Search

Probabilistic solar irradiance forecasting has received widespread attention in recent years, as it provides more uncertainty information for the future photovoltaic generation. In this study, a hybrid probabilistic solar irradiance prediction method is proposed, which combines a deep recurrent neural network and residual modeling. Specifically, the long short‐term memory‐based point prediction using historical records and related features is applied to obtain deterministic forecasts. Next, these deterministic forecasts are employed as inputs to estimate the residual distributions. Furthermore, maximum likelihood estimation is utilized to compute the parameters of the residual distribution. Finally, the point prediction and residual distribution jointly generate the final probabilistic forecasting results. Compared with other deterministic and probabilistic forecasting models, the proposed method yields promising results on a publicly available dataset. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

An accurate, real-time estimation of the states of a power distribution system is highly desirable but hard to achieve because of the complexity of the network and the relative inefficiency of the measuring system. To increase the efficiency, this paper analyzes the mathematical relationship between the measurement errors and estimation errors of the state vector using the classic weighted least square method. Then a heuristic algorithm is proposed to improve the accuracy by optimizing the deployment of the real-time measuring points, which is based on the deterministic factors of the measuring points/branches over the system state. The basic implementation starts with an initial measurement set and replaces the least important branches in the set with the most important branches outside the set using iterative optimization. The algorithm was tested in the IEEE 14-bus and 33-bus distribution systems and achieved 50% increase in accuracy at much lower computational cost compared with exhaustive search. Moreover, the proposed algorithm has also been compared with representative and widely used evolution algorithms such as particle swarm optimization and quantum-behaved particle swarm optimization. This comparison shows that our method can achieve stable and comparable accuracy with a speed at least 10 times higher. The performance of our method can be even better with increasing network size. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

The establishment of a multistage multiobjective substation siting and sizing planning model, taking into account various constraints such as load flow constraint, maximum capacity constraint, and maximum power supply radius constraint makes possible substation planning between multiple years to be adjusted to achieve an optimal overall plan. Through multiple optimization objectives, it is possible to prevent the plan from becoming useless because of excessive changes in power supply affiliation during the multistage optimization process. To find the optimal solution for the model, a repair operator is proposed and used with an improved multiobjective genetic algorithm to repair the decision variables for each chromosome corresponding to one stage so as to satisfy the constraints while ensuring that population diversity evolves heuristically to the optimal solution. Moreover, a tournament selection operator based on crowding distance is adopted, which can prevent the algorithm from premature convergence and make populations trend to the Pareto frontier. Experimental results show that the proposed model and algorithm can efficiently solve the issue of rolling planning between multiple target years and achieve a joint optimal planning. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]