SealOS+: A Sealos-based Approach for Adaptive Resource Optimization Under Dynamic Workloads for Securities Trading System

TL;DR

SealOS+ is a novel system that uses deep reinforcement learning, caching, and load prediction to optimize resource allocation in securities trading platforms, ensuring low latency and high throughput.

Contribution

It introduces a Sealos-based adaptive resource scheduling framework with deep reinforcement learning and LSTM load prediction tailored for securities trading systems.

Findings

Achieved 78% CPU utilization in real deployment.

Reduced transaction response time to 105ms.

Reached 15,000 transactions per second peak capacity.

Abstract

As securities trading systems transition to a microservices architecture, optimizing system performance presents challenges such as inefficient resource scheduling and high service response delays. Existing container orchestration platforms lack tailored performance optimization mechanisms for trading scenarios, making it difficult to meet the stringent 50ms response time requirement imposed by exchanges. This paper introduces SealOS+, a Sealos-based performance optimization approach for securities trading, incorporating an adaptive resource scheduling algorithm leveraging deep reinforcement learning, a three-level caching mechanism for trading operations, and a Long Short-Term Memory (LSTM) based load prediction model. Real-world deployment at a securities exchange demonstrates that the optimized system achieves an average CPU utilization of 78\%, reduces transaction response time to 105ms, and reaches a peak processing capacity of 15,000 transactions per second, effectively meeting the rigorous performance and reliability demands of securities trading.