More and more attention has been paid to the development of renewable energy in the world. Microgrids with flexible regulation abilities provide an effective way to solve the problem of renewable energy connected to power grids. In this article, an optimization strategy of a microgrid participating in day-ahead market operations considering demand responses is proposed, where the uncertainties of distributed renewable energy generation, electrical load, and day-ahead market prices are taken into account. The results show that, when the microgrid implements the demand response, the operation cost of the microgrid decreases by 4.17%. Meanwhile, the demand response program can transfer the peak load of the high-price period to the low-price period, which reduces the peak valley difference of the load and stabilizes the load curve. Finally, a sensitivity analysis of three factors is carried out, finding that, with the increase of the demand response adjustable ratio or the maximum capacity of the electrical storage devices, the operation cost of the microgrid decreases, while, with the increase of the demand response cost, the operation cost of the microgrid increases and, finally, tends to the cost without the demand response. The sensitivity analysis reveals that the demand response cost has a reasonable pricing range to maximize the value of the demand response.

Ultra-short-term load demand forecasting is significant to the rapid response and real-time dispatching of the power demand side. Considering too many random factors that affect the load, this paper combines convolution, long short-term memory (LSTM), and gated recurrent unit (GRU) algorithms to propose an ultra-short-term load forecasting model based on deep learning. Firstly, more than 100,000 pieces of historical load and meteorological data from Beijing in the three years from 2016 to 2018 were collected, and the meteorological data were divided into 18 types considering the actual meteorological characteristics of Beijing. Secondly, after the standardized processing of the time-series samples, the convolution filter was used to extract the features of the high-order samples to reduce the number of training parameters. On this basis, the LSTM layer and GRU layer were used for modeling based on time series. A dropout layer was introduced after each layer to reduce the risk of overfitting. Finally, load prediction results were output as a dense layer. In the model training process, the mean square error (MSE) was used as the objective optimization function to train the deep learning model and find the optimal super parameter. In addition, based on the average training time, training error, and prediction error, this paper verifies the effectiveness and practicability of the load prediction model proposed under the deep learning structure in this paper by comparing it with four other models including GRU, LSTM, Conv-GRU, and Conv-LSTM.

In comparison with traditional point forecasting method, probability density forecasting can reflect the load fluctuation more effectively and provides more information. This paper proposes a hybrid hourly power load forecasting model, which integrates K-means clustering algorithm, Salp Swarm Algorithm (SSA), Least Square Support Vector Machine (LSSVM), and kernel density estimation (KDE) method. Firstly, the loads at 24 times a day are grouped into three categories according to the K-means clustering algorithm, which correspond to the valley period, flat period, and peak period of the load, respectively. Secondly, the load point forecasting value is obtained by LSSVM method optimized by SSA algorithm. Furthermore, the kernel density estimation method is employed to fit the forecasting error of SSA-LSSVM in different time periods, and the probability density function of the error distribution is obtained. The final load probability density forecasting result is obtained by combining the point forecasting value and the error fitting result, and then the upper and lower limits of the confidence interval under the given confidence level are solved. In this paper, the performance of the model is evaluated by two indicators named interval coverage and interval average width. Meanwhile, in comparison with several other models, it can be concluded that the proposed model can effectively improve the forecasting effect.