A Novel Method for Energy Consumption Prediction of Underwater Gliders Using Optimal LSSVM with PSO Algorithm

Energy consumption prediction is important for improving the energy efficiency of underwater gliders. This paper establishes a novel prediction method for energy consumption of underwater gliders based on Least Squares Support Vector Machine (LSSVM). To improve the performance of the LSSVM model, the Particle Swarm Optimization (PSO) algorithm is introduced to optimize its parameters. Sea trial data obtained by a glider are used to train and validate the model. The results demonstrate that the LSSVM-PSO model has a higher prediction accuracy than the general energy consumption model derived from the dynamical equations in our previous study.