No abstract

There is a universal trend toward a data-driven smart grid, which aims to realize two-way communication of energy flow and data flow between various agents across power generation side, transmission& distribution side, electricity retailors and end users. However, the low frequency electrical measurement data accumulated over a long period of time is insignificant for intelligent agents. This paper presents a machine learning method for reconstructing the low frequency electrical measurement data in smart grid. Firstly, the electrical measurement data is converted into electrical images, and then the low frequency electrical measurement data is reconstructed into high frequency electrical measurement data by generative adversarial network to improve the training stability, Wasserstein distance is introduced into the reconstruction mechanism. In addition, by designing the deep residual network based generator, the deep convolutional network based discriminator as well as the perception loss function, the reconstruction accuracy and the high-frequency detail reduction ability are improved. The proposed method is tested on three publicly available datasets and compared with the traditional data reconstruction method, justifying that this method not only can restore high-frequency details with less error, but also can be generalized to different datasets at one location and to datasets at different locations with satisfactory accuracy.

In order to effectively apply the detailed geographic and load information provided by digital technology, this paper proposes a practical double-Q planning model for large-scale medium voltage distribution network. Meanwhile, a coding method and an elite Ant-Q algorithm(EAQ) suitable for solving the model in this paper are proposed. Based on the basic characteristics of the medium voltage distribution network, the components in the distribution network are abstracted into nodes and branches in the graph theory. A variety of practical issue, such as cost parameters (investments, maintenance, reliability) and technical constraints (feeder capacity constraints, number constraints of substation feeder), as well as road network constraints and connection mode constraints are taken into consideration. In addition, the storage of road network matrix information, reliability evaluation algorithm and model solving algorithm are suitable for large-scale distribution network. Finally, the proposed model and algorithm are applied to a business area to be planned in Guangzhou, which verifies the effectiveness of the proposed model and algorithm. INDEX TERMS Large-scale distribution network planning, double-Q planning, EAQ, sequence coding, shortest path method, closed loop design. NOMENCLATURE INDICES TAO YU (Member, IEEE) received the B.Eng. degree in electrical power system from Zhejiang University, Hangzhou, China, in 1996, the M.Eng. degree in hydroelectric engineering from

No abstract

Aiming at the problem of coordinating system economy, security and control performance in secondary frequency regulation of the power grid, a sectional automatic generation control (AGC) dispatch framework is proposed. The dispatch of AGC is classified as three sections with the sectional dispatch method. Besides, a hierarchical multi-agent deep deterministic policy gradient (HMA-DDPG) algorithm is proposed for the framework in this paper. This algorithm, considering economy and security of the system in AGC dispatch, can ensure the control performance of AGC. Furthermore, through simulation, the control effect of the sectional dispatch method and several AGC dispatch methods on the Guangdong province power grid system and the IEEE 39 bus system is compared. The result shows that the best effect can be achieved with the sectional dispatch method. INDEX TERMS automatic generation control; hierarchical multi-agent deep deterministic policy gradient; sectional AGC dispatch; reinforcement learning.