Deep Learning Based Hurricane Resilient Coplanning of Transmission Lines, Battery Energy Storages, and Wind Farms

In this article, a multistage model for expansion coplanning of transmission lines, battery energy storages, and wind farms (WFs) is presented considering resilience against extreme weather events. In addition to high-voltage alternating current lines, multiterminal voltage source converter based high-voltage direct current lines are planned to reduce the impact of high-risk events. To evaluate the system resilience against hurricanes, probable hurricane speed scenarios are generated using Monte Carlo simulation. The fragility curve concept is utilized for calculating the failure probability of lines due to extreme hurricanes. Based on each hurricane damage, the probable scenarios are incorporated in the proposed model. Renewable portfolio standard policy is modeled to integrate high penetration of WFs. To deal with the wind power and load demand uncertainties, a chronological time-period clustering algorithm is introduced for extracting representative hours in each planning stage. A deep learning approach based on bidirectional long short-term memory networks is presented to forecast the yearly peak loads. The mixed-integer linear programming formulation of the proposed model is solved using a Benders decomposition algorithm. A modified IEEE RTS test system is used to evaluate the proposed model effectiveness.

Automated summary

This article presents a multistage model for expansion coplanning of transmission lines, battery energy storages, and wind farms, taking into account resilience against extreme weather events. The model incorporates high-voltage direct current lines and uses Monte Carlo simulation to evaluate system resilience against hurricanes. The study also introduces deep learning and clustering algorithms to handle uncertainties in wind power and load demand.