A Grasshopper Optimization–Driven Smart Energy Management Framework for Renewable–EV–Storage Integrated Grids to Maximize Real‐Time Trading Revenue Under Weather Variability

ABSTRACT

The penetration of distributed renewable energy resources, battery energy storage systems (BESS) and electric vehicles (EVs) has increased, leading to the requirement for intelligent residential energy management strategies that can work in the face of uncertain renewable generation and dynamic electricity pricing. This paper proposes a market‐aware smart energy management system (SEMS) that simultaneously coordinates photovoltaic (PV) systems, wind turbines (WTs), BESS, EVs with bidirectional charging capability and flexible household appliances to maximize real‐time energy trading revenue while respecting distribution network, storage and user mobility constraints. The presented framework integrates time‐correlated stochastic renewable generation, weather‐dependent load scheduling, coordinated DER dispatch, EV charging/discharging and real‐time electricity trading into a unified optimization framework, which is different from conventional deterministic energy management strategies. The nonlinear constrained optimization problem obtained is solved using the grasshopper optimization algorithm (GOA). The proposed SEMS is tested on IEEE 69‐bus radial distribution system considering clear, cloudy and rainy weather conditions and benchmarked with four representative optimization algorithms, namely grey wolf optimizer, Harris Hawks optimization, marine predators algorithm and arithmetic optimization algorithm. The simulation results show that GOA provides the highest average trading revenue (₹67.34/h), the highest average traded power (27.81 kW), the lowest revenue variability (₹2.83) and the fastest convergence (54 iterations) among the investigated algorithms. Moreover, the Wilcoxon rank‐sum and Friedman statistical tests confirm the statistical significance of the performance improvements achieved. Scenario analysis shows that the coordinated use of PV, WT, BESS and EV resources can effectively mitigate the intermittency of renewables, improve the performance of energy trading and ensure the safe operation of the network under different weather conditions. The proposed framework is verified through extensive simulation studies and the results validate the potential of the proposed framework as a robust and computationally efficient optimization method for residential smart energy management. Future work will focus on verification with real world operational data and hardware‐in‐the‐loop platforms.