Optimal Design of an Artificial Intelligence Controller for Solar-Battery Integrated UPQC in Three Phase Distribution Networks

In order to minimize losses in the distribution network, integrating non-conventional energy sources such as wind, tidal, solar, and so on, into grid has been proposed many papers a viable solution. Using electronic power equipment control nonlinear loads impacts quality of power. The unified conditioner (UPQC) is FACTS device with back-to-back converters that are coupled together DC-link capacitor. Conventional training algorithms used by ANNs, Back Propagation Levenberg–Marquardt algorithms, can become trapped local optima, which motivates use ANNs trained evolutionary algorithms. This work presents hybrid controller, based on soccer league algorithm, an artificial neural network controller (S-ANNC), for shunt active filter. also fuzzy logic series filter UPQC associated solar photovoltaic system battery storage system. synchronization phases created using self-tuning (STF), association unit vector generation method (UVGM), superior performance during unbalanced/distorted supply voltage conditions; therefore, necessity phase-locked-loop, low-pass filters, high-pass filters totally eliminated. STF separating harmonic fundamental components, addition generating filters. prime objective suggested S-ANNC mean square error achieve fast action will retain voltage’s constant value load/irradiation variations, suppress current harmonics power–factor enhancement, mitigate sagging/swelling/disturbances voltage, provide appropriate compensation unbalanced voltages. analysis S-ANNC, five test cases several combinations loads/supply voltages, demonstrates supremacy S-ANNC. Comparative was carried out GA, PSO, GWO methods, other methods exist literature. showed extra-ordinary terms diminishing total distortion (THD); thus PF improved distortions were reduced.