Top Read Articles

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Multi-Energy Flow Modeling and Optimization of Electric-Gas-Thermal Integrated Energy System LI Bingjie, YUAN Xiaoyun, SHI Jing, XU Huachi, LUO Zixuan Journal of Shanghai Jiao Tong University    2024, 58 (9): 1297-1308.   DOI: 10.16183/j.cnki.jsjtu.2022.494 Abstract （3788）   HTML （44）    PDF（pc） （8902KB）（875）       Knowledge map    Save In view of the fact that the conversion of various energy forms such as electricity, gas, and heat in the regional integrated energy system (RIES) seriously affects the economy of the system operation, a mathematical model and an optimization model of RIES energy flow are established to improve the economy of the system and the absorption of renewable energy. First, the mathematical models of all kinds of energy conversion equipment in the system are established to determine the constraints of three kinds of energy transmission networks, namely electricity, natural gas, and heat. Then, taking economic operation as the primary objective, and taking into account the objective function of low carbon emissions and increasing the uptake rate of renewable energy, the RIES multi-energy flow optimization model is constructed. Finally, based on the large-scale integrated energy system, the load side demand response is introduced and the simulation model is established. The simulation results show that the introduction of demand response improves the flexibility of system scheduling, reduces the dependence of the system on energy storage equipment, and effectively reduces the energy consumption cost of users. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Optimal Allocation of Electric-Thermal Hybrid Energy Storage for Seaport Integrated Energy System Considering Carbon Trading Mechanism LIN Sen, WEN Shuli, ZHU Miao, DAI Qun, YAN Lun, ZHAO Yao, YE Huili Journal of Shanghai Jiao Tong University    2024, 58 (9): 1344-1356.   DOI: 10.16183/j.cnki.jsjtu.2022.428 Abstract （3006）   HTML （9）    PDF（pc） （5125KB）（491）       Knowledge map    Save With the continuous increase of electrification in seaports, the single energy supply mode of seaport microgrid is evolving towards multi-energy integration. Aimed to achieve the goals of peak carbon and carbon neutrality, an optimal carbon trading mechanism-based allocation scheme of hybrid electric and thermal storage system is proposed to further maximize the economic and environmental benefits. First, the integrated energy system model of a seaport is established, incorporating a scheme within the carbon trading market. Then, a bi-level optimization framework is proposed, in which the upper layer is utilized to optimize the allocation of the hybrid energy storage system and the lower layer is employed to optimize the operation. Afterwards, a combination algorithm of the mesh adaptive direct search and the adaptive chaotic particle swarm optimization is developed to solve the proposed problem. Finally, the real-world data of Tianjing port is utilized to verify the method. The numerical results demonstrate that with the help of the proposed method, both the cost and carbon emissions are dramatically reduced. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Two-Stage Day-Ahead and Intra-Day Rolling Optimization Scheduling of Container Integrated Port Energy System ZHOU Siyi, YANG Huanhong, HUANG Wentao, ZHOU Ze, JIAO Wei, YANG Zhenyu Journal of Shanghai Jiao Tong University    2024, 58 (9): 1357-1369.   DOI: 10.16183/j.cnki.jsjtu.2023.016 Abstract （2657）   HTML （10）    PDF（pc） （7518KB）（552）       Knowledge map    Save In view of the fact that the current integrated port energy system (IPES) considers neither the time scale difference of refrigerated containers in port scheduling nor the impact of renewable energy and load uncertainty, this paper proposes a day-ahead and intra-day two-stage rolling optimization scheduling method for a container IPES. In day-ahead scheduling, based on the temperature rise process of refrigerated containers, a port cold chain energy demand model is established, which is combined with the logistics process after the arrival of refrigerated containers. Then, the day-ahead output values of each unit in the system are obtained with the goal of the lowest operating cost. In intra-day scheduling, a two-layer rolling model is proposed to obtain the adjusted output of the port energy equipment, which considers the prediction error of shore power load and renewable energy as well as the different response speeds of cooling, heating and power. The calculation results show that the collaborative optimization scheduling of refrigerated containers and the container IPES can effectively reduce the port operation cost and carbon emissions. The two-stage day-ahead and intra-day rolling optimization scheduling can improve the economy and stability of the system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Improved Transformer-PSO Short-Term Electricity Price Prediction Method Considering Multidimensional Influencing Factors SUN Xin, WANG Simin, XIE Jingdong, JIANG Hailin, WANG Sen Journal of Shanghai Jiao Tong University    2024, 58 (9): 1420-1431.   