Devender Singh

Short-term load forecasting methods: A review

Short-term load forecasting methodsFor decision makers in the electricity sector, the decision process is complex with several different levels that have to be taken into consideration. These comprise for instance the planning of facilities and an optimal day-to-day operation of the power plant. These decisions address widely different time-horizons and aspects of the system. For accomplishing these tasks load forecasts are very important. This paper presents a comprehensive survey of the short term load forecasting. It also reviews various methodologies for short term load forecasting (STLF). Authors strongly believe that this survey article shall be very much helpful to the researchers working in the field of short term load forecasting for finding out the appropriate references and future work.

Effect of voltage step constraint and load models in optimal location and size of distributed generation

The distributed generation planning (DGP) in distribution system is affected with load models. Further, The size of distributed generation is also affected with voltage step constraints. In previous works, the effects of load models and voltage step constraint, in distributed generation planning (DGP), have not been studied together by the researchers so for. In this paper, voltage step constraint, along with usual constraints i.e. bus voltage limits and line capacity limits, and basic load models have been considered in DGP. The study has been carried out in 38 bus test system using incremental power flow and exhaustive search method. The results show that optimal location and size along with intake power from grid are significantly affected by voltage step constraint and load models.

Optimal feature selection using elitist genetic algorithm

A method of feature selection using elitist Genetic Algorithm is proposed in this work. Stratified-tenfold-cross-validation classification accuracy is used as fitness function. The method developed can detect redundant and irrelevant features, consequently producing the optimal feature set. The algorithm is carried out on the four benchmark datasets. Results of the experiments carried out shows that the algorithm developed selects the best set of features in terms of stratified-tenfold-cross-validation classification accuracy. Finally, the results obtained are compared with established results for the same datasets. Improvement in the size of selected subsets are also demonstrated.

Optimal Location and Size of Different Type of Distributed Generation with Voltage Step Constraint and Mixed Load Models

The optimal location and size of distributed generation in distribution network are essentially affected by type of DG, constraints, and loading condition. The type of distributed generation (DG) categorized on the basis of their terminal characteristic in terms of active and reactive power delivering capability have been considered for study. The voltage step change that occurs on sudden disconnection of DG is one of constraints to limit the size of DG more than the voltage level constraint. The loads connected to network are normally voltage dependent and varies with seasonal atmospheric conditions. The voltage dependency and seasonal variation of load necessitate to represent the load by load models for analysis. In this paper, the study has been carried out for distributed generation planning (DGP) for different type of DG in 38-bus test distribution system with voltage step constraint including normally considered constraints i.e. bus voltage constraint, line power capacity constraint, and seasonal mixed load models. The analysis shows that optimal location and size are significantly affected by type of DG, voltage step constraint, and load models.

Differential Evolution-Based Matched Wavelet for Differential Protection of Transformer

The work proposes a matched wavelet method for detection and discrimination of inrush and fault waveform in power transformers. The method rests on the concept that if analyzing wavelet is specialized to have shape matching with the waveform being analyzed (fault or inrush) its discrimination ability can improve drastically. The matched wavelet for inrush and fault waveforms is developed using Differential Evolution (DE) algorithm. It is established that the proposed method has sub-cycle (nearly half-cycle) discrimination ability. The method was tested by generating waveforms for all the angles to test its discrimination ability.

Butterfly Optimizer for Placement and Sizing of Distributed Generation for Feeder Phase Balancing

The present work investigates a new strategy of applying single-phase distributed generations (DGs) for the problem of phase load balancing. The work demonstrates that single-phase DG can be applied at specific location and phase so that overall phase loads are balanced at the root node. The problem of suitable size, bus-phase location of DGs is a mixed integer nonlinear programming (MINLP) problem. This problem is attempted using butterfly optimizer to get solution.

Fuzzy Rough Set-Based Feature Selection with Improved Seed Population in PSO and IDS

In this paper, fuzzy lower approximation-based fuzzy rough set is used for selection of features. A distributed sampling (DS)-based initialization method is introduced to pick better seed population, in particle swarm optimization (PSO) and intelligent dynamic swarm (IDS). PSO and IDS are used for simultaneously selecting the appropriate feature subset. Fitness function for these computations is fuzzy rough dependency measure. Using the proposed initialization, while using PSO and IDS, improvement in size of selected subset of features with improved classification accuracy is also demonstrated.

Butterfly Constrained Optimizer for Constrained Optimization Problems

An extension of the new optimization algorithm, butterfly optimizer (BO) for the constrained optimization problem is discussed in this paper. This version of BO is called butterfly constrained optimizer (BCO) which mimics the mate-locating behaviors of male butterfly and his behavior toward sunspots. In BCO, the location of male butterflies presents the trial solutions, and sunspots and dark-spots represent the feasible and infeasible region of search space. Two major mate-locating behaviors, patrolling and perching, are applied to generate new location of butterflies toward the feasible reason of search space to optimize the problem without violating any constraints. In this paper, five benchmark constrained optimization problems are considered to analyze the performance of BCO, and the benchmark results are compared with well-known state-of-the-art constrained techniques. Comparative result shows that the performance of BCO concerning its optimization capability, efficiency, and accuracy is better than other.