In distributed networks, wind turbine generators (WTGs) are to be optimally sized andpositioned for cost-effective and efficient network service. Various meta-heuristic algo-rithms have been proposed to allocate WTGs within microgrids. However, the ability ofthese optimizers might not be guaranteed with uncertainty loads and wind generations.This paper presents novel meta-heuristic optimizers to mitigate extreme voltage dropsand the total costs associated with WTGs allocation within microgrids. Arithmetic opti-mization algorithm (AOA), coronavirus herd immunity optimizer, and chimp optimizationalgorithm (ChOA) are proposed to manipulate these aspects. The trialed optimizers aredeveloped and analyzed via Matlab, and fair comparison with the grey wolf optimization,particle swarm optimization, and the mature genetic algorithm are introduced. Numericalresults for a large-scale 295-bus system (composed of IEEE 141-bus, IEEE 85-bus, IEEE69-bus subsystems) results illustrate the AOA and the ChOA outperform the other opti-mizers in terms of satisfying the objective functions, convergence, and execution time. Thevoltage profile is substantially improved at all buses with the penetration of the WTG withsatisfactory power losses through the transmission lines. Day-ahead is considered genericand efficient in terms of total costs. The AOA records costs of 16.575M$/year with areduction of 31% compared to particle swarm optimization.1INTRODUCTION1.1MotivationDepending on the size and allocation of renewable energysources (RESs), microgrids can effectively handle large numberof distributed generators (DGs) while maximizing economicand environmental aspects [1, 2 ]. Microgrids have certainunique features that make traditional optimization algo-rithms ineffective for RESs sizing and positioning, such as(i) Microgrids integrate DGs and RESs, which are inherentlyunpredictable and intermittent [3], (ii) microgrids are oftenformed interconnected by subsystems, which requires morecomputation, (iii) the traditional optimization and power flowThis is an open access article under the terms of theCreative Commons Attribution-NonCommercial-NoDerivsLicense, which permits use and distribution in any medium, provided theoriginal work is properly cited, the use is non-commercial and no modifications or adaptations are made.© 2023 The Authors.IET Renewable Power Generationpublished by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.methods are nonlinear problems, finding the global minimum isthus not assured in multi-energy subsystem [4], (iv) necessitiesto design future recommendation and possibility validationsfor future smart grids, (v) the increasing complexity of energydemand, which is increased by introducing certain load varietiessuch as plug-in electric vehicles and the coronavirus pandemicimpacts. The former fluctuates dramatically in the day-aheadmarket and the latter pandemic has a major effect on boththe generation and demand [5], and therefore on the voltageprofile. Several challenges arise in constructing meta-heuristics,including the hyper parameters, which necessitate intenseiterative labour. Besides, developing the solution criteria andgoal function need extensive research in order to meet par-ticular requirements. Accordingly, .