Efficient Resource Allocation in Edge Networks Using Autoencoder-Based Capacity Optimization and SHA-512 Security

The proliferation of interconnected mobile devices within densely packed cloud networks necessitates sophisticated frameworks for capacity optimization to ensure efficiency, reliability, and data security. This study explores the challenges posed by user mobility, dynamic calculations, and increasing service demands in edge computing environments. We propose a novel capacity optimization algorithm (COA) that leverages a deep autoencoder-based binary bat algorithm to improve resource allocation. The system uses the SHA-512 cryptographic hash function for capacity requests (CRs), facilitating seamless user access to resources while quickly detecting and revoking access for unauthorized users. The system employs a selective routing mechanism that considers specific service requirements, allowing it to prioritize user demands and maximize resource utilization. The quality of service (QoS) integration ensures consistent, high-quality performance for mobile nodes, leading to an improved user experience. The framework’s effectiveness is evaluated through experiments, demonstrating its ability to optimize throughput and reduce interference in multinode networks.