Secur ity region ‐ based power system operation guides operators in a fast and relevant decision ‐ making process as to what conditions r equire operators' actions. The key to this approach is the manne r in which effective attr ibutes are extracted among the network's operating var iabl es. This paper reconstr ucts the secur ity region of power system with high infor mation conten t. The secur ity region of power system is constr ucted by means of th e static secur ity boun dar ies such as s tatic vol tage stability limit, generator output power limit, and transfor mer and transmission line ther mal limits by increasing loading factor along var io us directions until these limits are violat ed. Then, the secur ity region is descr ibed by means of effective features set that contain maximum infor m ation content. In this paper, nonlinea r feature extraction te chniques have been propose d to dimensiona lity reduction and rel evant extraction of power system operating var iables. Convex and nonco nvex techniques of feature extraction are analyzed based on a mutual infor matio n index and generaliza tion er ror. The simulation results on the IEEE 9 ‐ bus and the IEEE 118 ‐ bus test systems demonstrate the effectiveness of the propose d method for descr ibing the secur ity region by consider ing high infor mat ion content.

Keywords