The hybrid AC/DC distribution networks with multienergy complementary systems (HDN-MECS) have become a powerful supporting platform for the vertical integration of single energy and the horizontal integration of multiple energy. However, the complex composition, diverse operating scenarios, and strong spatiotemporal coupling have all posed major challenges for the comprehensive evaluation of HDN-MECS operating effectiveness. To this end, a self-adaptive evaluation framework is proposed in this paper based on the unique characteristics of HDN-MECS. Taking maximum entropy criterion (MEC) as an objective function, this paper proposes a two-stage interval analytic hierarchy process (IAHP), and solves the problem with a hybrid algorithm of improved particle swarm optimization (IPSO) and chaos optimization (CO). A self-adaptive interval analytic hierarchy process (SAIAHP) is developed to weight performance indicators under the framework, which aims to enable dynamic, robust evaluation considering human expert inputs. A case study forecasting verifies the accuracy and applicability of the SAIAHP method. © 2021 IEEE.

High-precision prediction of photovoltaic (PV) output is essential in PV system access to the power grid. To realize the security, stability and economic operation of power system, this paper proposes a hybrid factor analysis, gray wolf optimization, and generalized regression neural network (FA-GWO-GRNN) framework for short-term PV output forecast. In order to reduce the dimension of input features to PV output forecasting, the paper first develops a factor analysis (FA) to extract effective information from meteorological inputs. A generalized regression neural network (GRNN) algorithm is then employed to make the forecast, whose parameters are optimized by the gray wolf optimization (GWO) for its global searching capacity and fast convergence. The proposed GWO-GRNN framework effectively achieves high precision in short-term PV output forecasting, demonstrated in a case study on the measured power of a real world PV plant, which validated the accuracy and applicability of the proposed method in real-world scenarios.
© 2020 IEEE.

Energy storage systems are promising solutions to the mitigation of power fluctuations and the management of load demands in distribution networks. However, the uncertainty of load demands and wind generations increasingly seen in distribution networks may have a great impact on the configuration of ESS. To solve the problem, a novel optimal configuration method for energy storage system is proposed to reduce the influence of uncertainty of both load demands and WGs. The proposed method first reduce the uncertainty of load through a comprehensive demand response system based on time-of-use and incentive. Then, to predict the output of wind generations, we use the particle swarm optimization and backpropagation neural network to create a predictive model of the wind power. Then, an optimal configuration model is established to minimize the ESS investment cost and the network power loss reduction, subject to technical constraints such as ESS operational constraints and power balance constraint et al. An improved simulated annealing PSO algorithm is used to solve the optimization problem. Finally, the numerical studies on a modified IEEE 33-node distribution system show the advantages of the proposed methodology.
© 2020 IEEE.

High-precision prediction of photovoltaic (PV) output is essential in PV system access to the power grid. To realize the security, stability and economic operation of power system, this paper proposes a hybrid factor analysis, gray wolf optimization, and generalized regression neural network (FA-GWO-GRNN) framework for short-term PV output forecast. In order to reduce the dimension of input features to PV output forecasting, the paper first develops a factor analysis (FA) to extract effective information from meteorological inputs. A generalized regression neural network (GRNN) algorithm is then employed to make the forecast, whose parameters are optimized by the gray wolf optimization (GWO) for its global searching capacity and fast convergence. The proposed GWO-GRNN framework effectively achieves high precision in short-term PV output forecasting, demonstrated in a case study on the measured power of a real world PV plant, which validated the accuracy and applicability of the proposed method in real-world scenarios. © 2020 IEEE.