Optimization of energy problems through heuristic algorithm based artificial neural networks

Energy is the capacity of a system to do work. In today's world, the focus is on utilizing technological advancements to achieve energy efficiency, given the potential depletion of energy resources. A significant portion of energy consumption occurs in buildings, highlighting the importance of studies on energy efficiency in this sector. This study aims to evaluate the Salp Swarm Algorithm (SSA), a metaheuristic algorithm, in optimizing major contemporary issues such as energy efficiency. Specifically, it examines SSA's effectiveness as both an optimizer and a classifier in an example energy problem.Efficient energy use is crucial for accurately estimating heating load (HL) and cooling load (CL) factors, which are essential for selecting equipment in building design. To address this issue, the study employs the Multi-Layer Perceptron (MLP), an artificial neural network architecture, in conjunction with SSA as an optimization consultant, and compares it with alternative algorithms. Statistical results and graphs indicate that SSA is a competitive, effective, and modern algorithm.The research utilizes the energy efficiency dataset to evaluate the optimal use of Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings. The SSA-based MLP architecture was trained using this dataset, and the experimental results demonstrated that SSA is an effective classifier for energy-related problems through various statistical analyses.