The transformer fault diagnosis based on dissolved gas analysis is greatly affected by the uncertainties existing in measured data during oil sampling, handling and storage. This work aims to develop an efficient code matrix based on dissolved gas percentages for accurate fault diagnosis considering measurement uncertainties. Fuzzy system is utilized to produce the rules that map the limits of gas ratios for different fault types. Each gas percentage range is divided into three regions represented by three fuzzy memberships. The fuzzy system is then developed to relate the gas percentages to the fault type. The membership limits are then optimized by using heuristic algorithms in order to maximize the accuracy. Hybrid Grey Wolf Optimization (HGWO) algorithm is utilized to produce the diagnostic code matrix. The proposed code limits the impact of measurement uncertainties on the output fault diagnosis. Different levels of measurement uncertainties up to 20% are considered to validate the effectiveness of the new code in improving the diagnostic accuracy. The accuracies during the training and testing processes attained 97.45% and 95.45%, respectively, with the maximum uncertainty level of 20%. Moreover, randomly selected case studies representing various fault types are investigated using the proposed method. For each case study, various levels of uncertainties are imposed on the original data. The proposed method proved its easiness towards diagnosing transformer faults and robustness against measurement uncertainties.

With the tendency to move toward automated home energy management systems, the cooperative capacity of the smart grid “SG” became more and more significant. Distributed generation “DG”, in addition to the novel patterns of electricity production, enabled the two-way energy flow. The concern of this paper is on introducing an automated control technique for optimizing the operational performance of the DG units within the residential applications. This problem is formulated in a constrained-nonlinear optimization structure based on a detailed economic system. Genetic algorithm “GA” technique is used to solve this problem by defining the optimal settings of the DG units. Availability of two-way communication and the use of smart meters will enable online implementation and facilitate data collection within a fully automated system. Based on certain tariffs and realistic load curves, many scenarios of operation are analyzed and assessed. The results show that using optimization technique in cooperative with advanced smart meters can enhance the economic situation of the overall grid significantly. Copyright © 2016 John Wiley & Sons, Ltd.

Future smart grids will require an observable, controllable and flexible network architecture for reliable and efficient energy delivery. The use of artificial intelligence and advanced communication technologies is essential in building a fully automated system. This paper introduces a new technique for online optimal operation of distributed generation (DG) resources, i.e. a hybrid fuel cell (FC) and photovoltaic (PV) system for residential applications. The proposed technique aims to minimize the total daily operating cost of a group of residential homes by managing the operation of embedded DG units remotely from a control centre. The target is formed as an objective function that is solved using genetic algorithm (GA) optimization technique. The optimal settings of the DG units obtained from the optimization process are sent to each DG unit through a fully automated system. The results show that the proposed technique succeeded in defining the optimal operating points of the DGs that affect directly the total operating cost of the entire system

The study presents a framework for online power system dynamic stability enhancement with a new market-based rescheduling approach. The objective is to solve the online transient and oscillatory stability constrained economic power dispatch problem using a mixture of a modified particle swarm optimisation (PSO) and artificial neural network. The problem is formulated as a non-linear constrained optimisation problem, and PSO has been used as optimisation tool to search for the optimal solution within the available hyperspace. For reducing the time consumed in the computations, neural network has been used to assess power system dynamic stability. The rescheduling process based on the market participants’ bids is used as a remedial action to maintain system operation sufficiently away from the limits of system stability. The goal of the approach is to minimise the additional payments arising from the rescheduling needed to enhance system dynamic stability. The critical clearing time corresponding to the critical contingency is considered as an index for transient stability, while system minimum damping of oscillation is considered as an indicator for oscillatory stability. The proposed framework is implemented on a 66-bus test system, and the results obtained are found to be satisfactory.

This paper presents an application of Artificial Neural Network (ANN) for monitoring transient stability assessment (TSA) considering system topology changes. Offline trained ANN makes use of the advance of online TSA in specifying the proper remedial action for real time power system operation to counteract the system instability. The training of ANN is executed using important selected features as inputs and critical fault clearing time (CCT) at pre-selected set of critical contingencies as desired target. CCT is considered as an indicator for system transient stability criterion. Multilayer feed forward neural network trained with back-propagation algorithm is used to provide the CCT. To demonstrate the effectiveness of the ANN in estimation of TSA considering various system topologies, the method is verified on 66-bus power system and the results are compared with time domain simulation (TDS). The simulation results indicate that the ANN provides a fast and accurate tool to evaluate online power system transient stability with acceptable accuracy.