DOI: 10.16183/j.cnki.jsjtu.2023.065 Abstract （2650）   HTML （18）    PDF（pc） （3027KB）（531）       Knowledge map    Save With the construction of a diversified electricity market, the factors affecting electricity prices are gradually increasing, and the market environment has undergone more drastic changes. In order to improve the accuracy of short-term electricity price prediction, an improved Transformer-particle swarm optimization (PSO) short-term electricity price prediction method considering multiple factors affecting electricity prices is proposed. First, based on the consideration of historical electricity prices and historical loads, the relevant factors of electricity price formation are further analyzed. The autocorrelation function is used to analyze the multi-cycle characteristics of electricity price and adjust input sequence, which overcomes the problem of limited prediction accuracy caused by using historical data only and adjusting the input sequence by experience. Then, by combining long short-term memory (LSTM), self-attention mechanism, multi-layer attention mechanism, and adopting a multi-input structure, an improved Transformer model is established to further enhance the ability of the LSTM model to capture long short-term dependencies between different time step information, to overcome the information utilization bottleneck of LSTM, and to adapt to complex multiple sequence inputs including historical electricity prices and various electricity price causes. In addition, the PSO intelligent algorithm is utilized to search for the optimal learning rate of the model at different learning stages, overcoming the limitations of manually adjusting the learning rate. Finally, the PJM market electricity price is used for example analysis. The results show that the proposed short-term electricity price prediction model can be applied to the market environment where electricity prices are affected by various factors and drastic changes, and effectively improve the accuracy of short-term electricity price prediction. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Dispatching Method of Combined Wind-Storage System for Multi-Time Scale Scenarios Application in Electricity Markets YIN Gaowen, SHEN Feifan, HUANG Sheng, WEI Juan, QU Yinpeng, WANG Pengda Journal of Shanghai Jiao Tong University    2024, 58 (9): 1410-1419.   DOI: 10.16183/j.cnki.jsjtu.2022.493 Abstract （2539）   HTML （13）    PDF（pc） （2736KB）（354）       Knowledge map    Save Aimed at the coupling problem of the combined wind-storage system participating in different call time scale scenarios in electricity markets, an optimal dispatching method of the combined wind-storage system oriented to the application of multi-time scale scenarios in electricity markets is proposed to guide the combined wind-storage system to suppress short-term wind power fluctuation, and participate in the electric energy market and the reserve ancillary service market, so as to realize the collaborative optimization among different call time scale scenarios application and maximize the economic benefits of the combined wind-storage system. First, considering the profit mechanism of different scenarios, the objective function is established with the objective of maximizing the economic benefits of multiple scenarios of the combined wind-storage system. Then, the constraints of the combined wind-storage system participating in various application scenarios and multi call time scale coupling constraints are established. Finally, the numerical simulation verifies that the proposed method can improve the comprehensive operation profit of the combined wind-storage system in the day-ahead electric energy market and the reserve ancillary service market while ensuring that the wind power fluctuation does not exceed the limit. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Switching Modeling and Application in Fault Diagnosis Algorithm Testing of Distribution Network XUE Guiting, LIU Zhe, HAN Zhaoru, SHI Fang, WANG Ti, WANG Xiao Journal of Shanghai Jiao Tong University    2024, 58 (9): 1381-1389.   