Taking advantage of the favorable operating efficiencies, photovoltaic (PV) with Battery Energy Storage (BES) technology becomes a viable option for improving the reliability of distribution networks;however, achievin...
详细信息
Taking advantage of the favorable operating efficiencies, photovoltaic (PV) with Battery Energy Storage (BES) technology becomes a viable option for improving the reliability of distribution networks;however, achieving substantial economic benefits involves an optimization of allocation in terms of location and capacity for the incorporation of PV units and BES into distribution networks. This article suggests a methodology based on the equilibrium Optimization (EO) algorithm for optimal integration of PV with BES in radial distribution networks. Multifarious objectives are comprised to minimize the cost of energy not supplied (CENS), the investment cost of PV and BES installations, their operational costs, the power losses through the distribution lines, the produced CO2 emissions relative to the grid and PV systems. Added to that, the power losses through the voltage source converter (VSC) interface between integrated PV and BES with the grid are assessed. The proposed methodology is applied on two radial distribution systems of 30-bus and 69-bus. The optimal integration of PV systems with BES have been obtained by considering various case studies by imposing several limits on the number of PV-BES and the state of charge (SoC) for BES. Subsequently, comparative performance analysis is performed using genetic algorithm (GA), EO algorithm, particle swarm optimization (PSO), differential evolution (DE), and grey wolf optimization (GWO).
The dynamic analysis of municipal solid waste (MSW) is essential for optimizing landfills and advancing sustainable development goals. Assessing damping ratio (D), a critical dynamic parameter, under laboratory condit...
详细信息
The dynamic analysis of municipal solid waste (MSW) is essential for optimizing landfills and advancing sustainable development goals. Assessing damping ratio (D), a critical dynamic parameter, under laboratory conditions is costly and time-consuming, requiring specialized equipment and expertise. To streamline this process, this research leveraged several novel ensemble machine learning models integrated with the equilibrium optimizer algorithm (EOA) for the predictive analysis of damping characteristics. Data were gathered from 153 cyclic triaxial experiments on MSW, which examined the age, shear strain, weight, frequency, and percentage of plastic content. Analysis of a correlation heatmap indicated a significant dependence of D on shear strain within the collected MSW data. Subsequently, five advanced machine learning methods-adaptive boosting (AdaBoost), gradient boosting regression tree (GBRT), extreme gradient boosting (XGBoost), random forest (RF), and cubist regression-were employed to model D in landfill structures. Among these, the GBRT-EOA model demonstrated superior performance, with a coefficient of determination (R2) of 0.898, root mean square error of 1.659, mean absolute error of 1.194, mean absolute percentage error of 0.095, and an a20-index of 0.891 for the test data. A Shapley additive explanation analysis was conducted to validate these models further, revealing the relative contributions of each studied variable to the predicted D-MSW. This holistic approach not only enhances the understanding of MSW dynamics but also aids in the efficient design and management of landfill systems.
暂无评论