Due to the recent development of information and communication technology (ICT), various studies using real-time data are now being conducted. The microgrid research field is also evolving to enable intelligent operation of energy management through digitalization. Problems occur when operating the actual microgrid, causing issues such as difficulty in decision making and system abnormalities. Using digital twin technology, which is one of the technologies representing the fourth industrial revolution, it is possible to overcome these problems by changing the microgrid configuration and operating algorithms of virtual space in various ways and testing them in real time. In this study, we proposed an energy storage system (ESS) operation scheduling model to be applied to virtual space when constructing a microgrid using digital twin technology. An ESS optimal charging/discharging scheduling was established to minimize electricity bills and was implemented using supervised learning techniques such as the decision tree, NARX, and MARS models instead of existing optimization techniques. NARX and decision trees are machine learning techniques. MARS is a nonparametric regression model, and its application has been increasing. Its performance was analyzed by deriving performance evaluation indicators for each model. Using the proposed model, it was found in a case study that the amount of electricity bill savings when operating the ESS is greater than that incurred in the actual ESS operation. The suitability of the model was evaluated by a comparative analysis with the optimization-based ESS charging/discharging scheduling pattern.

The capacity of photovoltaic (PV) generators can increase owing to the 4030 policy of the Government of South Korea.. In addition, there has been significant interest in developing a technology for the maintenance of PV generators owing to an increase in the number of outdated PV generators. This paper describes a failure diagnosis method that uses operational data for power generation and solar radiation of PV generators. The measured data stored since four years in an operational 50-kW PV generator that was installed in 2014, were analyzed. The proposed failure diagnosis logic uses support vector machine classification as a failure diagnosis method that can classify normal and failure data. The failure data were processed to be used as the fault diagnosis logic for solar power generators. A new 50-kW PV generator, which contained no fault data, was used for a case study in this paper. Fault data were generated and the operation data of the PV generators were diagnosed by applying the proposed method. In addition, the accuracy was calculated and the results were analyzed.

No abstract

-Analyze the customer daily load patterns, be used to determine the optimal charging and discharging schedule which can minimize the electrical charges through the battery energy storage system(BESS) installed in consumers is an object of this paper. BESS, which analyzes the load characteristics of customer and reduce the peak load, is essential for optimal charging and discharging scheduling to save electricity charges. This thesis proposes optimal charging and discharging scheduling method, using particle swarm optimization (PSO) and penalty function method, of BESS for reducing energy charge. Since PSO is a global optimization algorithm, best charging and discharging scheduling can be found effectively. In addition, penalty function method was combined with PSO in order to handle many constraint conditions. After analysing the load patterns of target BESS, PSO based on penalty function method was applied to get optimal charging and discharging schedule. 일반적으로 실시간 요금체계에서 피크부하의 이동을 통해 경제적