Data-driven real-time predictive control for industrial heating loads: data

Uncertainties and computational complexity are two growing challenges in scheduling industrial heating loads. In this paper, a data-driven real-time predictive control approach is proposed to deal with these challenges in the industrial scheduling of bitumen tanks. Specifically, predictive control technology is utilized to leverage the updated information to mitigate the negative impact of past uncertainties in equipment parameters and external environmental factors, which may lead to temperature constraint violations in the bitumen tank operation processes. Meanwhile, a data-driven method using artificial neural networks (ANN) is developed to ensure efficient computation for real-time predictive control. Moreover, a two-layer control method is devised to reduce the calculation time for day-ahead optimal scheduling of a large scale of bitumen tanks, aiming to generate sufficient high-quality data for training ANN. In the two-layer control method, the clustered temperature transfer processes of bitumen tanks are analyzed and modeled for the first time. Simulation results indicate that the two-layer control method can significantly reduce the computational time required for the day-ahead optimal scheduling of bitumen tanks, facilitating the generation of a large amount of high-quality data for training ANN. Subsequently, the application of ANN enables real-time predictive control, helping to eliminate the negative impact of uncertainties. “Numerical results and figures.xlsx” provides the numerical results of Fig. 7 - Fig. 13 of the paper. It contains seven sheets, providing the data behind Fig. 7 - Fig. 13 of the paper. In the “Fig. 7” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) of day-ahead direct control results for different numbers of bitumen tanks. In the “Fig. 8” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) and temperature (unit: ℃) of day-ahead two-layer control results with 30 bitumen tanks and their temperature transfer process. In the“Fig. 9” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) and temperature (unit: ℃) of day-ahead two-layer control results of 30 bitumen tanks with lower initial heat energy and (b) their temperature transfer process. In the “Fig. 10” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes the comparison between the empirical U (unit: Wm-2K-1) and the forecasted Tamb (unit: ℃) with their respective actual values. In the “Fig. 11” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) and temperature (unit: ℃) of actual execution results of day-ahead two-layer control commands with 30 bitumen tanks and their temperature transfer process. In the “Fig. 12” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) and temperature (unit: ℃) of real-time predictive control results of ANN-based control commands with 30 bitumen tanks and (b) their temperature transfer process. In the “Fig. 13” sheet, the x-axis describes the time variable (unit: h), and the y-axis describes power (unit: MW) of comparison of electricity exchange curves with the power grid under different control methods.