Search

The major obstacle in designing of the wind turbine/photovoltaic/battery storage system lies in the task of choosing the most optimum solution while simultaneously considering techno-economic objectives. Consequently, this study provides a distinctive amalgamation of multi-objective multi-perspective and group multi-criteria decision-making methodologies to ascertain collections of Pareto optimum configurations and to weight, rank, and pick up the most desirable optimum solutions that represent best trade-off between conflicting objectives. In this paper, the multi-objective Dragon fly algorithm is developed based on mutation scheme and crossover tactic algorithm is advanced to handle a lack of diversity and poor convergence, while non-dominated sorting and crowding distance strategy is addressed to store the best found optimum solutions in the achieve. Loss of load probability, excess energy, and life cycle cost are conflicting techno-economic objectives solved by multi-objective method. The optimum Pareto front solutions are ranked based on hybrid multi-criteria decision-making method for determining the most favorable solution for the WT/PV/BS system. The experimental outcomes indicated that the developed approach has a distinct performance in constructing a collection of Pareto front solutions in terms of diversity, converge, and convergence. Moreover, it demonstrates outstanding results when compared to well-organized multi-objective optimization methods. The future direction can be accomplished by applying the proposed hybrid sizing methodology for solving gird-connected system along with electric vehicle based on techno-economic scenarios. [ABSTRACT FROM AUTHOR]

• A new MPALW method is developed to minimize the RMSE using real experimental data. • The MPALW is used to extract the parameters of the SD and DD PV modules' models. • MPALW is outperformed well-published methods using several statistical indicators. • MPALW can accurately estimate the I-V and P-V data curves. Efficient and accurate estimation parameters of the PV model from real experimental data is crucial for modeling, increasing investments, and determining the actual performance before installing the PV panels. Recently, several stochastic methods have been proposed to extract the parameters of the PV module/cells optimally. However, some of these approaches have restrictions in terms of exploration and exploitation capacities individually or combined due to their stochastic searching strategies. In this research work, Marine Predator Algorithm (MPA) is combined with Lambert W function to tackle the parameters extraction optimization problem for the single diode and double diode PV models and called (MPALW). The performance of the MPALW algorithm is tested by using real experimental data at seven sunlight and temperature settings. The MPALW shows an excellent agreement with obtained experimental data compared with other well-published algorithms. The findings of this research show that the MPALW algorithm can be utilized for real engineering applications such as smart grids, energy sector, and fault error detection. [ABSTRACT FROM AUTHOR]

This paper offers an electromagnetism-like (IEM) algorithm to estimate the five parameters of a single-diode PV module's model. IEM uses local search and improves movement step to increase the convergence to optimal solutions. The key of improvement is performed by adding a nonlinear equation to adjust the length of the particle in each iteration. Moreover, the total force formula is simplified to speed up the exploration for an optimal solution. Analyses are carried out by experimental data points at various operational conditions to show the stability and reliability of the proposed methods. The results of the proposed IEM algorithm show a better convergence speed and high accuracy compared with other models in the literature, which involves various statistical errors. The values of average root mean square error, mean bias error, standard deviation, average absolute error, and average test statistic of the proposed method are 589%, 0.51%, 0.19%, 46%, and 0.53, respectively. As a conclusion, the IEM algorithm presents better performance than other methods in the literature in terms of accuracy and convergence. [ABSTRACT FROM AUTHOR]

The paper presents a new multiple scenario multi-objective salp swarm optimization (MS-MOSS) algorithm to optimally size a standalone PV system. An accurate estimation of the number of PV modules and storage battery is crucial as it affects the system reliability and cost. Three scenarios have been presented focusing on Pareto optimal solutions by minimizing two conflicting objectives. Loss of load probability (LLP) and life-cycle cost (LLC) are considered to obtain the Pareto front. The iterative method is employed for validation of the superiority results of the proposed MS-MOSS algorithm. The results show that the scenarios are able to find Pareto optimal configuration at a high level of accuracy and at a very low cost. The proposed three scenarios are faster than iterative approach approximately by 158, 194.2, and 141.6 times, respectively. The third scenario outperforms other scenarios in terms of coverage and convergence of the distribution of solution to the Pareto front. As a conclusion, The MS-MOSS algorithm is found to be very effective in sizing of SAPV system. • A new multiple scenario multi-objective salp swarm optimization (MS-MOSS) is proposed. • An optimal size for a standalone PV system is found using MS-MOSS. • Three scenarios have been presented to obtain on Pareto optimal solutions. • The results demonstrate the efficiency of MS-MOSS for sizing of SAPV system. [ABSTRACT FROM AUTHOR]

