29 February 2024, Volume 44 Issue 1

  

• Select all
  |

• Select
  Short-term Power Prediction Method of Wind Power Cluster Based on CBAM-LSTM

  ZHANG Zhe, WANG Bo

  2024, 44(1): 1-8. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0001-08

  Abstract ( )   Knowledge map   Save

  The accurate prediction of wind power is of great significance for China to achieve the goal of 'carbon peak and carbon neutrality '.Traditional wind power prediction methods often ignore the long-term dependence and spatial correlation in time series data, resulting in inaccurate prediction results. In order to solve this problem, this  paper  proposes  a  model  combining  Convolutional  Block  Attention    Module（CBAM）and Long  Short-Term Memory（LSTM）.Firstly , CBAM is used to extract the characteristics of wind power time series data and the spatial characteristics contained in numerical weather prediction. This module can adaptively learn important features in time and space. Then, the extracted features are input into the LSTM layer structure for power prediction. In order to verify the effectiveness of the proposed method, a data set of a wind farm in Jilin Province, China is used for verification. The experimental results show that compared with other power prediction methods used in this paper, the mean absolute error（MAE）of the proposed method is reduced by an average of 2.67%.The coefficient of determination（R-Square,R2）increased by an average of 23 %The root mean square error（RMSE）decreased by 2.69% on average.
  
• Select
  Short-term Power Prediction of Wind Power Cluster Based on FCM and I Transformer-TCN

  NIU Jiajun, ZHANG Wei , XU Daming

  2024, 44(1): 9-16. https://doi.org/10.19718/i.issn.1005-2992.2024-01-0009-08

  Abstract ( )   Knowledge map   Save

  Accurate wind power prediction is of great significance for the safe and stable operation of the power system. In view of the problems of unreasonable cluster division in cluster prediction and difficult to effectively improve the accuracy in short-term prediction, this paper proposes a short-term wind power cluster power prediction method based on Fuzzy C-means （FCM）and I Transformer-time convolutional network （Temporal Convolutional Network, TCN）.First, divide subclusters based on FCM clustering algorithm, and then use the advantages of I Transformer-TCN model dual feature extraction to model each subcluster. Finally, this method was applied to a wind power cluster in Jilin Province, China, and the RMSE decreased by 10.8%on average compared with other methods, which verified the effectiveness of this paper.
• Select
  Bi-level Optimal Scheduling of Multi-source Combined System Considering Wind Power Output Uncertainty

  CHEN Yiming, LIU Yunjing, WANG Jinxin

  2024, 44(1): 17-24. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0017-08

  Abstract ( )   Knowledge map   Save

   For a multi-source integrated system incorporating wind, fire, and storage, the wind power output exhibits uncertainty. There is a discrepancy between the predicted and actual power of the wind turbine during specific time periods. When the actual output of the wind turbine fails to meet the scheduled power in the dispatch plan, it leads to a significant reduction in the economic efficiency of the system. To address this issue, this paper proposes a two-layer optimization strategy that considers wind power prediction errors and demand-side response. The upper-level model aims to minimize the overall operating cost of wind power, thermal power, and dispatchable loads, utilizing an Improved Particle Swarm Algorithm（IPSO）to formulate optimal scheduling strategies for thermal power and dispatchable loads. Subsequently, the Gibbs method is employed to sample the probability density function of the maximum output prediction error of the wind turbine, obtaining a certain amount of samples and determining the power deficit for each sample in the upper-level power sources. The lower-level model aims to minimize the overall operating cost of energy storage and interruptible loads. It employs linear programming to offset the power deficits from the upper-level sources, thereby formulating the lower-level model's power dispatch strategy. With a large number of sampled scenarios, the proposed two-layer optimization strategy's economic and effective nature is validated by comparing the expected value and variance of the total cost function values for each sample.
• Select
  Optimization Dispatch of Integrated Energy Systems Considering Hydrogen Production Efficiency Variation and Hydrogen Energy Green Certificate

