In microgrids, energy management systems (EMS) have been considered essential systems to optimize energy scheduling, control and operation for reliable power systems. Conventional EMS researches have been predominantly performed by employing demand-side management and demand response (DR). Nonetheless, multi-action control in EMS is confronted with operational challenges in terms of the profitability and stability. In this paper, energy information systems (EIS), energy storage systems (ESS), energy trading risk management systems (ETRMS), and automatic DR (ADR) are integrated to efficiently manage the profitability and stability of the whole EMS by optimal energy scheduling. The proposed microgrid EMS architecture is optimized by using proximal policy optimization (PPO) algorithm, which has been known to have good performance in terms of learning stability and complexity. A novel performance metric, represented as a burden of load and generation (BoLG), is proposed to evaluate the energy management performance. The BoLG is incorporated into the reward settings for optimizing the management of multi-action controls such as load shifting, energy charging-discharging, and transactions. From the simulation results, it is confirmed that the proposed architecture can improve energy management performance with the proper trade-off between stability and profitability, compared to dynamic programming (DP)-based and double deep Q-network (DDQN)-based operation.

Energy theft causes a lot of economic losses every year. In the practical environment of energy theft detection, it is required to solve imbalanced data problem where normal user data are significantly larger than energy theft data. In this paper, a variational autoencoder-generative adversarial network (VAE-GAN)-based energy theft-detection model is proposed to overcome the imbalanced data problem. In the proposed model, the VAE-GAN generates synthetic energy theft data with the features of real energy theft data for augmenting the energy theft dataset. The obtained balanced dataset is applied to train a detector which is designed as one-dimensional convolutional neural network. The proposed model is simulated on the practical dataset for comparing with various generative models to evaluate their performance. From simulation results, it is confirmed that the proposed model outperforms the other existing models. Additionally, it is shown that the proposed model is also very useful in the environments of extreme data imbalance for a wide variety of applications by analyzing the performance of detector according to the balance rate.

Inefficiencies in energy trading systems of microgrids are mainly caused by uncertainty in non-stationary operating environments. The problem of uncertainty can be mitigated by analyzing patterns of primary operation parameters and their corresponding actions. In this paper, a novel energy trading system based on a double deep Q-networks (DDQN) algorithm and a double Kelly strategy is proposed for improving profits while reducing dependence on the main grid in the microgrid systems. The DDQN algorithm is proposed in order to select optimized action for improving energy transactions. Additionally, the double Kelly strategy is employed to control the microgrid’s energy trading quantity for producing long-term profits. From the simulation results, it is confirmed that the proposed strategies can achieve a significant improvement in the total profits and independence from the main grid via optimized energy transactions.