic generators without relying on environmental parameters.

Grid Stabilization Effect of Combined Electricity Generation from Wind and Photovoltaic Systems in Murcia, Spain

In this chapter, a model that calculates the impact on the grid of the simultaneous injection of electricity both from photovoltaic and wind sources is presented. The best locations for wind and photovoltaic technologies within Región de Murcia, southeast Spain, have been selected from a GIS database and evaluated and classified using a fuzzy version of the multicriteria decision method called Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). After the classification, the best locations are selected for each technology. Then, the impact on the grid arising from the injection of power generated in wind of photovoltaic systems installed at these specific locations and that are connected to the grid has been calculated in a power range of several kWp, including random steps of up to 50kW. The results show that stable grid parameters are obtained within 500ms in all cases, even when this relatively large power surge (or variation) is considered.

Evaluation of Renewable Energy Alternatives using Hesitant Fuzzy TOPSIS and Interval Type-2 Fuzzy AHP

The selection among renewable energy alternatives is a fuzzy multicriteria problem with many conflicting criteria under uncertainty. In many decision-making problems, the Decision Makers (DM) define their preference in linguistic form since it is relatively difficult to provide exact numerical values during the evaluation of alternatives. Therefore, in many studies, fuzzy logic is successfully used to model this kind of uncertainty. In this chapter, the authors try to capture this uncertainty by using interval type-2 fuzzy sets and hesitant fuzzy sets. They propose a fuzzy multicriteria method for the evaluation of renewable energy alternatives, in which the priority weights of the criteria are determined by interval type-2 fuzzy AHP, and the alternatives are ranked using hesitant fuzzy TOPSIS. A case study is also given.

Metaheuristics Applied to Biorefinery Supply Chain Problems

Bioenergy has been recognized as an important alternative source of energy. The production of bioenergy is expected to increase in the years to come, and one of the most important obstacles in increased bioenergy utilization are the logistics problems, which involve complex and large-scale optimization problems. Solving these problems constitutes a daunting task, and often, traditional mathematical approaches fail to converge to the optimal solution within a reasonable time. Thus, more robust methods are required in order to overcome complexity. Metaheuristics are strategies for solving complex and large-scale optimization problems, which provide a near-optimal or practically useful solution. The aim of this chapter is to present a survey of metaheuristics and the available literature regarding the application of metaheuristics in the bioenergy supply chain field as well as the uniqueness and challenges of the mathematical problems applied to bioenergy.

Current Status and Future Trends of the Evaluation of Solar Global Irradiation using Soft-Computing-Based Models

Most of the research on estimating Solar Global Irradiation (SGI) is based on the development of parametric models. However, the use of methods based on the use of statistics and machine-learning theories can provide a significant improvement in reducing the prediction errors. The chapter evaluates the performance of different Soft Computing (SC) methods, such as support vector regression and artificial neural networks-multilayer perceptron, in SGI modeling against classical parametric and lineal models. SC methods demonstrate a higher generalization capacity applied to SGI modeling than classic parametric models. As a result, SC models suppose an alternative to satellite-derived models to estimate SGI in near-to-present time in areas in which no pyranometers are installed nearby.

Modeling of Wind Speed Profile using Soft Computing Techniques

This chapter examines the capability of three soft computing techniques (Genetic Programming [GP], Support Vector Machine [SVM], and Multivariate Adaptive Regression Spline [MARS]) for prediction of wind speed in Nigeria. Latitude, longitude, altitude, and the month of the year have been used as inputs of GP, RVM, and MARS models. The output of GP, SVM, and MARS is wind speed. GP, SVM, and MARS have been used as regression techniques. To develop GP, MARS, and SVM, the datasets have been divided into the following two groups: 1) Training Dataset – this is required to develop GP, MPMR, and RVM models. This study uses 18 stations' data as a training dataset. 2) Testing Dataset – this is required to verify the developed GP, MPMR, and RVM models. The remaining 10 stations data have been used as testing dataset. Radial basis function has been used as kernel functions for SVM. A detailed comparative study between the developed GP, SVM, and MARS models is performed in this chapter.

Design and Implementation of a Fuzzy Inference Model for Mapping the Sustainability of Energy Crops

Energy crops are positioned as the most promising renewable energy sources. Over recent years, the use of biomass has been growing significantly, especially in countries that have made a strong commitment to renewable sources in their energy policies. One of the aspects of the use of biomass for energy is that it is still controversial with regard to full environmental sustainability. Unfortunately, the existing environmental evaluation tools in many cases are unable to manage uncertain input data. Fuzzy-set-based methods, instead, have proved to be able to deal with uncertainty in environmental topics. The idea of this chapter is to reproduce a solution by decoding it from the domain of knowledge with the calculus of fuzzy “if-then” rules. A methodology based on Fuzzy Inference Systems (FIS) is proposed to assess the environmental sustainability of biomass.

Measurement of Electricity Distribution Service in India by Soft Computing Technique (ANN)

Indian electric power division networks have evolved under certain assumptions. Industry architectures that bear multidirectional information exchange between the regulatory rules and the technology developers are likely to move toward to achieve optimal performance. Currently, very little attention is given to the potential for quality of service discrimination and improvements and/or cost reduction of electricity sector. Effective customer satisfaction investigation is a very important prerequisite for power supply enterprise to win in the market competition. It has for some time been realized that the performance of a service industry such as the electricity providers of a local authority is likewise evaluated by its consumers on the quality of its service delivered to the consumer. Therefore, in this chapter, efforts are taken to use an Artificial Neural Network (ANN) to evaluate service quality in an electricity utility industry.