The paper presents a new multiple scenario multi-objective salp swarm optimization (MS-MOSS) algorithm to optimally size a standalone PV system. An accurate estimation of the number of PV modules and storage battery is crucial as it affects the system reliability and cost. Three scenarios have been presented focusing on Pareto optimal solutions by minimizing two conflicting objectives. Loss of load probability (LLP) and life-cycle cost (LLC) are considered to obtain the Pareto front. The iterative method is employed for validation of the superiority results of the proposed MS-MOSS algorithm. The results show that the scenarios are able to find Pareto optimal configuration at a high level of accuracy and at a very low cost. The proposed three scenarios are faster than iterative approach approximately by 158, 194.2, and 141.6 times, respectively. The third scenario outperforms other scenarios in terms of coverage and convergence of the distribution of solution to the Pareto front. As a conclusion, The MS-MOSS algorithm is found to be very effective in sizing of SAPV system. • A new multiple scenario multi-objective salp swarm optimization (MS-MOSS) is proposed. • An optimal size for a standalone PV system is found using MS-MOSS. • Three scenarios have been presented to obtain on Pareto optimal solutions. • The results demonstrate the efficiency of MS-MOSS for sizing of SAPV system. [ABSTRACT FROM AUTHOR]

• The output power is conducted using 3D-PV model. • A new fusion of improved bi-archive multi-objective optimization algorithm is proposed. • A new hybrid MCDM method is considered to choose the most desirable configuration. • An accurate hybrid numerical method is used for validation of the proposed method. • Performance of optimum designs are evaluated for both cases: Malaysia and South Africa. Photovoltaic (PV) and Wind turbine (WT) systems are the most promising options for rural energy delivery. In the literature, numerous studies have simply considered only on economic efficiency, while maximizing dependability by a constant value for the given demand load. Moreover, a single set Pareto optimal front (PF) has been attained for the multi-objective optimization problem. Furthermore, the primary challenge of various the off-grid multiple renewable energy sources is excessive energy loss, resulting over/under sizing and a highly total cost for the system. Therefore, this paper presents a unique improved bi-archive approach to develop the diversity and convergence independently in order to find four optimum sets of PF solutions. In addition, a new integration based on best worst method (BWM) and preference ranking organization for enrichment evaluations (PROMETHEE II) method along with group decision making (GDM) mechanism are addressed to sort and rank the optimal sets PF solutions with full consistency ratios of the three experts opinions and high degree of stability in ranking configurations. The theoretical results based on actual hourly meteorological data in Malaysia and South Africa indicated that the suggested improved two-archive-BWM- PROMETHEE II-GDM method is not only able to construct a uniform set of Pareto optimal solutions with fast convergence and high diversity, but can also rank and select the most desired design for the PV/WT/Battery system. The optimum configurations of the two cases studies are composed of a single WT, 105 PV modules, and 69 batteries storages at zero LLP, 60185 ($) of LLC, and 13548018 (KWh) of P dump for Malaysia case study, meanwhile it composes of 16 WTs, 80 PV modules, and 69 batteries storage at zero of LLP, 66073 ($) of LCC, and 31371 (KWh) of P dump. The proposed standalone hybrid renewable energy sources system is verified and assessed in a comparison with existing hybrid methods in terms of increasing the reliability, lowering overall cost, and reducing wasted energy. [ABSTRACT FROM AUTHOR]

Extraction of the photovoltaic (PV) model parameters is critical for forecasting these systems' energy output. Numerous research have reviewed and presented approaches for figuring out the PV models parameter optimization problem in the literature. However, few studies have been undertaken to construct the objective function, or no review papers have been published on the applied methodologies for solving the equations of nonlinear, multi-variable, and complicated PV models based on the datasheet information or actual experimental data. Therefore, this study seeks to first explore the acquired approaches to solve the equations of PV models. Then, utilizing actual measured laboratory data collected under a variety of environmental circumstances, a hybrid approach for efficiently determining unknown the parameters of the single, double, and three diodes PV model has been developed. The proposed guaranteed convergence arithmetic optimization algorithm based on efficient modified third order Newton Raphson (GCAOA EmNR) method highlights important contributions to the literature in terms of methodology (explorer-exploiter phases) and objective function design. The experimental findings exhibit that the GCAOA EmNR minimizes the error to zero under diverse statistical criteria and environmental conditions. Moreover, the GCAOA EmNR beats all well-published approaches in the literature in terms of accuracy, stability, and convergence rate while requiring a reasonable amount of processing time. • An innovative GCAOA EmNR is presented to extract the parameters of the SD, DD, and TD PV model at various climatic conditions. • A hybrid methodology forecasts the output PV current using NR third-order convergence and adaptive LM damping parameter. • New quadratic and fourth convergences are included to broaden the PV models' search space. • A unique transition from localized to global strategy is proposed to update the lower and upper bounds. [ABSTRACT FROM AUTHOR]

