A novel grid-oriented dynamic weight parameter based improved variant of Jaya algorithm

Leghari, Zohaib Hussain; Hassan, Mohammad Yusri; Said, Dalila Mat; Jumani, Touqeer Ahmed; Memon, Zubair Ahmed

doi:10.1016/j.advengsoft.2020.102904

Cited by 14 publications

(8 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, DGs are directly integrated to the consumer side, unlike the centrally located power generating units situated far away from load centers and resulting in higher transmission losses [ 3 – 6 ]. However, connecting DG of inappropriate size to non-optimal location results in higher power losses and total cost, therefore offsetting the primary goal of connecting it to the distribution networks [ 7 – 10 ]. The optimal allocation of DGs, involves determining the best sizes and locations to satisfy the required goals while adhering to distribution network constraints.…”

Section: Introductionmentioning

confidence: 99%

Parallel operated hybrid Arithmetic-Salp swarm optimizer for optimal allocation of multiple distributed generation units in distribution networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

The installation of Distributed Generation (DG) units in the Radial Distribution Networks (RDNs) has significant potential to minimize active power losses in distribution networks. However, inaccurate size(s) and location(s) of DG units increase power losses and associated Annual Financial Losses (AFL). A comprehensive review of the literature reveals that existing analytical, metaheuristic and hybrid algorithms employed on DG allocation problems trap in local or global optima resulting in higher power losses. To address these limitations, this article develops a parallel hybrid Arithmetic Optimization Algorithm and Salp Swarm Algorithm (AOASSA) for the optimal sizing and placement of DGs in the RDNs. The proposed parallel hybrid AOASSA enables the mutual benefit of both algorithms, i.e., the exploration capability of the SSA and the exploitation capability of the AOA. The performance of the proposed algorithm has been analyzed against the hybrid Arithmetic Optimization Algorithm Particle Swarm Optimization (AOAPSO), Salp Swarm Algorithm Particle Swarm Optimization (SSAPSO), standard AOA, SSA, and Particle Swarm Optimization (PSO) algorithms. The results obtained reveals that the proposed algorithm produces quality solutions and minimum power losses in RDNs. The Power Loss Reduction (PLR) obtained with the proposed algorithm has also been validated against recent analytical, metaheuristic and hybrid optimization algorithms with the help of three cases based on the number of DG units allocated. Using the proposed algorithm, the PLR and associated AFL reduction of the 33-bus and 69-bus RDNs improved to 65.51% and 69.14%, respectively. This study will help the local distribution companies to minimize power losses and associated AFL in the long-term planning paradigm.

show abstract

Section: Introductionmentioning

confidence: 99%

Parallel operated hybrid Arithmetic-Salp swarm optimizer for optimal allocation of multiple distributed generation units in distribution networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…A number of solutions [42,43] have been suggested to prevent premature convergence in optimization-based algorithms, with one particularly significant study being carried out by Zhang Y et al [44], who proposed that in the case of a premature convergence The proposed WOA-FS optimally selected those minimum number of highly important features that attained maximum classification accuracy for any given volume of consumption data and extracted features (as depicted in the square matrix, where Con n f n represents Con n : consumer number and f n : feature number). Before initiating the feature selection process through WOA, the number of iterations, number of search agents, convergence criteria, search space boundaries, decision variables, and the learning classifier had to be decided.…”

Section: Proposed Feature-engineering Methodsmentioning

confidence: 99%

“…A number of solutions [42,43] have been suggested to prevent premature convergence in optimization-based algorithms, with one particularly significant study being carried out by Zhang et al [44], who proposed that in the case of a premature convergence problem, the best existing solution should be preserved and the mutation process should continue until an improved solution is found; once an improved solution is found, the current optimal solution is updated, and the mutation process is stopped. In the current study, in order to avoid the problem of premature convergence, humpback whales in the WOA technique, during the prey search phase, searched for prey in a random manner according to their relative positions to one another.…”

