Wireless Sensor Networks (WSNs) are critical across environmental monitoring, surveillance, and healthcare applications. Energy conservation prolongs network lifetime and ensures continuous data gathering. This research presents a novel approach to optimizing WSN energy consumption through Mahalanobis Distance-Based K-Means Clustering (MDB-KMC) combined with the Cuttlefish Algorithm for cluster head selection. MDB-KMC efficiently divides nodes into clusters, enabling effective data transmission. The Cuttlefish Algorithm then optimizes clusters by dynamically selecting heads based on conditions. Inspired by cuttlefish adaptability, it adjusts roles minimizing energy use. Extensive simulations demonstrate significant improvements over traditional methods. Adapting clustering and roles reduces consumption, extends lifetime, and enhances reliability and performance. Integrating MDB-KMC and the Cuttlefish Algorithm thus provides a robust, efficient solution to address WSN energy optimization challenges. This enables more reliable sensor network deployment. This novel integration of adaptive clustering and bio-inspired optimization techniques optimizes WSN energy efficiency, improving real-world performance.