The parameter determination based on experimental data aids in providing an accurate assessment for predicting the output current of the PV cells. This may be extremely helpful both practically and theoretically in the PV system simulation, optimization, and evaluation. Numerous stochastic methods have been widely utilized in recent decades to tackle the parameter extraction optimization problem. Hybrid methods that take advantage of two or more algorithms have been proposed by many to further enhance their accuracy, stability, and overall performance. However, the majority of the methods in the literature concentrate on the methodology, with few studies considering the formulation of the objective function, resulting in a theoretical gap in this area of study. In this work, a new improved arithmetic optimization method based on the adaption of Newton–Raphson and Levenberg–Marquardt damping parameter (IAOANRaLMp) is presented to globally extract the parameter of the single- and double-diode PV models. The experimental findings demonstrate that the proposed IAOANRaLMp approach performs exceptionally well in terms of minimizing error to zero for both models, as indicated by various statistical criteria and comparison with experimental data. [ABSTRACT FROM AUTHOR]

The (photovoltaic) PV models' performance is strongly dependent on their parameters, which are mainly standing on the utilized method and the formulated objective function. Therefore, extracting the PV models' parameters under several environmental conditions is crucial for maximizing its reliability, accuracy and reducing the system's overall cost. According to the scope of this problem, several methodologies have been extensively applied to tackle this problem. Thus, this paper presents an enhanced version of the well-known LSHADE (ELSHADE) method by integrating various contributions in the algorithm itself and the objective function to determine three diode PV models' parameters. In ELSHADE, the population is divided into two phases: a robust mutation scheme performs the first phase, and the chaotic-guided strategy is utilized in the second stage. Moreover, an improved Newton Raphson (INR) method is presented to address the I–V curve equation's chaotic behavior effectively. The results confirm that the proposed ELSHADE-INR can precisely find the global solutions by comparing it with state-of-the-art algorithms and its superiority demonstrated in several statistical criteria under real experimental data. The average values of root mean square error (RMSE), mean bias error, determination coefficient, deviation of RMSE, test statistical, absolute error, and CPU-execution time are 0.0060 and 5.88e-05, 0.9999, 2.54e-05, 0.0538, and 0.0042, 11.39s, respectively. We observed that the proposed ELSHADE is robust and stable, and very promising in its origin to obtain high-quality and accurate parameters. This paper is supported by https://aliasgharheidari.com/publications/ELSHADE.html. • An enhanced version of the LSHADE is proposed to extract the parameters of the PV model. • A robust mutation scheme performs the first phase and the chaotic-guided strategy is utilized in the second stage. • An improved NR (INR) method is presented to address the chaotic behavior of the I–V curve equation effectively. • The proposed ELSHADE-INR can precisely find the solutions of the three diode PV model. • The proposed ELSHADE-INR is robust and stable and very promising to obtain high-quality and accurate parameters. [ABSTRACT FROM AUTHOR]

Standalone photovoltaic (SAPV) systems have been considered as promising and fast development renewable energy sources due to free-noise, easy availability, and low-cost, especially for remote areas. However, the main disadvantages of these systems are low energy conversion and high capital cost. Therefore, many factors should be considered before installing the SAPV systems such as types of PV panels and configurations, mathematical models of PV module, storage battery, environmental criteria, sizing method based on techno-economic objectives, and selection the final optimum configuration. The goals of this paper are to presents a comprehensive review of the recent development in designing SAPV systems based on multi-objective optimization (MOO) and multi-criteria decision-making (MCDM) methodologies, including the mathematical models used in estimating the output power of the PV module and storage battery are also presented. Finally, the techno-economic criteria for assessing the performance of the SAPV system are considered. This will help the designers and customers to choose the most suitable design before installing the SAPV system. For supplementary resources and further discussions, please refer to the devoted homepage at http://aliasgharheidari.com. • Recent development in designing standalone photovoltaic system (SAPV) is reviewed. • Multi-objective optimization and multi-criteria decision-making methodologies are surveyed. • The mathematical models used in estimating the output power of the PV module and storage battery are also presented. • The techno-economic criteria for assessment the performance of the SAPV system are considered. [ABSTRACT FROM AUTHOR]

