@article{hu_shirsat_muthukaruppan_li_zhang_tang_baran_lu_2024, title={Adaptive cold-load pickup considerations in 2-stage microgrid unit commitment for enhancing microgrid resilience}, volume={356}, ISSN={["1872-9118"]}, DOI={10.1016/j.apenergy.2023.122424}, abstractNote={In an extended main grid outage spanning multiple days, load shedding serves as a critical mechanism for islanded microgrids to maintain essential power and energy reserves that are indispensable for fulfilling reliability and resiliency mandates. However, using load shedding for such purposes leads to increasing occurrence of cold load pickup (CLPU) events. This study presents an innovative adaptive CLPU model that introduces a method for determining and incorporating parameters related to CLPU power and energy requirements into a two-stage microgrid unit commitment (MGUC) algorithm. In contrast to the traditional fixed-CLPU-curve approach, this model calculates CLPU duration, power, and energy demands by considering outage durations and ambient temperature variations within the MGUC process. By integrating the adaptive CLPU model into the MGUC problem formulation, it allows for the optimal allocation of energy resources throughout the entire scheduling horizon to fulfill the CLPU requirements when scheduling multiple CLPU events. The performance of the enhanced MGUC algorithm considering CLPU needs is assessed using actual load and photovoltaic (PV) data. Simulation results demonstrate significant improvements in dispatch optimality evaluated by the amount of load served, customer comfort, energy storage operation, and adherence to energy schedules. These enhancements collectively contribute to reliable and resilient microgrid operation.}, journal={APPLIED ENERGY}, author={Hu, Rongxing and Shirsat, Ashwin and Muthukaruppan, Valliappan and Li, Yiyan and Zhang, Si and Tang, Wenyuan and Baran, Mesut and Lu, Ning}, year={2024}, month={Feb} }
 @article{hu_li_zhang_shirsat_muthukaruppan_tang_baran_lubkeman_lu_2021, title={A Load Switching Group based Feeder-level Microgrid Energy Management Algorithm for Service Restoration in Power Distribution System}, ISSN={["1944-9925"]}, DOI={10.1109/PESGM46819.2021.9638231}, abstractNote={This paper presents a load switching group based energy management system (LSG-EMS) for operating microgrids on a distribution feeder powered by one or multiple grid-forming distributed energy resources. Loads on a distribution feeder are divided into load switching groups that can be remotely switched on and off. The LSG-EMS algorithm, formulated as a mixed-integer linear programming (MILP) problem, has an objective function of maximizing the served loads while minimizing the total number of switching actions. A new set of topology constraints are developed for allowing multiple microgrids to be formed on the feeder and selecting the optimal supply path. Customer comfort is accounted for by maximizing the supply duration in the customer preferred service period and enforcing a minimum service duration. The proposed method is demonstrated on a modified IEEE 33-bus system using actual customer data. Simulation results show that the LSG-EMS successfully coordinates multiple grid-forming sources by selecting an optimal supply topology that maximizes the supply period of both the critical and noncritical loads while minimizing customer service interruptions in the service restoration process.}, journal={2021 IEEE POWER & ENERGY SOCIETY GENERAL MEETING (PESGM)}, author={Hu, Rongxing and Li, Yiyan and Zhang, Si and Shirsat, Ashwin and Muthukaruppan, Valliappan and Tang, Wenyuan and Baran, Mesut and Lubkeman, David and Lu, Ning}, year={2021} }
 @article{li_zhang_hu_lu_2021, title={A meta-learning based distribution system load forecasting model selection framework}, volume={294}, ISSN={["1872-9118"]}, DOI={10.1016/j.apenergy.2021.116991}, abstractNote={This paper presents a meta-learning based, automatic distribution system load forecasting model selection framework. The framework includes the following processes: feature extraction, candidate model preparation and labeling, offline training, and online model recommendation. Using load forecasting needs and data characteristics as input features, multiple metalearners are used to rank the candidate load forecast models based on their forecasting accuracy. Then, a scoring-voting mechanism is proposed to weights recommendations from each meta-leaner and make the final recommendations. Heterogeneous load forecasting tasks with different temporal and technical requirements at different load aggregation levels are set up to train, validate, and test the performance of the proposed framework. Simulation results demonstrate that the performance of the meta-learning based approach is satisfactory in both seen and unseen forecasting tasks.}, journal={APPLIED ENERGY}, author={Li, Yiyan and Zhang, Si and Hu, Rongxing and Lu, Ning}, year={2021}, month={Jul} }