Real-Time Machine-Learning-Based Optimization Using Input Convex Long Short-Term Memory Network

TL;DR

This paper introduces an Input Convex LSTM network to improve the computational speed of neural network-based optimization, enabling real-time decision-making in energy and manufacturing systems.

Contribution

The paper presents a novel IC-LSTM architecture that enhances optimization efficiency, demonstrated through real-world case studies showing significant speed improvements over traditional methods.

Findings

IC-LSTM achieves at least 4-fold speedup in real-time energy system optimization.

Demonstrated superior performance of IC-LSTM in practical applications.

Source code availability facilitates further research and implementation.

Abstract

Neural network-based optimization and control methods, often referred to as black-box approaches, are increasingly gaining attention in energy and manufacturing systems, particularly in situations where first-principles models are either unavailable or inaccurate. However, their non-convex nature significantly slows down the optimization and control processes, limiting their application in real-time decision-making processes. To address this challenge, we propose a novel Input Convex Long Short-Term Memory (IC-LSTM) network to enhance the computational efficiency of neural network-based optimization. Through two case studies employing real-time neural network-based optimization for optimizing energy and chemical systems, we demonstrate the superior performance of IC-LSTM-based optimization in terms of runtime. Specifically, in a real-time optimization problem of a real-world solar photovoltaic energy system at LHT Holdings in Singapore, IC-LSTM-based optimization achieved at least 4-fold speedup compared to conventional LSTM-based optimization. These results highlight the potential of IC-LSTM networks to significantly enhance the efficiency of neural network-based optimization and control in practical applications. Source code is available at https://github.com/killingbear999/ICLSTM.