Sun energy is widely utilized to power stand-alone photovoltaic systems (SAPV). However, the lack of long term hourly meteorological data and inaccurate methods result in obstacles in designing the SAPV system. Therefore, an optimal sizing methodology is necessary to guarantee satisfactory performance. In this study, a new mutation adaptive differential evolution (MADE) based on a multi-objective optimization algorithm is presented to optimize the configuration of the off-grid SAPV system. Three conflict objectives are normalized, weighted, and then aggregated by mono-objective function to optimally size the off-grid stand-alone PV system. The performance of the proposed SAPV system is analyzed based on three types of batteries which are lead-acid, AGM, and lithium-ion. The results show that the optimal configuration based on lead-acid has less fitness function (f), life cycle cost (LCC), levelized cost of energy (LCE), with a high level of loss of load probability (LLP), and their values are 0.0268, 54,896 USD, 1.58USD, and 0.19%, respectively. Moreover, the optimal numbers of the PV modules (in series and parallel) and lead-acid battery are 9, 28, and 42, respectively. Therefore, the SAPV system based on lead-acid battery can be very suitable for real-world applications. • MADE method is presented for optimally size of the SAPV system. • An efficient mutation vector with using 2-Opt approach is proposed. • Dynamically adapting F and C R are proposed to boost the convergence rate. • MOO design of SAPV system through reliability and cost assessments. • The SAPV system's performance is analyzed based on three types of batteries. [ABSTRACT FROM AUTHOR]

• BHHO method is proposed to extract the parameters of the PV module's model. • Two different intervals of EE are used to improve the research direction. • Random steps inspired by FPA with keep using the LF concept to enrich the diversity of the algorithm. • An effective mutation scheme of the DE approach with the 2-Opt algorithm is introduced. • An adapting F in the mutation phase is proposed. In order to realize the performance of the PV model before being installed, it is often indispensable to develop reliable and accurate parameter identification methods for dealing with the PV models. Up to now, several stochastic methods have been proposed to analyze the feature space of this problem. However, some of the stochastic-based methods may present unsatisfactory results due to their insufficient exploration and exploitation inclinations, and the multimodal and nonlinearity existed in PV parameters extraction problems. In this paper, a Boosted Harris Hawk's Optimization (BHHO) technique is proposed to achieve a more stable model and effectively estimate the parameters of the single diode PV model. The BHHO method combines random exploratory steps of evolution inspired by the flower pollination algorithm (FPA) and a powerful mutation scheme of the differential evolution (DE) with 2-Opt algorithms. The proposed strategies not only help BHHO algorithm to accelerate the convergence rate but also assist it in scanning new regions of the search basins. The results demonstrate that the proposed BHHO is more accurate and reliable compared to the basic version and several well-established methods. The BHHO method was rigorously validated by using real experimental data under seven sunlight and temperature conditions. Furthermore, the statistical criteria indicate that the proposed BHHO method has lower errors among other peers, which is highly useful for real-world applications. [ABSTRACT FROM AUTHOR]

