Browsing by Author "Onaolapo, Adeniyi Kehinde."

Now showing 1 - 1 of 1

Reliability study under the smart grid paradigm using computational intelligent techniques and renewable energy sources.
(2022) Onaolapo, Adeniyi Kehinde.; Carpanen, Rudiren Pillay.; Dorrell, David George.; Ojo, Evans Eshiomogie.
The increase in the demand for a reliable electricity supply by the utilities and consumers has necessitated the evaluation of the reliability of power systems. A reliable electricity supply is characterized by no or minimal duration and frequency of supply outages. Current power systems are changing due to increasing power demand and depletion of fossil fuel deposits. These changes are related to smart grids which are intelligent electric networks that are capable of using demand management methods, supporting communication devices and monitoring of consumer energy consumption. They can also integrate renewable energy sources thereby reducing reliance on fossils fuel sources. The main objective of this study is to optimize power systems operations and improve reliability. Different optimization methods are proposed in this study to address the issues of power systems operations. These optimization problems consider different constraints for maximum operations of the power systems. Case studies are used to confirm the proposed methods using the historical and climatic data for the City of Pietermaritzburg (29.37°S and 30.23°E), and Newcastle (27.71°S, 29.99°E) South Africa. Firstly, the implementation of the back-propagation algorithm method of the artificial neural networks (ANNs) for designing a predictive model for power system outage is proposed. The results obtained are found to be satisfactory. In situations where there is the problem of accessibility to large system data and presence of multiple system constraints, another method is proposed. This second technique proposes the application of a maximum entropy function-based multi-constrained event-driven outage prediction model, using the collaborative neural network (CONN) algorithm. The outcome is better than the conventional event-driven methods. Lastly, an adaptive model predictive control (AMPC) method with the integration of renewable energy sources (RESs) and a battery energy storage system (BESS) is proposed to further improve the reliability of the power system. The developed method uses a modified Roy Billinton Test System (RBTS) to implement the reliability improvement of the power system. The proposed computational intelligent techniques fulfil the necessities of operation robustness, implementation simplicity and reliability improvement of the power systems.