LSTM-Enhanced Chaotic Bat Algorithm for Real-Time Intelligent Motor Scheduling in Edge AI Environment

Abstract

Smart motors regulate voltage adaptively to prevent economic losses resulting from voltage instability. These motors generate massive volumes of data, which existing scheduling methods struggle to process efficiently, leading to significant delays. To address these limitations, this paper proposes a novel intelligent motor scheduling framework that integrates Long Short-Term Memory (LSTM) networks with an Improved Chaotic Bat Algorithm (ICBA) to meet the real-time and large-scale optimization demands of smart grid environments. The LSTM module predicts high-quality initial solutions based on historical scheduling patterns, thereby accelerating the convergence of the ICBA. Enhancements to the standard bat algorithm include a second-order oscillation mechanism for improved global exploration and a chaotic search strategy based on logistic mapping to increase population diversity. Furthermore, a hierarchical cloud–edge–end collaborative optimization architecture is introduced to balance computational efficiency with real-time responsiveness. In terms of response time, the LSTM-ICBA achieves an average latency that is 47.4% faster than LSTM. For voltage deviation, the framework achieves a 24.3% reduction compared with LSTM.