Smart warehouse management has been transformed by the emergence of Artificial Intelligence of Everything (AIoE), enabling simultaneous optimization of costs, energy consumption, and service levels. This research presents a multi-objective optimization model for AIoE-based warehouse management that balances conflicting goals such as minimizing operating costs, reducing emissions, and increasing logistics efficiency. The research innovation lies in designing a comprehensive mathematical model, comparing advanced optimization methods, and considering operational uncertainties. Four meta-heuristic algorithms, GA, PSO, GWO, and an improved hybrid version of GWGO, are investigated to solve the model. Computational results show that GWGO has higher accuracy, faster convergence, and more stable performance than other methods. Also, uncertainty analysis confirms that operational fluctuations significantly impact warehouse costs and robust models are essential for optimal management. This research provides practical guidance for supply chain managers and opens a new path for developing intelligent models and hybrid optimization methods. A future proposal is integrating machine learning and blockchain in smart warehouse management.