DOI: 10.16183/j.cnki.jsjtu.2023.129 Abstract （2533）   HTML （6）    PDF（pc） （4150KB）（224）       Knowledge map    Save Fault diagnosis in power distribution networks is crucial for fault location, enhancement of fault processing efficiency, and reduction of power outage losses. Currently, the impact of switch operations and other interferences is seldomly considered in fault diagnosis algorithm designing and testing, which may lead to frequent mal-function and poor performance in practical applications. In this paper, a detailed analysis and modeling of the transient process of switch operation in distribution networks is proposed with the combination of the Mayr and the Helmer models. The transient waveform of the on-site operation process is compared and analyzed with the simulation waveforms generated in PSCAD. Based on the accuracy verification of the model, typical fault scenarios in distribution networks, including switch operation processes, are constructed for fault diagnosis algorithm tests. Compared to the traditional model, the model proposed can simulate and generate disturbance data close to the on-site switch operation process for reliability testing of fault diagnosis algorithms. Finally, several suggestions for optimizing the fault diagnosis algorithm and testing process are proposed through result analysis. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Joint Economic Optimization of AGV Logistics Scheduling and Orderly Charging in a Low-Carbon Automated Terminal WANG Xuan, WANG Bao, CHEN Yanping, LIU Hong, MA Xiaohui Journal of Shanghai Jiao Tong University    2024, 58 (9): 1370-1380.   DOI: 10.16183/j.cnki.jsjtu.2023.027 Abstract （2288）   HTML （13）    PDF（pc） （3702KB）（844）       Knowledge map    Save To improve the current automated guided vehicle (AGV) charging strategy at automated terminals, which is not fully coordinated with the distributed power supply, a joint optimization method of AGV logistics scheduling and orderly charging is proposed. First, the synergetic relationship between AGV logistics scheduling and charging scheduling is analyzed, and a joint optimization framework is built. Then, a method to calculate the distance traveled by AGVs while considering the segregation requirements of trucks inside and outside the terminal is proposed. Afterwards, for the AGV charging module, the judgment conditions of AGV charging status and the pile selection method are defined. Furthermore, to minimize the cost of purchasing electricity at the terminal, a joint optimization model of logistics scheduling and orderly charging is constructed by considering time-of-use tariff, distributed power feed-in tariff, power balance constraint, state of charge constraint at the termination moment, upper and lower bound constraints of decision variables, and logistics scheduling constraint. Finally, a fast solution method based on improved particle swarm optimization algorithm is proposed, of which the effectiveness and economic efficiency are verified by an actual case of a terminal. Table and Figures | Reference | Related Articles | Metrics | Comments（0） Cited: CSCD(1)

Select

Pattern Recognition and Ultra-Short-Term Probabilistic Forecasting of Power Fluctuating in Aggregated Distributed Photovoltaics Clusters WANG Yubo, HAO Ling, XU Fei, CHEN Wenbin, ZHENG Libin, CHEN Lei, MIN Yong Journal of Shanghai Jiao Tong University    2024, 58 (9): 1334-1343.   DOI: 10.16183/j.cnki.jsjtu.2023.048 Abstract （2241）   HTML （9）    PDF（pc） （4167KB）（502）       Knowledge map    Save The quantitative evaluation of the uncertainty in distributed photovoltaic power is significant for the safe and stable operation of distribution network. Considering the significant differences in power characteristics of different output fluctuation patterns, in order to obtain a prediction model suitable for different fluctuation patterns and to perform a refined assessment of power uncertainty, this paper proposes a method for pattern recognition and ultra-short-term probabilistic forecasting of power fluctuating in aggregated distributed photovoltaic clusters. First, the satellite cloud images and photovoltaic power data are integrated, and the pattern recognition model of fluctuation is constructed via the feature extraction of power fluctuation, realizing the mining of fluctuation rules. On this basis, the difference in predictability of different fluctuation patterns and the correlation between fluctuation patterns and prediction errors are considered via classification modeling, so that the width of prediction interval can better adapt to the characteristics of prediction error distribution. Thus, refined consideration of power uncertainty of different fluctuation patterns is realized to improve the precision of probabilistic prediction, provide more references for power grid dispatching, and weaken the influence of the strong volatility in distributed photovoltaic power on the power system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Parameter Control of Adaptive Bistable Point Absorber Wave Energy Converter in Irregular Waves LI Yang, ZHANG Xiantao, XIAO Longfei Journal of Shanghai Jiao Tong University    2025, 59 (3): 293-302.   