Abstract:Many approaches about the planning and operation of power systems, such as network reconfiguration and distributed generation (DG), have been proposed to overcome the challenges caused by the increase in electricity consumption. Besides the positive effects on the grid, contributions on environmental pollution and other advantages, the rapid developments in renewable energy technologies have made the DG resources an important issue, however, improper DG allocation may result in network damages. A lot of studie… Show more
“…In [34], the authors have proposed machine learning methods to estimate the DG size and its effects on DS. The proposed methods such as Linear Regression, Artificial Neural Networks, Support Vector Regression, K-Nearest Neighbor and Decision Tree were applied on IEEE 12, 33 and 69-bus standard test systems.…”
Section: B Literature Reviewmentioning
confidence: 99%
“…The seasonal load curve is shown in Appendix Table A-2 and graphically in Fig. 6 [34]. While annual active and reactive energy losses were calculated as 680.8 MWh and 453.8 MVArh, the energy of 20.5 GWh active and 12.7 GVArh reactive were injected from the substation (SS) in a year.…”
In this paper, two metaheuristic methods, genetic algorithm and particle swarm optimization, are proposed to determine the optimal locations, sizes and power factors of single and double distributed generation units. In line with the 2050 carbon neutral goal, the aim was to integrate renewable distributed energy sources such as photovoltaic panels and wind turbines into the distribution system with a high penetration level. In contrast to most studies based on constant loads and dispatchable generations, an application considering the seasonal uncertainties of generation and consumption was performed to minimize the annual energy losses and voltage deviations of the distribution network. In addition, dispatchable, controllable and fuel-based conventional resources were allocated to compare the contributions of renewable resources. These seasonal case studies with various constraints were applied to IEEE 33-bus radial distribution network. To verify the feasibility and robustness of the proposed algorithms, case studies for peak loads were created and compared with the literature studies. While all distributed generation sources were operated at both unity and optimum power factor in all case studies, zero power factor and leading power factor scenarios were examined for a peak load only. Photovoltaic applications without energy storage technologies have not been very efficient because of the uneven daily distribution of solar irradiance, especially insufficient irradiation in the evening and excessive irradiation at noon. However, wind energy applications are more reliable and feasible, because the wind speed distribution is relatively more uniform than that of solar irradiation, both seasonally and daily. In all cases, operating distributed generation sources at the optimal power factor provided better results than those operating at unity power factor. As a result, wind turbines operating at optimal power factors have been found to contribute better than photovoltaic systems and are almost as good as conventional sources with controllable power output. While both proposed algorithms yielded better results than those in the literature, particle swarm optimization was better than genetic algorithm in terms of providing the best solution, faster convergence and shorter running time.
“…In [34], the authors have proposed machine learning methods to estimate the DG size and its effects on DS. The proposed methods such as Linear Regression, Artificial Neural Networks, Support Vector Regression, K-Nearest Neighbor and Decision Tree were applied on IEEE 12, 33 and 69-bus standard test systems.…”
Section: B Literature Reviewmentioning
confidence: 99%
“…The seasonal load curve is shown in Appendix Table A-2 and graphically in Fig. 6 [34]. While annual active and reactive energy losses were calculated as 680.8 MWh and 453.8 MVArh, the energy of 20.5 GWh active and 12.7 GVArh reactive were injected from the substation (SS) in a year.…”
In this paper, two metaheuristic methods, genetic algorithm and particle swarm optimization, are proposed to determine the optimal locations, sizes and power factors of single and double distributed generation units. In line with the 2050 carbon neutral goal, the aim was to integrate renewable distributed energy sources such as photovoltaic panels and wind turbines into the distribution system with a high penetration level. In contrast to most studies based on constant loads and dispatchable generations, an application considering the seasonal uncertainties of generation and consumption was performed to minimize the annual energy losses and voltage deviations of the distribution network. In addition, dispatchable, controllable and fuel-based conventional resources were allocated to compare the contributions of renewable resources. These seasonal case studies with various constraints were applied to IEEE 33-bus radial distribution network. To verify the feasibility and robustness of the proposed algorithms, case studies for peak loads were created and compared with the literature studies. While all distributed generation sources were operated at both unity and optimum power factor in all case studies, zero power factor and leading power factor scenarios were examined for a peak load only. Photovoltaic applications without energy storage technologies have not been very efficient because of the uneven daily distribution of solar irradiance, especially insufficient irradiation in the evening and excessive irradiation at noon. However, wind energy applications are more reliable and feasible, because the wind speed distribution is relatively more uniform than that of solar irradiation, both seasonally and daily. In all cases, operating distributed generation sources at the optimal power factor provided better results than those operating at unity power factor. As a result, wind turbines operating at optimal power factors have been found to contribute better than photovoltaic systems and are almost as good as conventional sources with controllable power output. While both proposed algorithms yielded better results than those in the literature, particle swarm optimization was better than genetic algorithm in terms of providing the best solution, faster convergence and shorter running time.
“…Various machine learning techniques, including linear regression, artificial neural networks, support vector regression, K-nearest neighbours, and decision trees, have been leveraged for these estimations and applied across established test systems. Purlu and Turkay (2021).…”
As the modern power system continues to grow in size, complexity, and uncertainty, traditional methods may occasionally prove insufficient in addressing the associated challenges. The improper location of distributed generation varies the voltage profile, increases losses and compromises network capacity. Machine learning algorithms predict accurate site positions, and network reconfiguration improves the capacity of the power system. The proposed algorithm is a hybrid of machine learning and deep learning algorithms. It cascades Support Vector Machine as the main model and uses Random Forest and Radial Neural Networks as classification algorithms for accurately predicting DG position. The non-linearity characteristics of the DG problem are directly mapped to the proposed algorithms. The proposed algorithm is employed on familiar test setups like the IEEE 33-bus and 69-bus distribution systems using MATLAB R2017 as simulation software. The R-squared (R2) values for all parameters yield a value of 1, while the MAPE values are minimal for the proposed cascaded algorithm in contrast to other algorithms of LSTM, CNN, RNN and DQL.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.