Zhengmao Li

Daniyaer Paizulamu, Lin Cheng, Ning Qi et al.

Uncertainties in balancing generation and load in low-carbon industrial microgrids (IMGs) make hybrid energy storage systems (HESS) crucial for their stable and economic operation. Existing model predictive control (MPC) techniques typically enforce periodic state of charge (SOC) constraints to maintain long term stability. However, these hard constraints compromise dispatch flexibility near the end of the prediction horizon, preventing sufficient energy release during critical peaks and leading to optimization infeasibility. This paper eliminates the periodic SOC constraints of individual storage units and proposes a novel full-timescale hierarchical MPC scheduling framework. Specifically, comprehensive physical and cost models are established for the HESS composed of flywheel, battery, compressed-air, and hydrogen-methanol energy storage. The control problem is decoupled into a hierarchical MPC architecture. Furthermore, a novel adaptive feedback mechanism based on micro trajectory inverse projection (MTIP) is embedded into the scheduling process, accurately mapping the high frequency dynamic buffering capabilities of lower tier storages into the upper decision space to generate dynamic boundaries. Experiments using 14 consecutive months of second-level data from a real-world IMG validate the effectiveness of the proposed method, demonstrating its significant superiority over existing approaches. By effectively preventing limit violations and deadlocks in lower-tier storages under extreme fluctuations, it achieves a 97.4\% net load smoothing rate and a 62.2\% comprehensive cycle efficiency.

Dafang Zhao, Xihao Piao, Zheng Chen et al.

Accurate forecasting of the electrical load, such as the magnitude and the timing of peak power, is crucial to successful power system management and implementation of smart grid strategies like demand response and peak shaving. In multi-time-scale optimization scheduling, rolling optimization is a common solution. However, rolling optimization needs to consider the coupling of different optimization objectives across time scales. It is challenging to accurately capture the mid- and long-term dependencies in time series data. This paper proposes Multi-pofo, a multi-scale power load forecasting framework, that captures such dependency via a novel architecture equipped with a temporal positional encoding layer. To validate the effectiveness of the proposed model, we conduct experiments on real-world electricity load data. The experimental results show that our approach outperforms compared to several strong baseline methods.

Dafang Zhao, Zheng Chen, Zhengmao Li et al.

Heat, Ventilation and Air Conditioning (HVAC) systems play a critical role in maintaining a comfortable thermal environment and cost approximately 40% of primary energy usage in the building sector. For smart energy management in buildings, usage patterns and their resulting profiles allow the improvement of control systems with prediction capabilities. However, for large-scale HVAC system management, it is difficult to construct a detailed model for each subsystem. In this paper, a new data-driven room temperature prediction model is proposed based on the k-means clustering method. The proposed data-driven temperature prediction approach extracts the system operation feature through historical data analysis and further simplifies the system-level model to improve generalization and computational efficiency. We evaluate the proposed approach in the real world. The results demonstrated that our approach can significantly reduce modeling time without reducing prediction accuracy.