Smart energy management: process structure-based hybrid neural networks for optimal scheduling and economic predictive control in integrated systems

TL;DR

This work proposes a physics-informed hybrid time-series neural network (NN) surrogate to predict the dynamic performance of IESs across multiple time scales, and designs an NN-based scheduler and an NN-based economic model predictive control framework to meet global operational requirements.

Abstract

Integrated energy systems (IESs) are complex systems consisting of diverse operating units spanning multiple domains. To address its operational challenges, we propose a physics-informed hybrid time-series neural network (NN) surrogate to predict the dynamic performance of IESs across multiple time scales. This neural network-based modeling approach develops time-series multi-layer perceptrons (MLPs) for the operating units and integrates them with prior process knowledge about system structure and fundamental dynamics. This integration forms three hybrid NNs (long-term, slow, and fast MLPs) that predict the entire system dynamics across multiple time scales. Leveraging these MLPs, we design an NN-based scheduler and an NN-based economic model predictive control (NEMPC) framework to meet global operational requirements: rapid electrical power responsiveness to operators requests, adequate cooling supply to customers, and increased system profitability, while addressing the dynamic time-scale multiplicity present in IESs. The proposed day-ahead scheduler is formulated using the ReLU network-based MLP, which effectively represents IES performance under a broad range of conditions from a long-term perspective. The scheduler is then exactly recast into a mixed-integer linear programming problem for efficient evaluation. The real-time NEMPC, based on slow and fast MLPs, comprises two sequential distributed control agents: a slow NEMPC for the cooling-dominant subsystem with slower transient responses and a fast NEMPC for the power-dominant subsystem with faster responses. Extensive simulations demonstrate that the developed scheduler and NEMPC schemes outperform their respective benchmark scheduler and controller by about 25% and 40%. Together, they enhance overall system performance by over 70% compared to benchmark approaches.

Figures (23)

• Figure 1: The considered grid-connected IES for power and cooling generation.
• Figure 2: The workflow of establishing the hybrid neural network models for IESs.
• Figure 3: Step responses of operating units within the IES: the red dashed lines indicate where the approximate time constants of the outputs are located.
• Figure 4: The dynamic time-series multi-layer perceptron employed in this work: $q^{-1}$ stands for the unit time delay.
• Figure 5: A segment of the fuel cell training datasets on the 5-second time scale: (i) the upper subfigure shows the training input signal, which includes ten-level PRMSs with a 5-second sampling interval, where the duration is randomly repeated; (ii) the lower subfigure depicts the corresponding system output, where the blue line represents the nominal output and the red dashed line represents the processed output with white noise.

Theorems & Definitions (7)

• Remark 1
• Remark 2
• Remark 3
• Remark 4
• Remark 5
• Remark 6
• Remark 7