  ZENG Yuxuan, JI Shuang, WANG Jinxin

  2024, 44(1): 25-33. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0025-09

  Abstract ( )   Knowledge map   Save

   Proton exchange membrane（PEM）water electrolysis hydrogen production technology is one of the main methods for producing green hydrogen, but its hydrogen production efficiency is influenced by many factors.Considering the influence of input power on the hydrogen production efficiency of electrolyzers, this paper introduces an integrated energy system optimization model that accounts for the variability in electrolyzer efficiency. Firstly, the coupling relationship between hydrogen production efficiency and electrolyzer input power is studied. Utilizing historical data analysis, a correlation curve is established to depict the relationship between electrolyzer power and hydrogen production efficiency. Secondly, by combining the stepwise carbon trading mechanism with the green certificate trading mechanism, a carbon-green certificate trading mechanism is proposed. Subsequently, a comprehensive energy system optimization dispatch model is developed, which takes into account the fluctuation in hydrogen production efficiency and incorporates considerations regarding hydrogen energy green certificates, with the primary objective of minimizing the total system cost. Finally, through case analysis, the effectiveness of the proposed model in reducing the total operating cost of the system is verified.
• Select
  Multi-Load Forecasting of Integrated Energy Systems Based on STL -Crossformer

  CAI Yi, ZHANG Wei

  2024, 44(1): 34-41. https://doi.org/10.19718/i.issn.1005-2992.2024-01-0034-08

  Abstract ( )   Knowledge map   Save

   Multi-load forecasting in integrated energy systems is crucial for the operation and scheduling of the system. Traditional forecasting models have not fully captured the long-term dependencies in time series or considered the coupling relationships between multiple loads, limiting improvements in forecasting accuracy. To address the challenges of multi-load forecasting in integrated energy systems, this paper proposes a forecasting model that integrates Seasonal Trend Decomposition and Crossformer. Initially, the original load data is decomposed into three sub-sequences using seasonal trend decomposition. Then, by employing a dimension-segmented embedding method and a two-stage attention mechanism, the model extracts cross-time and cross-dimensional correlations of multi-load data. Finally, a hierarchical encoder-decoder structure is utilized to generate forecasting results. Comparative experiments on real load datasets demonstrate that the model proposed in this paper has higher accuracy compared to other comparison models.
• Select
  Review of Artificial Intelligence Algorithms-based Wind Turbine Condition Monitoring and Fault Diagnosis Techniques

  WANG Zhongxing, ZHOU Yuangui, ZHANG Xueguang

  2024, 44(1): 42-51. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0042-10

  Abstract ( )   Knowledge map   Save

   With the rapid development of my country's wind power industry, the service life of wind turbines has been extended, and the failure rate and maintenance costs have increased accordingly. Using artificial intelligence algorithms to mine wind power big data and achieve condition monitoring and fault diagnosis of wind turbines has important practical significance for improving the quality and efficiency of the wind power industry, and has gradually become a research hotspot in recent years. This article introduces the characteristics of the wind turbine supervisory control and data acquisition system and vibration signal data, and explains the framework of the intelligent algorithm for wind turbine condition monitoring and fault diagnosis. Relevant research results are summarized, and the challenges and development trends faced by wind turbine condition monitoring and fault diagnosis technology are prospected.
• Select
  Review of Modular High Voltage and Large Capacity DC/DC Converter

  ZHANG Shuxin, ZHAO Ruofan, LIU Hongpeng

  2024, 44(1): 52-60. https://doi.org/10.19718/i.issn.1005-2992.2024-01-0052-09

  Abstract ( )   Knowledge map   Save

   With the increasing proportion of new energy generation and the continuous expansion of power grid scale, the capacity of DC transmission system is constantly improving, and DC power grid with different voltage levels is the inevitable trend of future development. In this context, DC/DC converter, as the key equipment of DC power network, plays an important role in multi-voltage level interconnection scenarios. In this paper, the existing modular high-voltage and large-capacity DC/DC converters are summarized, classified and compared, then the topology, working principle and characteristics of the current modular high-voltage and large-capacity DC/DC converters are expounded, and the applicable scenarios of different converters are put forward according to their characteristics. Finally，suggestions for future research directions are put forward.
• Select
  Optimal Configuration of Hybrid Energy Storage System for Primary Frequency Regulation Based on VMD

