\documentclass[a4paper,fleqn]{cas-sc}
\usepackage{booktabs,siunitx}
\sisetup{detect-all}
\usepackage{hyperref}
%\usepackage{cite}
\usepackage{amsmath}
\usepackage{amssymb,amsthm}
%\usepackage[numbers]{natbib}
\usepackage{mathtools, cuted}
\usepackage[english]{babel}
\usepackage[numbers]{natbib}
%\usepackage[options]{natbib}
%\usepackage[classicReIm]{kpfonts}
\usepackage{booktabs,tabularx}
\usepackage{longtable}
\usepackage{float}
\usepackage{graphicx}
\usepackage{caption}
\usepackage{subcaption}
\usepackage{multirow}
\usepackage{url}
\usepackage{algorithm2e} % <============================================
\usepackage{pseudocode} % <=============================================
\usepackage{blindtext}% <=============================================
\usepackage{blindtext}
\usepackage[noend]{algpseudocode}
\usepackage{etoolbox}
\usepackage{setspace}
\usepackage{pifont}
\newcommand{\cmark}{\ding{51}}%
\newcommand{\xmark}{\ding{55}}%
%\doublespacing
%%%Author definitions
\def\tsc#1{\csdef{#1}{\textsc{\lowercase{#1}}\xspace}}
\tsc{WGM}
\tsc{QE}
\tsc{EP}
\tsc{PMS}
\tsc{BEC}
\tsc{DE}
\begin{document}
\let\WriteBookmarks\relax
\def\floatpagepagefraction{1}
\def\textpagefraction{.001}
\title [mode = title]{energy optimization}
\author[1]{ Ahmad }[]
\affiliation[1]{organization={Electrical Engineering Department, Najran University},
city={Najran},
% citysep={}, % Uncomment if no comma needed between city and postcode
postcode={11001},
% state={},
country={Saudi Arabia}}
\begin{abstract}
he FCDBN based framework reduces average execution time to 188 seconds while benchmark models like CRBM reduce to 195 seconds, ANN to 210 seconds, and LSTM to 220 seconds. Results validate that the proposed FCDBN based forecasting framework's performance is outstanding compared to benchmark frameworks.
\end{abstract}
\begin{keywords}
Deep belief network \sep
electricity demand forecasting \sep
factored conditional deep belief network \sep
neural network \sep
deep neural network \sep
smart grid\sep
\end{keywords}
\section*{Nomenclature}
\addcontentsline{toc}{section}{Nomenclature}
\begin{IEEEdescription}[\IEEEusemathlabelsep\IEEEsetlabelwidth{$V_1,V_2,V_3$}]
\item[] \textbf{ABBREVIATIONS}
\item[ANN] Artificial neural network
\item[ARMA] Autoregressive moving average
\section{Introduction}\label{Introduction}
\doublespacing
Ali baba
\begin{table*}[!htbp]
\centering
\caption{Day ahead accuracy assessment of electricity demand forecasting on US utility GEFCOM-2012}
\label{tab:Day_ahead_Accuracy}
\begin{tabular}{@{} l *{12}{c} @{}}
\toprule
Hours &
\multicolumn{12}{c}{US utility GEFCOM-2012} \\
\cmidrule(lr){2-13} %\cmidrule(l){10-17}
&
\multicolumn{3}{c}{ANN} &
\multicolumn{3}{c@{}}{LSTM} &
\multicolumn{3}{c}{CRBM} &
\multicolumn{3}{c}{FCDBN} \\
\cmidrule(lr){2-4} \cmidrule(l){5-7} \cmidrule(l){8-10} \cmidrule(l){11-13} %\cmidrule(l){10-11} \cmidrule(l){12-13} \cmidrule(l){14-15} \cmidrule(l){16-17}
& {\thead{MAPE}} & {\thead{RMSE}} & {\thead{r}} & {\thead{MAPE}} & {\thead{RMSE}} & {\thead{r}}& {\thead{MAPE}} & {\thead{RMSE}} & {\thead{r}} & {\thead{MAPE}} & {\thead{RMSE}} & {\thead{r}} \\
\midrule
01 & 4.81 & 30.1 & 0.325 & 3.35 & 25.3 & 0.500 & 1.08 & 20.5 & 0.725 & 0.54 & 12.5 & 0.930 \\
02 & 4.84 & 28.4 & 0.625 & 2.80 & 28.9 & 0.590 & 1.11 & 18.9 & 0.756 & 0.63 & 11.2 & 0.990 \\
03 & 3.80 & 30.6 & 0.551 & 3.27 & 23.3 & 0.585 & 1.10 & 17.3 & 0.805 & 0.45 & 9.12 & 0.976 \\
\bottomrule
\end{tabular}
\end{table*}
\end{document}
