Research on Intelligent Auxiliary Control Technology for Large Power Grid Section Based on Artificial Intelligence

We must constantly ensure the operational stability of the electric power system since it is fundamental to contemporary civilization. The inertia of big spinning turbines is what traditional thermal power producers use to keep the grid stable. To achieve decarbonization in the energy sector, renewable energy sources must replace traditional thermal generators. The standard methods of power grid stabilization are ineffective against these renewable energy sources due to their lack of electromechanical inertia. When renewable energy sources encounter disruptions, such an abrupt drop in power supply, this study suggests a new control method that makes them act like traditional generators. This is how emerging renewable energy sources may be used to stabilize the system. Without compromising grid stability, this idea for renewable energy integration into the power grid has the potential to hasten the energy sector's decarbonization. The goal of this proposed study is to provide a smart algorithm that grid-connected PV systems may use to manage power quality problems. Grid stability, energy management, and efficiency are all improved with the use of Model Predictive Control (MPC) with Graphical Convolutional Neural Networks (GCN). In addition, MPC generates the control signals that reduce the current in harmonics. Reason being, power generating systems can more effectively transmit energy to grid-connected PV systems. Power quality issues, such as voltage distortions, THD and power fluctuations, in grid-connected PV systems have been reduced by the created KNN-SMOTE-GCN algorithm. Capturing sunlight, converting it into photovoltaic (PV) panels, and finally generating electricity is the first step. In addition, the DC-DC boost converter is designed to work with the DC bus system, which is appropriate for PV panels since they generate DC current. After that, the MPPT algorithm could monitor the PV panels' peak output and change the voltage to meet the demand. A DC-AC converter is then used to transform the DC power into AC power. Second, the SP UPQC model helps with power distribution process issues with voltage and current. At last, the performance is evaluated by looking at voltage deviation, power loss, reactive power fluctuation, and THD.