In the electricity market environment, the market clearing price has strong volatility, periodicity and randomness, which makes it more difficult to select the input features of artificial neural network forecasting. Although the traditional back propagation (BP) neural network has been applied early in electricity price forecasting, it has the problem of low forecasting accuracy. For this reason, this paper uses the maximum information coefficient and Pearson correlation analysis to determine the main factors affecting electricity price fluctuation as the input factors of the forecasting model. The improved particle swarm optimization algorithm, called simulated annealing particle swarm optimization (SAPSO), is used to optimize the BP neural network to establish the SAPSO-BP short-term electricity price forecasting model and the actual sample data are used to simulate and calculate. The results show that the SAPSO-BP price forecasting model has a high degree of fit and the average relative error and mean square error of the forecasting model are lower than those of the BP network model and PSO-BP model, as well as better than the PSO-BP model in terms of convergence speed and accuracy, which provides an effective method for improving the accuracy of short-term electricity price forecasting.
For transformer fault diagnosis of the IEC three-ratio is an effective method in the dissolved gas analysis (DGA). But it does not offer completely objective, accurate diagnosis for all the faults. Aiming at parameters are confirmed by the cross validation, using the ant colony algorithm, the ACSVM-IEC method for the transformer fault diagnosis is proposed. Experimental results show that the proposed algorithm in this paper that can find out the optimum accurately in a wide range. The proposed approach is robust and practical for transformer fault diagnosis.
Hydropower, as a crucial component of power grid systems, plays an essential role in peak regulation due to its fast start-stop and high-speed climbing capabilities. Current hydropower peak regulation methods struggle to consider complex load demand and the highly coupled characteristics of runoff simultaneously. This study proposes the Adaptive Segmented Cutting Load Algorithm (ASCLA) to restructure the power station's load process and segment the scheduling period based on load characteristics, ensuring hydropower stations operate in peak regulation mode throughout the entire cycle. The method determines each sub-scheduling period's peak regulation depth based on runoff characteristics and considers factors impacting peak regulation capability. To minimize the residual load's rolling data window standard deviation, we apply ASCLA to the Three Gorges Reservoir (TGR) simulation. We introduce four evaluation indicators: Mean Squared Deviation of the Rolling Window (MSDRW), total time variation of residual load, peak residual load, and response time to assess peak regulation effectiveness. Our method can handle peak regulation demands under varying runoff conditions, providing feasible scheduling solutions. Simulations and analyses reveal ASCLA demonstrates stronger load tracking ability, a broader adjustment range of load peaks and valleys, and a more significant peak regulation effect compared to the conventional method. Finer segmentation of sub-scheduling periods and final water level determination under conditions of higher load variability and drier runoff optimizes the power station's regulation capacity and meets the power grid's operational needs. In conclusion, our research develops a comprehensive and adaptable peak regulation scheduling model for hydropower stations, offering more effective solutions to address challenges related to extreme weather events and renewable energy integration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.