Chimps’ hunting behavior could improve photovoltaic energy’s production prediction

Researchers have analyzed the impact of chimp optimization algorithm (ChOA) on various photovoltaic energy production prediction machine learning models.

The study led by researchers from German Jordanian University focused on the algorithm that’s based on the cooperative hunting behavior of chimpanzees in nature.

Researchers studied the impact of ChOA on five distinct machine learning (ML) models which are built and compared to predict energy production based on four independent weather variables: wind speed, relative humidity, ambient temperature, and solar irradiation.

Models were hyperparameter tuned using chimp optimization algorithm

The evaluated models include multiple linear regression (MLR), decision tree regression (DTR), random forest regression (RFR), support vector regression (SVR), and multi-layer perceptron (MLP). These models were hyperparameter tuned using chimp optimization algorithm (ChOA) for a performance appraisal.

Solar photovoltaic (PV) systems, integral for sustainable energy , face challenges in forecasting due to the unpredictable nature of environmental factors influencing energy output, according to the study.

The importance of PV forecasting in the many applications of PVs is practiced for the proper management and maintenance of the PV systems worldwide. Effective utility grid management is realized from this process, given the immense ability to predict the expected output in energy generation, according to the study published in journal Nature .

All five models, with ChOA and without, were trained on 948 records and tested on 362 records. The records were taken between 2015 and 2018 from a 264 Kw PV system installed on a roof at the Applied Science University in Amman, the capital of Jordan. The installation tilt angle was set at 11 degrees and the azimuth angle to −36 degrees, reported PV Magazine .

Optimization of hyperparameters enhanced ML models’ performance

The optimization of hyperparameters significantly enhanced the performance of all ML models.

“The ChOA effectively fine-tuned the parameters, resulting in improved model fitting, reduced overfitting, and enhanced generalization compared to two other widely used optimization algorithms from the literature: PSO (Particle swarm optimization) and GA (Genetic algorithm),” said researchers in the study .

Specifically, the ChOA achieved the lowest prediction errors (in terms of RMSE- Root mean square error) and demonstrated greater efficiency, requiring fewer iterations to achieve optimal hyperparameters.

The study underlines the fact that fine-tuning of ML models for improved prediction accuracy in energy production domain still involves the use of advanced optimization techniques like ChOA , compared with other widely used optimization algorithms from the literature.

Researchers also stated that real-time predictive capabilities and operational efficiency of solar PV systems can be investigated via the integration of real-time weather data.