DOI: 10.16183/j.cnki.jsjtu.2023.309 Abstract （2216）   HTML （19）    PDF（pc） （4987KB）（372）       Knowledge map    Save Although the adaptive bistable wave energy generation device solves the problem that the bistable system may be difficult to cross the barrier when the amplitude of the incident wave is small, its efficiency can still be improved. Previous studies have proved that the change of the parameters of the device will have a great impact on its performance, and the optimal device parameters are closely related to the spectral peak frequency at a given time. Therefore, in the control study of the device, a control scheme is designed and the device parameters are adjusted accordingly in order to improve efficiency assuming that the peak frequency within a period of time is predictable. In this study, three control parameters are selected, and the optimal device parameter library with different spectral peak frequencies is determined by simulation calculation. The control module is then added to the simulation program to control the parameters by interpolation. The results show that the device with variable parameter control improves energy capture efficiency. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Online Monitoring Method for Inertial Support Capacity of Point-to-Grid in New Power Systems DENG Xiaoyu, LIU Muyang, CHANG Xiqiang, NAN Dongliang, MO Ruo, CHEN Junru Journal of Shanghai Jiao Tong University    2024, 58 (9): 1390-1399.   DOI: 10.16183/j.cnki.jsjtu.2023.029 Abstract （2184）   HTML （10）    PDF（pc） （2472KB）（109）       Knowledge map    Save An accurate and timely monitoring for the inertia support capability of the point of interconnection of aggregated sources to the grid in a low-inertia new power system is crucial for the safety, stability, and economic operation of the system. In order to explain the basic idea of the online point-to-grid inertia monitoring method, the definition of inertia of power system based on the swing equation and existing online monitoring methods are analyzed. Then, in order to improve the accuracy of the existing online inertia monitoring method, an equivalent inertia constant identification method based on the regression method is developed. Combining the proposed inertia constant identification method with the online inertia monitoring method, a systematic method for online monitoring of the inertia support capacity of point-to-grid in new power system is developed based on synchronous phasor measurement units. Finally, the simulation analysis of a modified New England 10-machine 39-bus system proves the accuracy and the feasibility of the developed real-time inertia monitoring method for the new power system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Robust Optimal Scheduling of Micro Energy Grid Considering Multi-Interval Uncertainty Set of Source-Load and Integrated Demand Response MI Yang, FU Qixin, ZHAO Haihui, MA Siyuan, WANG Yufei Journal of Shanghai Jiao Tong University    2024, 58 (9): 1323-1333.   DOI: 10.16183/j.cnki.jsjtu.2023.022 Abstract （2141）   HTML （8）    PDF（pc） （1898KB）（457）       Knowledge map    Save Aiming at the uncertainty of the source and load in micro energy grid, a robust optimal scheduling model considering multi-interval uncertainty set of source-load and integrated demand response is proposed. First, considering the uncertainty of wind power, photovoltaic output and electric, and thermal and cooling loads in the micro energy grid, a multi-interval uncertainty set of source-load is established. Then, in order to fully tap the potential of load side dispatching, an integrated demand response model is established, which includes reducible electric load, transferable electric load, flexible cooling, heating load, and replaceable load, based on which, the uncertainty of integrated demand response is considered. Afterwards, with the lowest dispatching cost of micro energy grid as the objective function, a two-stage robust optimal scheduling model of micro energy network is constructed, which considers the multi-interval uncertainty set of source load and the integrated demand response. The model is solved by the column and constraint generation algorithm, the strong duality theory, and the large M method. Finally, the rationality and effectiveness of the proposed model are verified through the analysis of numerical examples. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Short-Term Carbon Emission Accounting Method for Power Industry Using Electricity Data Based on a Combined Model of CNN and LightGBM ZENG Jincan, HE Gengsheng, LI Yaowang, DU Ershun, ZHANG Ning, ZHU Haojun Journal of Shanghai Jiao Tong University    2025, 59 (6): 746-757.   