[Display omitted] • A hybrid algorithm for reliable and efficient parameter estimation of the PV model. • Significant advancements are achieved in methodology and objective function design. • Performance of the algorithm is analyzed with partial shading and noise effects. • Proposed approach achieves enhancements in the overall performance and accuracy. • It outperforms other algorithms in terms of accuracy, consistency, and convergence. A reliable methodology is essential for accurately estimating the parameters of PV models, enabling reliable performance evaluations, effective control studies, accurate analysis of partial shading effects, and optimal optimization of Photovoltaic (PV) systems. It ensures that the obtained parameters reflect the true characteristics of the PV system, leading to more accurate and reliable results in various applications. The existing literature extensively explores the utilization of powerful Metaheuristic Algorithms (MAs) to address the complex constrained optimization problem in PV systems and achieve optimal solutions. However, it is important to note that a significant portion of these MAs primarily concentrates on the development of methodologies, often overlooking the design of the objective function tailored for PV systems. This oversight has created a theoretical gap in this research domain, underscoring the necessity for additional exploration and investigation to address this limitation. To address the existing theoretical gap, this study focused on developing an objective function that accurately estimates the initial root parameters of Photovoltaic (PV) models. This objective function was designed by incorporating the first-order Berndt-Hall-Hall-Hausman (BHHH) numerical method, along with the non-linear damping parameter of the Levenberg-Marquardt technique (LM). By implementing this approach, the study aimed to significantly improve the precision and reliability of estimating the initial root parameters in PV models, effectively filling the theoretical void in this specific research area. Then in terms of methodology, the Enhanced Henry Gas Solubility Optimization (EHGSO) algorithm is combined with the Sine-Cosine mutualism phase of Symbiotic Organisms Search (SOS) for efficiently estimating the unknown parameters of PV models. The keystone of EHGSO in terms of methodology enhances exploration at the beginning of optimization and intensifies exploitation in later iterations. The proposed EHGSO methodology based on the adaptive damping BHHH technique (EHGSO AdBHHH) is tested on Single Diode (SD), and Double Diode (DD) PV models using actual experimental data. EHGSO AdBHHH exhibits outstanding accordance with attained experimental data compared with other algorithms, and its superiority is validated using several statistical criteria. [ABSTRACT FROM AUTHOR]

Blind and visually impaired people experience difficulty positioning themselves in unfamiliar areas; they may become disoriented and need help from another person. Referred to as 'localization', this task is one of the significant challenges frequently encountered by blind people in unfamiliar indoor and outdoor environments. This paper aims to design and implement an energy-efficient localization system (EELS) for the blind and visually impaired based on a Zigbee wireless network and an artificial neural network (ANN) used in indoor environments. The ANN algorithm was adopted to improve localization accuracy for the blind and visually impaired. The ANN was fused independently with six metaheuristic algorithms, namely backtracking search algorithm (BSA), crow search algorithm (CSA), gravitational search algorithm (GSA), slime mould algorithm (SMA), particle swarm optimization (PSO) and multi-verse optimizer-ANN (MVO), to determine the optimal neurons and learning rate of ANN. Consequently, the ANN's performance was optimized and localization errors were improved. In addition, the power consumption of the EELS was minimized based on a proposed energy-efficient localization algorithm (EELA). The experimental results in indoor environments verified the potential of MVO-ANN in improving localization errors, achieving mean errors of 0.55 and 0.65 m in testing and validating phases, respectively. In addition, the EELS achieved a power savings of 63% based on EELA. Moreover, the EELS had better localization accuracy and power savings than other systems reported in the literature. [ABSTRACT FROM AUTHOR]

Accurate forecasting techniques for a stochastic pattern of water demand are essential for any city that faces high variability in climate factors and a shortage of water resources. This study was the first research to assess the impact of climatic factors on urban water demand in Iraq, which is one of the hottest countries in the world. We developed a novel forecasting methodology that includes data preprocessing and an artificial neural network (ANN) model, which we integrated with a recent nature-inspired metaheuristic algorithm [marine predators algorithm (MPA)]. The MPA-ANN algorithm was compared with four nature-inspired metaheuristic algorithms. Nine climatic factors were examined with different scenarios to simulate the monthly stochastic urban water demand over 11 years for Baghdad City, Iraq. The results revealed that (1) precipitation, solar radiation, and dew point temperature are the most relevant factors; (2) the ANN model becomes more accurate when it is used in combination with the MPA; and (3) this methodology can accurately forecast water demand considering the variability in climatic factors. These findings are of considerable significance to water utilities in planning, reviewing, and comparing the availability of freshwater resources and increasing water requests (i.e., adaptation variability of climatic factors). [ABSTRACT FROM AUTHOR]

Modelling drought is vital to water resources management, particularly in arid areas, to reduce its effects. Drought severity and frequency are significantly influenced by climate change. In this study, a novel hybrid methodology was built, data preprocessing and artificial neural network (ANN) combined with the constriction coefficient-based particle swarm optimisation and chaotic gravitational search algorithm (CPSOCGSA), to forecast standard precipitation index (SPI) based on climatic factors. Additionally, the marine predators algorithm (MPA) and the slime mould algorithm (SMA) were used to validate the performance of the CPSOCGSA algorithm. Climatic factors data from 1990 to 2020 were employed to create and evaluate the SPI 1, SPI 3, and SPI 6 models for Al-Kut City, Iraq. The results indicated that data preprocessing methods improve data quality and find the best predictors scenario. The performance of CPSOCGSA-ANN is better than MPA-ANN and SMA-ANN algorithms based on various statistical criteria (i.e., R2, MAE, and RMSE). The proposed methodology yield R2 = 0.93, 0.93, and 0.88 for SPI 1, SPI 3, and SPI 6, respectively. [ABSTRACT FROM AUTHOR]

