Boyang Qu

To enhance the market-oriented operation capability of integrated energy retailers and improve the synergy and economic efficiency of complex microgrids, this paper constructs a bi-level optimization model of “upper-level price optimization, lower-level multi-energy flow scheduling” under the background of multi-energy coupling of electricity, heat, gas, and hydrogen. The upper level optimizes electricity and heat price signals using the APSO and IGWO algorithms, while the lower level realizes coordinated multi-energy flow scheduling based on these signals. The operational performance of the two algorithms is compared across four scenarios. The results show that the scenario with multi-energy storage (Scenario 3) is the optimal adaptive scenario: the charge–discharge regulation of energy storage interacts with price guidance, and the peak-shaving and valley-filling characteristics significantly improve the system’s energy utilization efficiency. This scenario can fully unlock the value of bi-level optimization and meet the operational requirements of complex multi-energy coupling. In the algorithm comparison, the APSO algorithm presents distinct advantages, outperforming the IGWO algorithm in the precise regulation of upper-level electricity and heat prices, lower-level multi-energy flow balance, total operation cost control, and convergence stability. It provides an effective technical solution for the economic and stable operation of integrated energy systems.

To address the challenges of power generation rights trading and profit distribution in the integrated energy system of multi-park combined cooling, heating, and power (CCHP) with new energy grid integration, we constructed a hierarchical game model involving multi-energy system aggregators. By having aggregators price electricity, heat, cold, and carbon costs, the model establishes a hierarchical game framework with the linkage of the four prices (electricity, heat, cold, and carbon), achieving inter-park peer-to-peer (P2P) multi-energy dynamic price matching for the first time. It aims to coordinate distribution network dispatching, renewable energy, energy storage, gas turbine units, demand response, cooling–heating–power coupling, and inter-park P2P multi-energy interaction. With the goal of optimizing the profits of integrated energy aggregators, a hierarchical game mechanism is established, which integrates power generation rights trading models and incentive-based demand response. The upper layer of this mechanism is the profit function of integrated energy aggregators, while the lower layer is the cost function of park microgrid alliances. A hierarchical game mechanism with Two-Level Optimization, integrating the Adaptive Disturbance Quantum Particle Swarm Optimization (ADQPSO) algorithm and the branch and bound method (ADQPSO-Driven Branch and Bound Two-Level Optimization), is used to determine dynamic prices, thereby realizing dynamic matching of energy supply and demand and cross-park collaborative optimal allocation. Under the hierarchical game mechanism, the convergence speed of the ADQPSO-driven branch and bound method is 40% faster than that of traditional methods, and the optimization profit accuracy is improved by 1.59%. Moreover, compared with a single mechanism, the hierarchical game mechanism (Scenario 4) increases profits by 17.17%. This study provides technical support for the efficient operation of new energy grid integration and the achievement of “dual-carbon” goals.

Large-scale fluctuating and intermittent new energy power generation in a new power system is gradually connected to the grid. In view of the impact of the uncertainty of wind power on the spinning reserve capacity of thermal power units in the new power system’s day-ahead dispatching and reserve auxiliary service market, the original dispatching mode and intensity can no longer meet the system demand. To address this problem, the establishment of a wind power grid-connected new power system’s standby auxiliary service market reward and punishment assessment mechanism is undertaken to fundamentally reduce the demand for auxiliary services of the new power system pressure. In the first part of this paper, a two-stage optimal scheduling strategy is proposed for the first day of the year that takes into account the operational risk and standby economics. First, a data-driven method is used to generate the forecast value of the wind power interval before the day, and a unit start–stop optimization model (the first-stage optimization model) is established by taking into account the CvaR (conditional value at risk) theory to optimize the risk loss of wind abandonment and loss of load and the fuel cost of each unit, and an optimization algorithm is used to carry out the three scenarios and the corresponding four scenarios to optimize the configuration of the start–stop state and power output of each unit. The optimization algorithm is used to optimize the starting and stopping status and output of each unit for three circumstances and four corresponding scenarios. Then, in the second stage, a standby auxiliary service market incentive and penalty assessment model is established to effectively coordinate the sharing of rotating standby capacity and cost among thermal power units through the incentive and penalty mechanism so as to make a reasonable and efficient allocation of wind power output, curtailable load, and synchronized standby capacity. The new power system with improved IEEE30 nodes is simulated and verified, and it is found that the two-stage optimization model obtains a scheduling strategy that takes into account the system operating cost, standby economy, and reliability, and at the same time, through the standby auxiliary service market incentive and penalty assessment mechanism, the extra cost caused by standby cost mismatch can be avoided. This evaluation model provides a reference for the safe, efficient, flexible, and nimble operation of the new power system, improves the economic efficiency and improves the auxiliary service market mechanism.