DOI: 10.16183/j.cnki.jsjtu.2023.382 Abstract （2101）   HTML （3）    PDF（pc） （6089KB）（3097）       Knowledge map    Save The electric power industry plays a pivotal role in carbon emission control. Accurate and real-time accounting of carbon emissions in the power industry is essential for supporting the carbon reduction of the power industry. At present, the measurement of carbon emissions in the power industry relies mainly on direct measurement or the accounting methods, which often struggles to balance low measurement costs with real-time accuracy. Therefore, in this paper, the robust power data infrastructure in the power industry is leveraged and the correlation between electricity consumption and carbon emissions is explored to propose a short-term electricity-to-carbon method using machine learning methods based on historical data of electricity. This method utilizes convolutional neural networks (CNNs) for feature extraction, and light gradient boosting machine (LightGBM) for carbon emission estimation based on extracted features. Moreover, K-fold cross-validation is used in model training, with parameter optimization using grid search to enhance the generalization capability and robustness of the model. To validate the proposed method, it is compared with other machine learning models under the same data segmentation condition for daily and hourly data sets. The results indicate that the proposed model outperforms other models in both performance evaluation and the consistency between estimated and target values. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Coordinate Scheduling Model of Electric Vehicle-Unmanned Aerial Vehicle Joint Rescue System BAI Wenchao, BAN Mingfei, SONG Meng, XIA Shiwei, LI Zhiyi, SONG Wenlong Journal of Shanghai Jiao Tong University    2024, 58 (9): 1443-1453.   DOI: 10.16183/j.cnki.jsjtu.2023.052 Abstract （2091）   HTML （12）    PDF（pc） （3151KB）（520）       Knowledge map    Save The rapid development of electric vehicles (EVs) and unmanned aerial vehicles (UAVs) provides new ways for personnel search and material distribution during emergency periods. This paper proposes an EV-UAV joint rescue system, in which the UAVs use the EVs as charging and maintenance base stations to provide various services for the objects to be rescued, and the EVs can use distributed generations to obtain diversified electricity supply, which improves the adaptability and endurance level of the system in emergencies. The coordinated scheduling model of the EV-UAV system is established in the mixed-integer linear programming (MILP) formulation, which considers factors including electricity consumption, electricity replenishment, loading capacity, distribution route, and distribution time window of the EVs and the UAVs. Case studies verify the validity of the model proposed, compare the EV-UAV and ground vehicle (GV)-UAV rescue systems, and illustrate the technical characteristics and application potential of the EV-UAV system in emergency assistance. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Robust Optimal Scheduling of Agricultural Microgrid Combined with Irrigation System Under Uncertainty Conditions YANG Sen, GUO Ning, ZHANG Shouming Journal of Shanghai Jiao Tong University    2024, 58 (9): 1432-1442.   DOI: 10.16183/j.cnki.jsjtu.2023.035 Abstract （2082）   HTML （9）    PDF（pc） （2680KB）（172）       Knowledge map    Save Agricultural microgrids offer a promising solution for energy supply in remote rural areas in a low-cost manner. In this paper, under uncertain conditions of renewable energy output and electricity load demand, a robust optimal scheduling model combined with the isolated agricultural microgrid and irrigation system containing a pumped hydro storage (PHS) power station is proposed, considering the factors that the wind-landscape pumped storage integrated agricultural microgrid can satisfy the uncertain fluctuations of power load demand and water load demand. By utilizing the abundant water resources in rural areas and the advantages of landscape drainage and storage compensation, the total cost of the system is minimized while the absorption of renewable energy is increased. Considering distributed generation, power load demand and water load demand, turbine flow, and irrigation flow, the proposed model is characterized by diversity, multi-constraint, and discontinuity. A gravitational whale optimization algorithm (GWOA) is proposed to solve the model. The simulation results of an agricultural microgrid show that the GWOA can obtain a more competitive solution than the CPLEX solver and other newly developed algorithms do. In addition, the impact of the change of water load demand caused by precipitation uncertainty on the operating cost of the irrigation system and the necessity of using PHS power station are explored. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Influence of DC-Bus Voltage on Synchronization Stability of Grid-Following Converters SI Wenjia, CHEN Junru, ZHANG Chenglin, LIU Muyang Journal of Shanghai Jiao Tong University    2025, 59 (3): 313-322.   