Demand-side management (DSM) increases the complexity of the forecasting environment, which makes traditional forecasting methods difficult to meet the firm's need for predictive accuracy. Since deep learning can comprehensively consider various factors to improve the prediction results, this paper improves the deep belief network from three aspects of input data, model and performance, and uses it to solve the short-term load forecasting problem in DSM. In the data optimization stage, the Hankel matrix is constructed to increase the input weight of DSM data, and the gray relational analysis is used to select strongly correlated data from other data. In the model optimization stage, the Gauss-Bernoulli restricted Boltzmann machine is used as the first restricted Boltzmann machine of the deep network to transform the continuity features of the input data into binomial distribution features. In the performance optimization stage, a pre-training method combining error constraint and unsupervised learning is proposed to provide good initial parameters, and the global fine-tuning of network parameters is realized based on genetic algorithm. Based on the actual data of Tianjin Power Grid in China, the experimental results show that the proposed method is superior to other methods.
This paper presents an online smart meter measurement error estimation algorithm. Extended Kalman filter (EKF) and limit memory recursive least square (LMRLS) methods are used for remote calibration of a large amount of user-side smart meters. Then, a modified joint estimation model is obtained by selecting the estimation step that conforms to the actual working condition and filtering the abnormal estimation value according to the line loss rate characteristics. Finally, based on the experimental data obtained by the program-controlled load simulation system, the precision of metering error estimation is verified. The results show that the method improves the precision of error estimation by analyzing the coupling between line loss rates and metering error estimation. By using the limited memory RLS algorithm, the influence of old measured data on error parameter estimation is reduced so that new data can be added to correct error parameter estimation to enhance the precision of the real-time smart meter error estimation.
19 October 2016 in Journal of Modern Power Systems and Clean Energy
A day-ahead optimal scheduling method for a grid-connected microgrid based on energy storage (ES) control strategy is proposed in this paper. The proposed method optimally schedules ES devices to minimize the total operating costs while satisfying the load requirements of cold, heat, and electricity in microgrids. By modeling the operating cost function of each stage, the proposed method is able to adapt to different types of electricity markets and pricing mechanisms. The technical characteristics of ES, such as self-discharge and round-trip efficiency, are considered in the control strategy with a multi-stage process model. An improved dynamic programing method is used to solve the optimization model. Finally, case studies are provided to illustrate the application process and verify the proposed method.
6 October 2021 in IEEE Transactions on Sustainable Energy
With the large-scale access of all kinds of distributed generations (DGs), the operation mode of the distribution network is increasingly diverse and changeable. To monitor the operation of an active distribution network, an adaptive dynamic estimation method is proposed to address the new generation of power system. Considering the features of different types of operation scenario change of distribution network and DGs, the proposed method uses the state deviation index to identify the current operation mode before state estimation. In the adaptive estimation stage, two typical estimators are improved to cope with the typical operation mode and embedded in the interactive multiple model (IMM) algorithm framework. IMM uses the identification results of operation mode to give higher weight to the corresponding estimator and finally outputs the joint estimation results. The proposed estimation method is investigated in an improved IEEE 33-bus system and an actual distribution network in China, which results indicate the proposed method converges more quickly and maintains better accuracy while facing the complex distribution network.