Wireless Sensor Networks (WSNs) are widely employed in environmental monitoring, healthcare, industrial automation, military surveillance, and smart city applications. Limited battery capacity and irregular power consumption are major issues in WSN deployments, both of which considerably reduce network longevity, scalability, and communication performance. This article presents a novel Deep Learning-based Energy-Efficient Clustering Algorithm (DL-EECA) that improves WSN performance and prolongs network lifetime. The proposed framework combines an Artificial Neural Network (ANN)-based Cluster Head (CH) selection mechanism with dynamic clustering, multi-hop communication, and energy-aware data dissemination strategies. The ANN model is trained via backpropagation on simulated WSN datasets to evaluate CH suitability with respect to residual energy, distance to the Base Station (BS), node density, neighbor distribution, and event frequency. A TDMA-based scheduling technique, together with data aggregation and sleep/wake scheduling, reduces energy wastage by minimizing redundant transmissions, while a multi-hop inter-cluster routing scheme improves scalability and communication efficiency. Extensive experiments confirm that DL-EECA achieves energy efficiency above 95%, network lifetime above 97.2%, scalability above 96.5%, throughput above 99.1%, and latency as low as 93.2% (lower is better), outperforming conventional protocols such as LEACH, MODLEACH, and EEM-LEACH. The results indicate that the proposed deep learning-based clustering approach enhances energy efficiency, balances energy consumption, reduces the probability of early node failure, and substantially improves the operational lifetime of WSN deployments.