DOI: 10.16183/j.cnki.jsjtu.2023.321 Abstract （2076）   HTML （7）    PDF（pc） （2943KB）（251）       Knowledge map    Save With the increasing penetration of new energy sources and the development of new power systems, grid-following converter (GFL) plays a crucial role in maintaining the stability of power systems. However, existing transient stability analyses of GFLs assume that the direct current (DC) side behaves as a constant-voltage source, neglecting the effects of DC-bus voltage control. This paper aims to investigate the transient instability mechanism of GFL considering DC-bus voltage control. First, a transient synchronous stability model considering DC voltage control is established, followed by an analysis of the transient synchronous stability of GFL under DC-bus voltage control. The findings indicate that DC voltage control increases the active current reference value and decreases the equivalent damping of the GFL, which in turn reduces its transient synchronous stability of GFL. By increasing the proportional coefficient or reducing the integral coefficient of DC-bus voltage control, transient synchronous stability can be appropriately improved. Finally, the theoretical analysis is validated through MATLAB/Simulink simulations. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

An Optimization Method for Iteration Path Search of Large-Scale Power Grid Unit Commitment State CUI Yiyang, PAN Dounan, LI Canbing, LIU Jianzhe Journal of Shanghai Jiao Tong University    2025, 59 (6): 711-719.   DOI: 10.16183/j.cnki.jsjtu.2024.301 Abstract （2052）   HTML （18）    PDF（pc） （1544KB）（50）       Knowledge map    Save To address the computational challenge posed by the “curse of dimensionality” inherent in traditional branch and bound algorithms for large-scale power grid unit commitment problems, an optimization method for iteration path search of unit commitment state is proposed. To prevent the loss of the optimal solution due to the simplification of the problem and the reduction of the feasible region, the determination of the unit state scheme is divided into a two-stage process of depth traverse and breadth iteration. Based on an initial solution, the unit dynamic priority list is used as the search direction for the unit state iteration path. In deep traverse stage, the optimal shutdown redundant units and their corresponding shutdown time are determined. Breadth iteration is then used to expand the feasible region of the problem to improve the optimality of the solution. The results of a comparative case study conducted on the IEEE 118 system and ACTIVSg10k system indicate that the proposed method effectively reduces the scale of the problem, minimizes the number of unit state attempts, and achieves efficient search and iteration of unit states, exhibiting fast computational speed, high efficiency, which has practical applicability for solving problems of large-scale unit commitment. Table and Figures | Reference | Supplementary Material | Related Articles | Metrics | Comments（0）

Select

Shared Energy Storage Multi-Objective Allocation Strategy Considering Integrated Energy Microgrid Access to Active Distribution Network MI Yang, CHEN Yuyang, CHEN Boyang, HAN Yunhao, YUAN Minghan Journal of Shanghai Jiao Tong University    2024, 58 (9): 1309-1322.   DOI: 10.16183/j.cnki.jsjtu.2023.021 Abstract （2033）   HTML （16）    PDF（pc） （4556KB）（234）       Knowledge map    Save In order to give full play to the advantages of shared energy storage in improving economy and energy utilization, while considering the role of multi-energy complementation and coupling of integrated energy microgrids in active distribution networks, a multi-objective optimal allocation strategy of shared energy storage is proposed for the active distribution network connected with integrated energy microgrid. First, the optimization objectives of the economy and voltage stability of the distribution network and the configuration capacity of the shared energy storage are analyzed, the coordinated operation of the source-net-load side multi-flexible resources of the active distribution network is considered, and the active distribution network and the integrated energy microgrid are modeled. Then, the model is solved based on the Pareto optimal multi-objective particle swarm algorithm. Finally, the optimization algorithm of shared energy storage configuration is established in conjunction with the IEEE 33-node distribution system to verify the effectiveness of the proposed configuration strategy. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Distributed Photovoltaic Power Outlier Detection Based on Quantile Regression Neural Network WANG Xiaoqian, ZHOU Yusheng, MAO Yuanjun, LI Bin, ZHOU Wenqing, SU Sheng Journal of Shanghai Jiao Tong University    2025, 59 (6): 836-844.   