Abstract
The smart grid is a fully automatic delivery grid for electricity power with a two-way reliable flow of electricity and information among different equipment on the grid. With the rapid development of smart grids, smart meters and sensors are used to monitor the system and provide a wide reporting which produce a huge amount of data in various part of the grid. To logical manage this trouble, the presented paper proposes a new lossy data compression approach for big data compression. In the proposed method, at the first step, the optimal singular value decomposition (OSVD) is applied to a matrix that achieves the optimal number of singular values to the sending process and the other ones will be neglected. This goal is done due to the quality of retrieved data and the rate of compression ratio. In the presented scheme, to implementation of the optimization framework, various intelligent optimization methods are used to determine the number of optimal values in the elimination stage. The efficiency and capabilities of the proposed method are examined using the experimental dataset of several residential microgrid consumers and market dataset. Simulation results show the high performance and efficiency of the proposed model in smart grids with big data.

Abstract
The use of distributed generators (DGs) in the distribution networks has many economic and technical advantages. In order to achieve these advantages, DGs should have the proper size and be installed in suitable locations. In this work, a differential evolution algorithm is proposed to find the best location and capacity of DGs in the distribution network with the aim of getting to the minimum losses and optimal voltage profile. The important loads need continuity of power supply when the network is in islanding mode due to various events such as short circuit faults. The existence of at least one DG in these networks is necessary. In this paper, the proposed method is applied to the IEEE 33-bus distribution network in two connection modes. First, it is connected with the power grid and then it works in the islanding operation mode. The results show the effectiveness of the proposed algorithm.

Abstract
Residential customers account for an indispensable part in the demand response (DR) program for their capability to provide flexibility when the system required. However, their available DR capacity has not been fully comprehended by the aggregator, who needs the information to bid accurately on behalf of the residential customers in the market transaction. To this end, this paper devised an optimal bidding strategy for the aggregator considering the bottom-up responsiveness of residential customers. Firstly, we attempt to establish the customers' responsiveness function in relation to different incentives, during which a home energy management system (HEMS) is introduced to implement load adjustment for electrical appliances. Secondly, the function is applied to the aggregator's decision-making process to formulate the optimal bidding strategy in the day-ahead (DA) market and the optimal scheduling scheme for the energy storage system (ESS) with the aim to maximize its own revenue. Finally, the validity of the proposed method is verified using the dataset from the Pecan Street experiment in Austin. The obtained outcome demonstrates the practical rationality of the proposed method.

Abstract
Ultra-short-term photovoltaic (PV) power forecasting can support the real-time dispatching of power grid and the optimal operation of PV power station itself. However, due to various meteorological factors, the photovoltaic power has great fluctuations. To improve the refined ultra-short-term forecasting technology of PV power, this paper proposes an ultra-short-term forecasting model of PV power based on optimal frequency-domain decomposition and deep learning. First, the amplitude and phase of each frequency sine wave is obtained by fast Fourier decomposition. As the frequency demarcation point is different, the correlation between the decomposition component and the original data is analyzed. By minimizing the square of the difference that the correlation between low-frequency components and raw data is subtracted from the correlation between high-frequency components and raw data, the optimal frequency demarcation points for decomposition components are obtained. Then convolutional neural network is used to predict low-frequency component and high-frequency component, and final forecasting result is obtained by addition reconstruction. Finally, the paper compares forecasting results of the proposed model and the non-spectrum analysis model in the case of predicting the 1 hour, 2 hours, 3 hours, and 4 hours. The results fully show that the proposed model improves forecasting accuracy.

Abstract
Determining the optimal management in terms of operative decisions (charging, discharging, or disconnection) as well as their magnitudes (charging/discharging current/power), considering the nonlinearities of battery energy storage system (BESS) is a crucial process on the successful acceptance of energy storage technologies. This work presents an optimization model for the management of BESS operating in real-time electricity markets in order to maximize the economic profits by energy arbitrage. The optimization model proposed combines genetic algorithm (GA) with gravitational search algorithm (GSA). On one hand, GA uses an integer codification, where charging, discharging, and disconnection are represented. On the other hand, GSA optimizes the maximum charging or discharging energy. The proposed combination of optimization algorithms allows determining the integer and continuous variables involved in the management problem, taking into account the nonlinear behavior of BESS. The proposed approach was implemented considering lead acid and vanadium redox flow batteries under the conditions of Spanish electricity market.

Abstract
The precise minute time scale forecasting of an individual Photovoltaic power station output relies on accurate sky image prediction. To avoid the two deficiencies of traditional digital image processing technology (DIPT) in predicting sky images: relatively limited input spatiotemporal information and linear extrapolation of images, convolutional auto-encoder (CAE) based sky image prediction models are proposed according to the spatiotemporal feature extraction ability of 2D and 3D convolutional layers. To verify the effectiveness of the proposed models, two typical DIPT methods, including particle image velocimetry (PIV) and Fourier phase correlation theory (FPCT) are introduced to build the benchmark models. The results show that the proposed models outperform the benchmark models under different scenarios.