  CAI Tingting , XUE Wendong

  2024, 44(1): 61-71. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0061-11

  Abstract ( )   Knowledge map   Save

  Power-type energy storage and energy-type energy storage can be combined in a certain proportion to form a hybrid energy storage system, which can significantly enhance the power output of the energy storage system. In order to fully utilize the advantages of hybrid energy storage in participating in the primary frequency regulation of wind farms and consider economic factors, a capacity optimization configuration method based on variation mode decomposition is proposed. Firstly, a mathematical model is established with the objective of maximizing the net benefits of the hybrid energy storage system. Next, the power demand signal is decomposed into high-frequency power demand and low-frequency power demand using the variation mode decomposition method. Finally, taking a 100 MW wind farm in the Northeast as a case study, based on power demand data for a typical day, considering constraints such as energy storage charging and discharging power and state of charge, the objective model is solved using the quantum particle swarm algorithm. The results show that the optimized energy storage configuration scheme can effectively improve the economic viability of hybrid energy storage for assisting the primary frequency regulation of wind farms.
• Select
  Low-carbon Economic Dispatch of Integrated Energy Systems Considering HRD-containing Photovoltaic Plants and Integrated Demand Response

  WANG Yijun, SUN Jianchun, GAO Min, QIN Yerong, ZHANG Xidong

  2024, 44(1): 72-82. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0072-11

  Abstract ( )   Knowledge map   Save

   In the context of "dual-carbon"，in order to further enhance the economic and environmental benefits of integrated energy system, the paper proposes a low-carbon optimal scheduling methodology for IES under the reward-penalty ladder-type carbon trading mechanism, taking into account a photovoltaic power plant with heat recovery device and integrated demand response. Optimal scheduling method. Firstly, the IES architecture for the joint operation of a photovoltaic power plant with heat recovery device and a cogeneration unit with carbon capture is constructed on the source side, and the operation principle of the two stages of power-to-gas conversion is analysed to establish a model of power-to-gas conversion equipment taking into account the waste heat recovery. Secondly, considering the flexible characteristics of the three loads of electricity, heat and gas on the customer side, an integrated demand response model for electricity, heat and gas is established on the load side. Finally, the carbon trading mechanism is introduced to further reduce the carbon emissions of the system,s o as to construct a low-carbon optimal dispatch model of the integrated energy system with the goal of minimising the total operating costs of the system, including the energy purchase cost, operation and maintenance cost, and the carbon trading cost, during the scheduling cycle. The results of the analyses show that the proposed method not only improves the operating potential of the units, but also effectively reduces the total system operating costs and carbon emissions.
• Select
  Optimization and Scheduling Strategy for Comprehensive Energy Systems Based on Bilateral Multi-agent Game Interaction Between Energy Supply and Demand

  WANG Hefei, CAI Guowei, WU Tong, HUANG Nantian, HU Chenhan, WNAG Xinran

  2024, 44(1): 83-93. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0083-11

  Abstract ( )   Knowledge map   Save

  The high proportion of renewable energy such as wind power connected to the grid is a necessary path for the green and low-carbon transformation of the power system under the "dual carbon "goal, but it also brings enormous pressure to the safe operation of the power grid. Therefore, a game theory based integrated energy system（IES）optimization scheduling strategy for carbon capture is proposed in the article. Firstly, a comprehensive energy system carbon cycle optimization model was constructed to promote wind power consumption. Then, a two-layer game scheduling strategy with Stackelberg game was constructed and proved to be balanced. Finally, the improved differential evolution algorithm is used to solve the two-layer game model to meet the convergence speed requirements of the scheduling model.
• Select
  Thermal and Electrical Performance Experimental Study of a Bi-fluid Type Photovoltaic/thermal Roof Module

