Search

In a “low-carbon” context, the power load is affected by the coupling of multiple factors, which gradually evolves from the traditional “pure load” to the generalized load with the dual characteristics of “load + power supply.” Traditional time-series forecasting methods are no longer suitable owing to the complexity and uncertainty associated with generalized loads. From the perspective of image processing, this study proposes a graphical short-term prediction method for generalized loads based on modal decomposition. First, the datasets are normalized and feature-filtered by comparing the results of Xtreme gradient boosting, gradient boosted decision tree, and random forest algorithms. Subsequently, the generalized load data are decomposed into three sets of modalities by modal decomposition, and red, green, and blue (RGB) images are generated using them as the pixel values of the R, G, and B channels. The generated images are diversified, and an optimized DenseNet neural network was used for training and prediction. Finally, the base load, wind power, and photovoltaic power generation data are selected, and the characteristic curves of the generalized load scenarios under different permeabilities of wind power and photovoltaic power generation are obtained using the density-based spatial clustering of applications with noise algorithm. Based on the proposed graphical forecasting method, the feasibility of the generalized load graphical forecasting method is verified by comparing it with the traditional time-series forecasting method.

With increasing reforms related to integrated energy systems (IESs), each energy subsystem, as a participant based on bounded rationality, significantly influences the optimal scheduling of the entire IES through mutual learning and imitation. A reasonable multiagent joint operation strategy can help this system meet its low-carbon objectives. This paper proposes a bilayer low-carbon optimal operational strategy for an IES based on the Stackelberg master-slave game and multiagent joint operation. The studied IES includes cogeneration, power-to-gas, and carbon capture systems. Based on the Stackelberg master-slave game theory, sellers are used as leaders in the upper layer to set the prices of electricity and heat, while energy producers, energy storage providers, and load aggregators are used as followers in the lower layer to adjust the operational strategy of the system. An IES bilayer optimization model based on the Stackelberg master-slave game was developed. Finally, the Karush-Kuhn-Tucker (KKT) condition and linear relaxation technology are used to convert the bilayer game model to a single layer. CPLEX, which is a mathematical program solver, is used to solve the equilibrium problem and the carbon emission trading cost of the system when the benefits of each subject reach maximum and to analyze the impact of different carbon emission trading prices and growth rates on the operational strategy of the system. As an experimental demonstration, we simulated an IES coupled with an IEEE 39-node electrical grid system, a six-node heat network system, and a six-node gas network system. The simulation results confirm the effectiveness and feasibility of the proposed model. [ABSTRACT FROM AUTHOR]