Cheetah optimization-based smart energy management for appliance scheduling and DER integration in residential and commercial-industrial grids

• COA-based framework for DER allocation, appliance scheduling, and tariff-based cost minimization. • Balances technical, economic, and environmental goals, improving REUF, SSR, PLR, and CO 2 reduction. • Handles EV availability and renewable intermittency for resilience and real-time adaptability. • Outperforms GA, PSO, WOA with up to 40.9% cost savings and higher energy independence. • Proven scalable on IEEE 15-bus RDS for residential and commercial grids under dynamic loads. This study proposes a smart energy management strategy for the IEEE 15-bus radial distribution system (RDS) to minimize electricity costs, power losses, and grid dependency, while maximizing renewable energy usage and system stability. The system includes solar (PV) and wind (WT) generation, modeled using Monte Carlo (MC) simulations, along with electric vehicles (EVs) operating in vehicle-to-grid (V2G) mode and battery energy storage systems (BESS), addressing both residential and commercial-industrial loads. These normalized power outputs serve as inputs to a multi-objective optimization framework that balances technical (power loss, voltage stability, fault detection), economic (total electricity cost), and operational criteria. The cheetah optimization algorithm (COA), implemented in MATLAB, handles this complex optimization task. COA offers an adaptive exploration–exploitation balance through dynamic coefficients and stochastic movements, delivering better solution diversity and faster convergence than traditional algorithms such as GA, PSO, and WOA. Simulation results verify COA’s superior performance. In the residential sector, COA achieves the lowest multi-objective function value (0.7064), with a 73.37 % increase in renewable energy usage and a 64.49 % drop in grid dependency. Similar improvements appear in commercial-industrial scenarios. These outcomes demonstrate COA’s effectiveness in solving smart energy management challenges and establish the proposed framework as a scalable solution for modern smart grids.