Comparative Analysis of Particle Swarm Optimization and Artificial Neural Network Based MPPT with Variable Irradiance and Load

Abstract

The escalating demands and increasing awareness for the environment, resulted in deployment of Photovoltaic (PV) system as a viable option. PV system are widely installed for numerous applications. However, the challenges in tracking the maximum power with intermittent atmospheric condition and varying load is significant. Maximum Power Point Tracking (MPPT) algorithms are employed and based on their convergence speed, control of external variations and oscillation, the output power efficiency, and other significant factors viz. the algorithm complexity and implementation cost, novel MPPT approach are preferable than the conventional approach. This paper presents an artificial intelligence-based optimization controller for MPPT in a PV system under varying load and irradiance conditions. Comparative analysis of Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) based MPPT is simulated and analysed. The PV system consisting of PV array and boost converter with MPPT controller feeds the DC load. The power conversion and panel efficiency are the significant factors to determine the effectiveness of tracking maximum power point. The simulation results show the performance of these controllers on the PV panel output power and the load side output power under changing loads and irradiance. In addition, the comparison of PV panel efficiency of ANN and PSO based MPPT techniques w.r.t changing loads is carried out. Based on the above analysis, PSO based MPPT algorithm marginally outperforms the ANN based MPPT algorithm. Further, the implementation of hybrid MPPT (ANN &PSO) for higher accuracy and tracking capability can be carried out as future work.