Preventive Dynamic Security Control of Power Systems Based on Pattern Discovery Technique

Abstract

This paper presents a statistical learning-based method for preventive dynamic security control of power systems. Critical operating variables regarding system dynamic security are first selected via a distance-based feature estimation process. An unsupervised learning procedure called pattern discovery (PD) is then performed in the space of the critical variables to extract the subtle structure knowledge called patterns. The patterns are geometrically non-overlapped hyper-rectangles, representing the system dynamic secure/insecure regions and can be explicitly presented to provide decision support for real-time security monitoring and situational awareness. By formulating the secure patterns into a standard optimal power flow (OPF) model, the preventive control against dynamic insecurities can be efficiently and transparently attained. The proposed method is validated on the New England 39-bus system considering both single-and multi-contingency conditions.

Large-scale network security situational awareness based on association rule research

“…Classification means getting the character of user' behavior and rules that extracted by data processing, and matches it with the rules or patterns which is exist in the knowledge base, so it can judge whether the administrator should be informed, and achieves the dynamic prevention [6] . The rule base need to be updated when faced with new rules or patterns [7] , and the rules in the base need to be merged as well, then the automatic learning and updating of the rule base will be come true. As a means of decision support, the rules that new added to the data base could timely detect the attacks in the network.…”

Preventive and Emergency Control of Power System for Transient Stability Enhancement

“…Transient stability enhancement through generation rescheduling can be found in [7][8][9][10][11][12][13][14]. In [7], a hybrid approach is proposed for on-line security evaluation and generator rescheduling as preventive control.…”

“…In [13], risk based coordinated generation rescheduling and load shedding has been suggested for improving the transient stability of the system. Pattern discovery based preventive control is suggested in [14] to improve the dynamic security of the system. However, it is not possible to prevent power system from collapse for the entire contingency set for all the operating conditions using only the preventive control actions [10].…”

Advanced Pattern Discovery-based Fuzzy Classification Method for Power System Dynamic Security Assessment

“…In [14], [15], an alternative knowledge extraction technique, called Pattern Discovery (PD) [16], [17], is applied in dynamic security assessment and stability control of harmful disturbances. This new technique has shown better prediction performance than other methods.…”

“…Those patterns, when discovered in a power system dynamic security database, can represent the secure/insecure regions of the system. With the discovered regions, stability assessment can be made by a distance-based classification procedure [14] and stability control can be realized by driving an operating point from an insecure region to a secure region [15].…”