Section: Proposed Feature-engineering Methodsmentioning

confidence: 99%

A Novel Feature-Engineered–NGBoost Machine-Learning Framework for Fraud Detection in Electric Power Consumption Data

Hussain

Mustafa

Al-Shqeerat

et al. 2021

Sensors

View full text Add to dashboard Cite

This study presents a novel feature-engineered–natural gradient descent ensemble-boosting (NGBoost) machine-learning framework for detecting fraud in power consumption data. The proposed framework was sequentially executed in three stages: data pre-processing, feature engineering, and model evaluation. It utilized the random forest algorithm-based imputation technique initially to impute the missing data entries in the acquired smart meter dataset. In the second phase, the majority weighted minority oversampling technique (MWMOTE) algorithm was used to avoid an unequal distribution of data samples among different classes. The time-series feature-extraction library and whale optimization algorithm were utilized to extract and select the most relevant features from the kWh reading of consumers. Once the most relevant features were acquired, the model training and testing process was initiated by using the NGBoost algorithm to classify the consumers into two distinct categories (“Healthy” and “Theft”). Finally, each input feature’s impact (positive or negative) in predicting the target variable was recognized with the tree SHAP additive-explanations algorithm. The proposed framework achieved an accuracy of 93%, recall of 91%, and precision of 95%, which was greater than all the competing models, and thus validated its efficacy and significance in the studied field of research.

show abstract

“…In contemporary literature, numerous studies [53][54][55][56][57][58][59][60][61][62][63][64] have proved the dominating performance of Jaya and Rao algorithms over different optimization algorithms applied in diverse fields. However, the Rao and Jaya algorithms also suffer from deficiencies of slow and premature convergence as they lose population diversity [63,[65][66][67].…”

Section: Existing Research and Itsmentioning

confidence: 99%

Parameter-Free Improved Best-Worst Optimizers and Their Application for Simultaneous Distributed Generation and Shunt Capacitors Allocation in Distribution Networks

Leghari

Hussain

Memon

et al. 2022

International Transactions on Electrical Energy Systems

Self Cite

View full text Add to dashboard Cite

This paper proposes parameter-free two best-worst optimizers (BWOs) that combine the searching capabilities of Jaya and Rao-1 algorithms to intensify their exploration and exploitation capabilities. For the proposed first optimizer, BWO-1, parallel taxonomy has been adopted for the Jaya and Rao-1 combination to obtain dual sets of updated solutions for a given current solution set. For the proposed second optimizer, BWO-2, along with the parallel taxonomy, a subloop of random scaling factors has been introduced in the solution updating mechanism of both standard Jaya and Rao-1 algorithms to generate multiple sets of updated solutions in a single iteration. The best solutions from obtained multiple solution-sets will survive only and lead to the next iteration. Hence, the proposed solution updating mechanisms for BWO-1 and BWO-2 increase the probability of getting a quality solution under set conditions. The ability and scalability of BWO-1 and BWO-2 were assessed, solving the optimization problem of power loss reduction and voltage deviation minimization in the IEEE 33-bus and 69-bus test systems. The results show that the BWO-2 exhibited a lead of 2.97%, 1.83%, and 0.72% over the Rao-1, Jaya, and BWO-1 techniques, respectively. Besides, the BWO-2 achieves up to 38.76% more reduction in power losses against the existing standard, improved, and hybrid optimization techniques.

show abstract

A novel grid-oriented dynamic weight parameter based improved variant of Jaya algorithm

Cited by 14 publications

References 49 publications

Parallel operated hybrid Arithmetic-Salp swarm optimizer for optimal allocation of multiple distributed generation units in distribution networks

Parallel operated hybrid Arithmetic-Salp swarm optimizer for optimal allocation of multiple distributed generation units in distribution networks

A Novel Feature-Engineered–NGBoost Machine-Learning Framework for Fraud Detection in Electric Power Consumption Data

Parameter-Free Improved Best-Worst Optimizers and Their Application for Simultaneous Distributed Generation and Shunt Capacitors Allocation in Distribution Networks

Contact Info

Product

Resources

About