DOI: 10.16183/j.cnki.jsjtu.2023.412 Abstract （1967）   HTML （1）    PDF（pc） （3885KB）（69）       Knowledge map    Save The distributed photovoltaic power generation system is widely dispersed and lacks a scientific and standardized operation and maintenance management system. Due to the limited availability of data, it is difficult to accurately detect abnormal conditions in photovoltaic devices caused by fluctuations in weather. In this paper, according to the operation and maintenance status and data characteristics of distributed photovoltaic, a quantile regression neural network (QRNN)-based method is proposed for detecting photovoltaic power outliers. First, the solar irradiance characteristics of sunny days are analyzed, and the influence of rainy weather is excluded by using a sunny day screening method. Then, the power output correlation of different power stations is analyzed to identify the photovoltaic stations with high power output correlation, which is used as a horizontal reference. Subsequently, the curves of the power output of the stations tested on different sunny days are compared vertically to eliminate the interfering factors such as weather and environmental conditions. The measured active power data is fed into the QRNN model to establish the normal active power range for the photovoltaic system, whose threshold is used to detect photovoltaic power outliers. The simulation results of actual photovoltaic system data show that the method proposed can eliminate the meteorological influence, accurately identify the faulty photovoltaic system, and promote the fine operation and maintenance of distributed photovoltaic. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Optimal Scheduling Strategy of Newly-Built Microgrid in Small Sample Data-Driven Mode CHEN Shi, YANG Linsen, LIU Yihong, LUO Huan, ZANG Tianlei, ZHOU Buxiang Journal of Shanghai Jiao Tong University    2025, 59 (6): 732-745.   DOI: 10.16183/j.cnki.jsjtu.2023.394 Abstract （1909）   HTML （8）    PDF（pc） （4880KB）（203）       Knowledge map    Save Newly built microgrids lack historical operation data, making it challenging to predict renewable power output accurately using conventional data-driven methods, which in turn affects the accuracy of scheduling plans. To address this problem, an optimal scheduling method for newly built microgrids in scenarios with limited sample data is proposed. First, an improved network structure integrating a domain adversarial neural network with a long-short-term memory network is designed. The domain adversarial approach and gradient inversion mechanism are incorporated into transfer learning to improve the generalization ability of the model. This reduces the domain distribution discrepancy in the data, and uses the rich operation data of power stations with similar output characteristics to predict the output of the target station, which overcomes the challenge of poor accuracy under the conditions of small samples. Additionally, the optimal scheduling model is transformed into a Markov decision process and solved using double-delay deep deterministic policy gradient algorithm. Finally, the effectiveness of the proposed method is validated through a case study involving an improved CIGRE 14-node microgrid. Table and Figures | Reference | Supplementary Material | Related Articles | Metrics | Comments（0）

Select

Unit Commitment Optimization Model Considering Impact of Multiple Operating Conditions on Unit Life Loss LUO Yifu, HU Qinran, QIAN Tao, CHEN Tao, ZHANG Yuanshi, ZHANG Fei, WANG Qi Journal of Shanghai Jiao Tong University    2025, 59 (6): 768-779.   DOI: 10.16183/j.cnki.jsjtu.2023.401 Abstract （1909）   HTML （5）    PDF（pc） （3746KB）（766）       Knowledge map    Save Thermal power units face a dilemma of accelerated lifespan degradation and extended service duration. On one hand, large-scale integration of new energy sources has increased peak shaving conditions and accelerated losses of the units. On the other hand, service units will reach designed lifespan before carbon neutrality is achieved, while flexible operation of the power system necessitates extending their service life of units. Therefore, it is of great significance to consider the losses caused by varicus operating conditions on the lifespan of the unit and optimize the operating structure of the unit in scheduling simulation for unit longevity and carbon reduction efforts. To make unit life losses in theoretical research more practical, the traditional model that averages the losses in deep peak shaving conditions has been discarded. Instead, new judgment criteria for conventional and various special operating conditions of thermal power units are established. The lifespan loss cost of the unit is integrated into the operating objective function and the corresponding constraint conditions are modified. Finally, a unit commitment model considering the multi-operating condition lifespan losses of thermal power units is constructed. Example simulations indicate that the conventional model underestimates the actual loss cost of the units. In constrast, the proposed model can not only reduce the operating cost and unit life loss by considering the lifespan impacts of multi-operating conditions, but also enhance the peak shaving capacity of thermal power units and promote wind power consumption. Table and Figures | Reference | Supplementary Material | Related Articles | Metrics | Comments（0）