Optimizing Distribution Systems with Renewable Energy Integration: Hybrid Mud Ring Algorithm-Quantum Neural Network Approach

A hybrid approach is proposed for optimizing distribution systems (DSs) by integrating clean energy sources, specifically photovoltaic (PV) and wind power (WT). The proposed technique combines the mud ring algorithm (MRA) and quantum neural network (QNN), referred to as the MRA-QNN technique. The primary objective is to minimize power loss and enhance voltage stability. The MRA method generates the control signal of the converter, while the QNN method predicts the control signal based on the MRA output. The effectiveness of the approach is revealed through simulations on standard IEEE 33 bus and 69 bus systems. Implementation in MATLAB shows superior performance compared to existing methods, with lower power loss values. There has been a sustained rise in the system voltage profile (In the WT and PV situations, 0.950. and 93 p.u), as well as a considerable reduction in the active power (AP) losses (to 132.39 kW with PV and 81.23 kW with WT from 362.86 kW). With PV, the entire yearly economic loss is lowered from $158932.68 to just $57996.939, and with WT, it is decreased to $56805.479. With three PVs, the yearly economic loss and active power losses are decreased to 30419.871 $ and 69.449, and 4.27 kW and 1875.930 $, respectively. A hybrid approach is proposed for optimizing distribution systems (DSs) by integrating clean energy sources, specifically photovoltaic (PV) and wind power (WT). The proposed technique combines the mud ring algorithm (MRA) and quantum neural network (QNN), referred to as the MRA-QNN technique. The primary objective is to reduce power loss and enhance voltage stability.image (c) 2024 WILEY-VCH GmbH