Real-Time Cost Optimization Approach Based on Deep Reinforcement Learning in Software-Defined Security Middle Platform

Abstract

In today’s business environment, reducing costs is crucial due to the variety of Internet of Things (IoT) devices and security infrastructure. However, applying security measures to complex business scenarios can lead to performance degradation, making it a challenging task. To overcome this problem, we propose a novel algorithm based on deep reinforcement learning (DRL) for optimizing cost in multi-party computation software-defined security middle platforms (MPC-SDSmp) in real-time. To accomplish this, we first integrate fragmented security requirements and infrastructure into the MPC-SDSmp cloud model with privacy protection capabilities to reduce deployment costs. By leveraging the power of DRL and cloud computing technology, we enhance the real-time matching and dynamic adaptation capabilities of the security middle platform (Smp). This enables us to generate a real-time scheduling strategy for Smp resources that meet low-cost goals to reduce operating costs. Our experimental results demonstrate that the proposed method not only reduces the costs by 13.6% but also ensures load balancing, improves the quality-of-service (QoS) satisfaction by 18.7%, and reduces the average response time by 34.2%. Moreover, our solution is highly robust and better suited for real-time environments compared to the existing methods.

Keywords

• software-defined security
• deep reinforcement learning
• cost optimization
• Internet of Things
• privacy protection