By improving the accuracy of wind power prediction, reliable data support is provided for the Economic Dispatch(ED) model of Electric and Heat Integrated Energy System(EHIES) based on wind power consumption. In this paper, Convolutional Neural Network(CNN), Bidirectional Long Short Term Memory (BI-LSTM) and Attention Mechanism(AM) are used for wind power prediction. For the input of the CNN-BI-LSTM-AM model, the intrinsic mode signals obtained through Variational Mode Decomposition(VMD) and multidimensional power time series are used. Taking the October data of a coastal wind farm in Liaoning Province as an example, the accuracy of the CNN-BI-LSTM-AM model for wind power prediction reached 97.81%, which is better than the traditional model. Exploring the influence of wind power prediction accuracy on economy, wind power utilization efficiency, and carbon emissions in Two-stage robust optimization(TRO) and deterministic optimization models for EHIES. The EHIES model proposed in this paper considers the deterministic and uncertain economic dispatch of wind power under the situation of conventional heat load and heat load demand when the temperature drops suddenly. By solving the deterministic scheduling model and uncertain two-stage robust optimal scheduling model under different wind power forecasting accuracy, the electric heating integrated energy system can obtain the scheduling scheme with the lowest system operation cost, the highest wind power utilization and the less carbon emissions under the "universal" and "worst" scenarios, respectively. The simulation results show that compared with the traditional CPLEX solver, the C&CG algorithm can solve the main problem and sub problem alternately based on the column constraint generation algorithm and the strong duality theory. It can obtain the optimal solution of the economic dispatch model, providing an important reference for the optimal economic dispatch and wind power consumption strategy of the EHIES with wind power access.

Reliable wind farm short‐term output power prediction plays a crucial role in the safety and economy of power system operation. By embedding multiple neural network methods, such as long short‐term memory (LSTM) neural network, multiple optimized BP neural network and wavelet neural network (WNN), combined with multiple methods based on signal decomposition and reconstruction to evaluate the short‐term prediction effect. In this study, the variational modal decomposition (VMD) method and the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) are used to reduce the fluctuation of the original wind power signal. Besides, the intrinsic mode function (IMF) signals obtained by VMD and CEEMDAN methods are used. By predicting the IMF signals, the prediction error of each signal can be reduced, and the accuracy of wind power prediction can be indirectly improved. In order to test the validity of the proposed composite model, the validation prediction and rolling prediction of 72 h with a resolution of 10 min were carried out, respectively, using the data of Caijiagou wind farm in 2018. Through experiments, the relationship between the two predictions is analyzed, which provides an important reference for the selection of the prediction model. Corresponding results show that the proposed VMD‐LSTM and CEEMDAN‐LSTM methods significantly outperform other benchmark methods and provide very satisfactory results in both the accuracy and stability of wind farm power prediction.

Short‐term prediction of wind power plays a vital role in wind power application. In order to improve the accuracy of wind power forecasting, this paper investigates neural network combined forecasting models to forecast the wind power, the data of a real wind farm, the Pacific Wind Farm, is used. In view of the difficulty of predicting the large fluctuations of wind power, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm is used to decompose the wind power time series which can reduce the complexity of the forecasting process, and then the intrinsic mode function (IMF) signal is predicted by the BP Neural Network, wavelet neural network (WNN) and long short‐term memory (LSTM) neural network respectively, and the final result is obtained through wavelet reconstruction. By comparing with a single model, the combined prediction model has better prediction accuracy and stability, among them, the NMAE predicted by CEEMDAN‐GA‐BP in January was 4.167%, and the NRMSE was 6.590%. Reformed neural network based short‐term wind power forecasting models proposed in here provides very useful information for operation and control of high renewable energy penetrated power systems.