  ZHANG Yanfeng, DUANMU Lin, ZHOU Chuang, LI Xiangli

  2024, 44(1): 94-100. https://doi.org/10.19718/i.issn.1005-2992.2024-01-0094-07

  Abstract ( )   Knowledge map   Save

   In this paper, a new type of bi-fluid photovoltaic/thermal roof module without cover is proposed. By combining the water-cooling duct of tube-plate with the air-cooling duct of baffle-plate, the water capacity of the component is reduced and the air outlet temperature is increased, and the supply of hot water and hot air for the module is realized. By building a performance test bench with a stable testing environment, the temperature difference between the inlet and outlet of the module and temperature of the module with solar irradiance and working fluid flow was studied, and the all-day thermal and electrical performance of the module was analyzed. The results show that the module has an obvious cooling effect. The electrical efficiency of water cooling and air cooling modes can reach up to16.80%and 17.62%.It has high all-day comprehensive performance and the all-day primary-energy saving efficiency is up to 74%.
• Select
  Analysis of the Effect of Surface Configuration on the Collision Characteristics of Transmission Conductor Icing

  SHEN Bowen, LI Lin, JI Kunpeng

  2024, 44(1): 101-108. https://doi.org/10.19718/i.issn.1005-2992.2024-01-0101-08

  Abstract ( )   Knowledge map   Save

   Conductor icing seriously affects the safety of power grid operation, the local collision coefficient is a key indicator to characterize the growth rate of transmission conductor ice cover, the traditional steel core aluminum stranded wire or its simplified cylindrical model of the growth of the ice cover characteristics of the previous analysis, the aluminum conductor composite core （ACCC），as a new type of conductor that is developing rapidly, the local collision coefficient and the growth process of the ice cover has rarely been studied. First realized the numerical simulation of ice cover growth based on the commercial finite element software Fluent, and verified the validity of the simulation method by comparing with the simulated test results. Subsequently, using the validated numerical simulation method, a comparative study of the ice cover growth characteristics of the ACCC refined model and the simplified circular conductor model was carried out to simulate the distribution of droplet collision coefficients on the surfaces of the two, and the effects of different median diameters of the raindrops and the change of the wind speed on the collision coefficients were discussed, and the icing ice shapes of the ACCC model were obtained. The results show that: the local collision coefficient of ACCC model is significantly smaller than that of round model when the wind speed is low, at the early stage of ice-covering, the ice shape is very significantly affected by the surface configuration of conductor, when the surface of conductor is completely wrapped by the ice-covering, the resistance coefficient of the round model is 15.3%lower than that of the ice shape of ACCC model as a whole, and it shows galloping instability under each wind attack angles. The results of the study are valuable for obtaining the growth characteristics of ACCC ice cover and understanding the disaster mechanism of ice cover on conductors with different surface configurations.
• Select
  Application of Inverter Air Conditioner aggregation External Characterization Study in Active Distribution Grid Optimization Scheduling

  YUAN Dian, JIN Xu , QIAN Tao, CHEN Tao, ZHANG Fei, ZHANG Yuanshi, HU Qinran

  2024, 44(1): 109-119. https://doi.org/10.19718/j.issn.1005-2992.2024-01-0109-11

  Abstract ( )   Knowledge map   Save

  Under the background of the "carbon peaking and carbon neutrality" goals and the construction of new power systems, the proportion of distributed energy resources in the distribution network has been increasing year by year. However, new energy generation is random and intermittent, and with the increasing peak-to-valley difference of loads, it is difficult to satisfy the demand for peak load following with only traditional generation resources. With the development of demand response technology, it has become possible to regulate flexible resources on the load side. There is an urgent need to explore the adjustable potential of controllable loads, analyze their regulation capability qualitatively and quantitatively from the perspective of the system, and establish their external characteristic models so as to be precisely dispatched. In this paper, research is carried out on inverter air conditioners on the customer side. First, the load model and control method of inverter air conditioners are clarified；then the qualitative assessment of the regulation potential of inverter air conditioner aggregation is carried out；then, according to different regulation scenarios, the external characteristic model of inverter air conditioner aggregation is established；and finally, the example verification is carried out in the active power distribution network. The result shows that the inverter air conditioner aggregation has similar external characteristics and regulation potential as the traditional generator, and can effectively participate in the optimization of the active distribution network scheduling.