Huo Limin

Bayesian networks-based approach for power systems fault diagnosis

In this paper, three element-oriented models based on simplified Bayesian networks with Noisy-Or and Noisy-And nodes are proposed to estimate the faulty section of a transmission power system. The three models are used to test if any transmission line, transformer, or busbar within a blackout area is faulty. They can deal with uncertain or incomplete data and knowledge relating to power system diagnosis, so they are flexible. The structures and initial parameters of the Bayesian networks depend on the prior knowledge of the domain experts. The parameters can be revised by using an error back propagation algorithm similar to the back-propagation algorithm for artificial neural networks. The fault diagnosis models do not vary with the change of the network structure, so they can be applied to any transmission power system. Furthermore, they have clear semantics, rapid reasoning, powerful error tolerance ability, and no convergence problem during the diagnosing procedure. Experimental tests show that the approach is feasible and efficient, so the prototype program based on the approach is promising to be used in a large transmission power system for online fault diagnosis.

Deployment strategy of WSN based on minimizing cost per unit area

Article history: Received 20 December 2012 Received in revised form 3 August 2013 Accepted 5 October 2013 Available online 12 October 2013

Bayesian Network Based Time-Sequence Simulation for Power System Reliability Assessment

In this paper, an approximate inference algorithm on Bayesian networks (BN) for reliability assessment of power systems by time-sequence simulation is presented. Based on uniformly distributed pseudo random numbers, the duration time sampling for a component state can be obtained through inverse transform method. According to the logical relationship of the power system to be assessed, the sampling of minimal state cut sets of the system and the system nodes sampling are obtained respectively. Thus, the corresponding sample sequence in forward sampling is available. When the amount of sample sequence is large enough, marginal and conditional statistic values are close to marginal and conditional probability of the node. Then the approximate inference results of the BN can be obtained. Numerical simulating results show the effectiveness of the proposed algorithm. It can easily identify the weaker components of a system in reliability, calculate the system reliability indices, and is suitable for a large-scale power system.

Reactive Power Optimization for distribution systems based on Dual Population Ant Colony Optimization

The dual population ant colony optimization (DPACO) was tried to be applied to power system dynamic reactive power optimization. The installation positions of capacitors were taken as obstacles, the capacities of capacitors installed were taken as the paths through which the ants climb over the obstacles and the mathematical models of the reactive power planning under the multiple load state were adopted. In running process, the pheromone was adjusted according to the antpsilas search results and the principle of pheromone modification and the convergence speed was fastened. At the same time, the dual population ant colony optimization (DPACO) avoided trapping in local optimum and increased the precision of reactive power optimization for doing well in global optimization. After optimization, the voltage quality was enhanced obviously and comprehensive fees decrease significantly. The running results show that dual population ant colony optimization (DPACO) applied to power system dynamic reactive power optimization is feasible and effective.

Novel method for power system fault diagnosis based on Bayesian networks

Three element-oriented Bayesian networks models are built to estimate the fault section of a power system. Each of them is composed of noisy-or and noisy-and nodes. The three models are used to locate three types of fault elements: transmission lines, transformers and bus bars respectively. The learning algorithm for network parameters is analogous to the back propagation algorithm of neural networks. Taking the sum of the mean-squared error between the expected values and the computed results of target variables as the minimizing optimization function, it adjusts the networks parameters continuously. According to the operation information of protective relays and circuit breakers, fault credibility of elements in the blackout area is calculated based on the structure of the Bayesian network. By comparing the resultant beliefs of possible fault elements, the fault element(s) is identified. The proposed approach can deal with uncertainties in fault section diagnosis, and the models have clear semantics, rapid reasoning, etc. The testing results for a real power system have shown that the fault diagnosis models are correct, efficient and are promising to be used in a large power system for on-line fault diagnosis.

Application of Rough Set Theory in the Fault Diagnosis of Distribution Line

Based on the rough set theory, a new distribution network fault diagnosis approach to deal with the imperfect alarm signals that caused by malfunction or failing operation of protection relays and circuit breakers, error in the communication equipment is proposed. Due to rough set theory can effectively handle the imprecise problems without any ancestor information except the data set itself, a decision table including all kinds of fault cases is established by considering the signals of protection relays and circuit breakers, and the approach can extract diagnosis rules from the set of fault samples directly. The inherent redundancy in the alarm information is exposed. Finally, a practical fault diagnosis program of the typical distribution network is proposed based on VC#. The result shows the validity of the proposed method.