Predicting the stability of smart grid for improving the sustainability using distributed generation technology

Abstract

Distributed Generation balances the supply in the grid effectively. Numerous distributed power generation technologies need more efficiency, cost, and power output to meet the energy requirements. Hence, this paper has aimed to provide an efficient DG system by integrating a PV module with a smart grid through a 3-phase AC-DC converter. Numerous PV modules are combined through DC linking, and different inverter control strategies are used to control the network. The ANN algorithm is used to optimize the demand and supply in the network. PV modules are included in the network to boost up the renewable energy source for the network. The power generated from the PV module is converted to DC through 3 phase AC-DC converter. A DC-link modeling is carried out between various converters and PV modules. It helps balance the variation in the DC input from the PV modules converted by AC-DC converters. The input current is again sent into a closed-loop inverter system to control the input current appropriately based on the demand. The problems between demand and supply are sorted through an ANN algorithm that optimizes the whole model based on supply and demand. The whole is simulated, and the results obtained are discussed in detail. The results are compared with similar Distributed power generation technologies to compare their efficiency. The comparison clearly shows that the proposed model provides better environmental sustainability and expandability to the system.

Keywords

• Distributed generation
• Smart grid
• Renewable energy sources
• Deep Learning
• Supply-Demand