# Optimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks

## TL;DR

This paper introduces a new hybrid framework combining the iHow optimization algorithm and multi-scale attention networks to improve wind and solar energy forecasting accuracy and efficiency.

## Contribution

The novel contribution is the integration of the iHow optimization algorithm with a multi-scale attention network for scalable and accurate renewable energy forecasting.

## Key findings

- The MSAN model achieved MSE of 0.0105 for wind and 0.0976 for solar forecasting.
- Using biHOW reduced misclassification rates to 0.3925 for wind and 0.4161 for solar.
- iHOW optimization achieved MSE of 1.10883×10⁻⁶ for wind and 7.08664×10⁻⁶ for solar, outperforming other metaheuristics.

## Abstract

Deep learning models often encounter two key challenges in developing intelligent and scalable forecasting frameworks for renewable energy systems: input feature space dimensionality and sensitivity to hyperparameter settings. These limitations increase computational cost and compromise generalization and robustness. This paper presents a hybrid deep learning–optimization framework that leverages cognitively inspired metaheuristics to address these challenges, employing the Binary iHow Optimization Algorithm (biHOW) for feature selection and its continuous counterpart, iHOW, for hyperparameter tuning. Both variants emulate human cognitive phases—data absorption, information analysis, reinstitution, and adaptive knowledge development enabling efficient traversal of complex search spaces. Using the Multi-Scale Attention Network (MSAN) as the forecasting backbone, which is well suited for modeling renewable energy time series due to its ability to capture multi-scale temporal dependencies ranging from short-term fluctuations to long-term seasonal patterns, the proposed framework achieved high accuracy for wind and solar generation prediction. The MSAN model attained Mean Squared Errors (MSE) of 0.0105 for wind and 0.0976 for solar forecasting. Applying biHOW for feature selection reduced the average misclassification rate to 0.3925 (wind) and 0.4161 (solar) while identifying compact, interpretable feature subsets. The iHOW optimizer further fine-tuned architectural and training parameters, decreasing MSE to \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$1.10883\times 10^{-6}$$\end{document} for wind and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$7.08664\times 10^{-6}$$\end{document} for solar, outperforming state-of-the-art metaheuristics including HHO, GWO, PSO, and JAYA. These findings demonstrate the effectiveness of iHOW-based optimization in enhancing forecasting accuracy and computational scalability. The proposed hybrid framework supports adaptive forecasting for intelligent energy management within modern smart grids.