An Innovative synthesis of deep learning techniques (DCapsNet & DCOM) for generation electrical renewable energy from wind energy

• Published in: Soft computing (Berlin, Germany) Vol. 24; no. 14; pp. 10943 - 10962
• Main Authors: Al-Janabi, Samaher, Alkaim, Ayad F., Adel, Zuhal
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2020; Springer Nature B.V
• Subjects: Algorithms; Alternative energy sources; Artificial Intelligence; Carbon dioxide; Climate change; Computational Intelligence; Computer science; Control; Data science; Datasets; Electric industries; Electricity; Energy industry; Energy resources; Engineering; Geothermal power; Industrial plant emissions; Linear programming; Machine learning; Mathematical Logic and Foundations; Mechatronics; Methodologies and Application; Multilayers; Multiple objective analysis; Neural networks; Normal distribution; Objectives; Optimization; Optimization techniques; Renewable energy; Renewable resources; Robotics; Wind power; Green energy; Search method; Multi-objective optimization; Optimization
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-020-04905-9

Renewable energy becomes one of the main resources that help the world to safety the environment from pollution and provide the people of new type of energy; therefore, this paper presents model called multi-objectives renewable energy-generation (MORE-G) for generating electrical energy from the wind. In general, this model consists of five basic phases: in a first phase collecting and preparing the data, so to make it in format suitable for the decision-making stage, this phase split into multi-steps (i.e., handle missing values and normalization dataset), and the second phase focuses on building constraints for each dataset and develops one of the optimization algorithms called cuckoo based on horizontal combination and multi-objective optimization used in third phase to generate the energy. Another model is developed as multi-layer neural network called ( DCapsNet ) based on linear combination and multi-objective functions used in the fourth phase to generate the energy. Final phase is related to evaluation of both models ( DCOM and DCapsNet ) to determine the best. The MORE-G is characterized by addressing one of the real problems, saving on material costs (i.e., reducing the need for manpower and reducing dependence on other countries in importing electric power) and upgrading the scope of the ministry of electricity.