Methodology for a Security/Dependability Adaptive Protection Scheme Based on Data Mining

Abstract

The power industry is currently in the process of re-inventing itself. The unbundling of the traditional monopolistic structure that gave birth to a deregulated electricity market, the mass tendency towards a greener use of energy, the new emphasis on distributed generation and alternative renewable resources, and new emerging technologies have revolutionized the century old industry.Recent blackouts offer testimonies of the crucial role played by protection relays in a reliable power system. It is argued that embracing the paradigm shift of adaptive protection is a fundamental step towards a reliable power grid. The adaptive philosophy of protection systems acknowledges that relays may change their characteristics in order to tailor their operation to prevailing system conditions. The purpose of this dissertation is to present methodology to implement a security/dependability adaptive protection scheme. It is argued that the likelihood of hidden failures and potential cascading events can be significantly reduced by adjusting the security/dependability balance of protection systems to better suit prevailing system conditions.

Power Quality Disturbances Feature Selection and Recognition Using Optimal Multi-Resolution Fast S-Transform and CART Algorithm

“…CART is an effective binary recursive partitioning algorithm that can automatically construct the ODT and complete feature selection according to the classification effect of the features at each node. Thereby, the feature computation is reduced, the structure of the classifier is simplified, and the classification efficiency and accuracy are improved [38][39][40]. The processing of the CART algorithm is described as follows (F indicates the current PQ sample set, and F_attributelist represents the current candidate feature set):…”

“…With these CP values as the threshold, pruning is carried out in order. This can simplify the process of classifier design while effectively maintaining recognition accuracy [38,40].…”

Data-Mining-Based Intelligent Differential Relaying for Transmission Lines Including UPFC and Wind Farms

“…DTs are grown through a systematic process known as recursive binary partitioning; a divide and conquer approach where successive questions with yes/no answers are asked in order to partition the sample space [15], [16]. Variable importance is one of the key performance indices of DT that provides information on the contribution of features to the decision making process and thus, selects the optimal numbers of features for final decision making.…”

Enhanced Protection Security Using the System Integrity Protection Scheme (SIPS)

“…An algorithm to support relay zone 3 operation using synchrophasor data is proposed in [18]. Security of power system protection operation is defined as the measure of certainty that the relay will not operate incorrectly even under any stressed condition [19]. Use of modern technologies can reduce the risk of large systemwide disturbance and blackout by preserving system integrity under adverse situations.…”