Power system resiliency and robustness became major concerns of the system operators and researchers after the introduction of the smart grid concept. The improvements in the battery storage systems (BSS) and the photovoltaic (PV) systems encourage power systems operators to enable the use of those systems in resiliency and robustness studies. Utilization of those systems not only contributes to the robustness of the power systems but also decrease the operational costs. There are several methods in literature to operate the grid systems with partitions of PV and BSS in the most economical way. Although these methods are straightforward and work fine, they can not guarantee the most economical result on a daily basis. In this paper, deep learning based PV generation and load forecasts are used to improve the results of optimization in terms of economic aspects in nano-grid applications. In the considered system, there are loads, PV generation units, BSS and grid connection. Bi-directional power flow is permitted between the main grid and the nano-grid system. The forecasting methodologies and used optimization algorithms will be explained in this paper.