The optimal power flow (OPF) is one of the most noticeable and integral tools in the power system operation and control and aims to obtain the most economical combination of power plants to exactly serve the total demand of the system without any load shedding or islanding through adjusting control variables to meet operational, economic, and environmental constraints. To achieve this goal, the successful implementation of an expeditious and reliable optimization algorithm is crucial. To solve this issue, this research proposes an enhanced democratic political algorithm (DPA), which can effectively solve multi-objective optimum power flow problems. The proposed method is a version of the democratic political optimization algorithm in which the search capability of this method to cover the borders of the Pareto frontier is enhanced. For the sake of practicality, the objectives with innate differences such as total emission, active power loss, and fuel cost are selected. Due to the practical limitations in real power systems, additional restrictions including valve-point effect, multi-fuel characteristics, and forbidden operational zones, are also considered. The proposed approach is tested and validated on IEEE 57-bus and IEEE 118-bus systems with different case studies. Simulation results are analyzed and compared with two popular and commonly used multi-objective-evolutionary algorithms namely, non-dominated sorting genetic algorithm II (NSGA-II) and the multi-objective particle swarm optimization (MOPSO) on the problem. The study results illustrate the effectiveness of the proposed method in handling different scales, non-convex, and multi-objective optimization problems. [ABSTRACT FROM AUTHOR]

Sleep apnea (SA) is a common respiratory disorder, especially among obese people. It is caused by either the relaxation of the upper respiratory tract muscles or the failure of the neural signal to reach the muscles responsible for breathing, both of which interrupt the patient's sleep–wake cycles. The traditional method for diagnosing this disorder, based on polysomnography, is complicated, vexing, expensive, time-consuming, and requires both sleep centers and specialized staff capable of connecting electrodes to the patient's body. This paper proposes an SA prediction system based on merging five soft computing algorithms, specifically, combining the multi-verse optimizer (MVO) with an artificial neural network (ANN) to leverage measurements from heart rate, SpO2, and chest movement sensors. The most substantial novelty of this research is the hybridization of MVO and ANN (MVO-ANN), which improves the ANN performance by selecting the best learning rate and number of neurons in hidden ANN layers. This enables highly accurate prediction of sleep apnea events. This work's experimental results reveal that the MVO-ANN performs better than other algorithms, with mean absolute errors of 0.042, 0.202, and 0.166 for training, testing, and validation of the ANN. In addition, the SA prediction system achieved an accuracy of 98.67%, a sensitivity of 96.71%, and a specificity of 99.24%. These results provide good evidence that the proposed method can reliably predict respiratory events in people suffering from SA. [ABSTRACT FROM AUTHOR]

Salinity is a classic problem in water quality management since it is directly associated with low water quality indices. Debate continues about selecting the best model for water quality forecasting, it remains a major challenge and causes much uncertainty. Accordingly, identifying the optimal modelling that can capture the salinity behaviour is becoming a common trend in recent water quality research. This study applies novel combined techniques, including data pre- processing and artificial neural network (ANN) optimised with constriction coeffi- cient-based particle swarm optimisation and chaotic gravitational search algorithm (CPSOCGSA) to forecast monthly salinity data. Historical monthly total dissolved solids (TDS) and electrical conductivity (EC) data of the Euphrates River at Al- Musayyab, Babylon, and climatic factors from 2010 to 2019 were used to build and validate the methodology. Additionally, for more validation, the CPSOCGSA-ANN was compared with the slime mould algorithm (SMA-ANN), particle swarm optimisation (PSO-ANN) and multi-verse optimiser (MVO-ANN). The results reveal that the pre-processing data approaches improved data quality and selected the best predictors’ scenario. The CPSOCGSA-ANN algorithm is the best based on several statistical criteria. The proposed methodology accurately simulated the TDS and EC time series based on R² = 0.99 and 0.97, respectively, and SI = 0.003 for both parameters. [ABSTRACT FROM AUTHOR]