Integrated Intelligent Energy

Digital empowerment of transport-energy integration：Technological pathways， application scenarios and future prospects

LIU Bin, SUN Zhou, JIANG Zhiwei, GUO Mingyang, CAO Can

2025, 47(2): 1-12. doi:10.3969/j.issn.2097-0706.2025.02.001

Asbtract ( 109 )

HTML ( 7)

PDF (1018KB) ( 64 )

Figures and Tables | References | Related Articles | Metrics

With the advancement of China's "dual-carbon" strategic goals and the accelerated development of the construction of a strong transportation network， the deep integration of transportation and energy has become a vital measure to enhance new productivity in the transportation systems. Driven by the wave of digitalization， technologies such as the internet of things （IoT），big data， and artificial intelligence （AI） offer new opportunities for the integration of transportation and energy. In this study， how digital technologies empower transport-energy integration is analysed from three aspects： technological pathways， application scenarios， and future prospects. The current state of transport-energy integration is reviewed and the advantages and challenges of digital technology applications in this field are explored. Leveraging typical cases such as wind-solar-storage-charge integrated intelligent highways， the technological pathways and demonstration applications of digital empowerment of transport-energy are expounded. The future prospects of digital technologies in transport-energy integration are envisioned and strategic recommendations in areas such as government policies， standard systems， and business models are offered. This study aims to provide reference for promoting the digitalization process of transportation and energy integration in China.

Research on application scenarios and technical system for transportation-energy integration

ZHANG Min, WANG Yanhe, SUN Zhou, LIU Bin, JIANG Zhiwei, CAO Can, GAO Feng

2025, 47(2): 13-28. doi:10.3969/j.issn.2097-0706.2025.02.002

Asbtract ( 76 )

HTML ( 4)

PDF (1131KB) ( 52 )

Figures and Tables | References | Related Articles | Metrics

Developing renewable energy sources such as wind and solar power according to local conditions and promoting comprehensive， multi-field， and in-depth integration of transportation and energy aims to continuously enrich and improve the development concept and technical system of transportation-energy integration. Based on existing research and incorporating scenario analysis， this paper summarized the core concept and basic characteristics of transportation-energy integration. A scenario system was established， covering six major scenarios： land transportation， land-based logistics， digital infrastructure along transportation routes， land-based economy， buildings along the routes， and operational conditions along the routes. Based on the technical requirements for each scenario， the paper proposed a "three horizontal and one vertical" technical system architecture for transportation-energy integration. This framework included the identification and organization of key technologies at the physical， digital， application， and mechanism layers. A directory of key technologies for transportation-energy integration was compiled， aimed at providing technical references for domestic and international scholars conducting researches on transportation integration.

Energy storage capacity configuration and scheduling optimization strategy for the expressway microgrids

CHEN Xiaoqi, ZHANG Min, SUN Zhou, LIU Bin, MAO Yong, TAO Yongjin

2025, 47(2): 29-40. doi:10.3969/j.issn.2097-0706.2025.02.003

Asbtract ( 83 )

HTML ( 7)

PDF (3057KB) ( 55 )

Figures and Tables | References | Related Articles | Metrics

To improve the utilization of clean energy for highways and achieve the scientific and economical allocation and flexible scheduling optimization of energy storage facilities， an energy storage capacity allocation and scheduling optimization model for highway photovoltaic-storage-charging microgrids is proposed. A novel solution algorithm was used to solve the model and conduct simulation analysis. Based on meteorological information along the highways and load conditions of highway service areas， a mathematical model for the highway photovoltaic-storage-charging microgrids was established. Monte Carlo simulations were conducted to analyze the charging loads of electric vehicles in the service areas. Additionally， based on the load characteristics of highway service areas， management centers， toll stations， and tunnels， a highway microgrid load model was developed. From the perspective of the economic efficiency of highway microgrids， a bi-level optimization model was established to achieve integrated optimization of energy storage system allocation and scheduling. The （Exponential Distribution Optimizer-Mixed-Integer Linear Programming， EDO-MILP） algorithm was applied to solve the model. Taking the distributed photovoltaic-storage demonstration project on the Panzhihua-Dali Expressway （Sichuan section） as an example， simulation and optimization were conducted over a period of 8 760 h. The simulation results showed that for microgrids with a photovoltaic installed capacity of 2 MW and a maximum load of approximately 800 kW， the introduction of 1 131 kW·h/283 kW of energy storage devices led to an annual increase in system revenue of 384 000 yuan， effectively improving the economic efficiency. This was a 42.8% improvement compared to the non-energy storage scheme and a 4.3% improvement over the empirical scheme. Additionally， the allocation scheme increased the microgrid system's consumption capacity for photovoltaic green electricity. Compared to the non-energy storage scheme， the consumption capacity increased by 5.7%， and compared to the traditional scheme， it improved by 3.4%.

Optimization of travel routes and economic operation strategies for integrated transportation and energy systems considering EV carbon emissions

YANG Jian, HAO Guojie, WU Xinyue, GUO Mingqiang, CHEN Chong, LEI Zhimin

2025, 47(2): 41-49. doi:10.3969/j.issn.2097-0706.2025.02.004

Asbtract ( 43 )

HTML ( 3)

PDF (1432KB) ( 15 )

Figures and Tables | References | Related Articles | Metrics

To address the unbalanced power flow in distribution networks of urban areas caused by the large-scale grid-connection of electric vehicles （EVs）， a method for the optimization of travel routes and economic operation strategies for integrated transportation and energy systems considering EV carbon emissions was proposed， along with corresponding solution methods. The urban areas and their functions were analyzed， and the Huff model was used to quantify the regional travel attractiveness， enabling precise zoning of cities and numerical simulation of EV charging loads. The flow fueling location model （FRLM） evaluation system was introduced to select suitable locations for EV charging stations. This helped organize the mapping of EV loads to the power flow grid， thereby forming a "transportation-energy" coupling network that took both EV charging service coverage and power supply uniformity into consideration. Based on the carbon emissions from EV travel， the user equilibrium theory was adaptively improved， complemented by a power flow uniformity evaluation function guided by grid stability optimization. Then，an EV travel route optimization system that guided the reasonable distribution of local load peaks was established， ensuring that the proposed solution aligned with the expectations for economic and low-carbon operation. Moreover， a simulation analysis was conducted on an IEEE 33 node distribution network and a main road network model of an urban area. The results verified the effectiveness and feasibility of the proposed model.

Optimization configuration of photovoltaic and energy storage microgrid system in high way service areas based on energy self-sufficiency

LIU Bin, LUO Yi, SUN Zhou, CHEN Xiaoqi, JIANG Zhiwei, JIANG Chun, CHEN Mingtao

2025, 47(2): 50-59. doi:10.3969/j.issn.2097-0706.2025.02.005

Asbtract ( 58 )

HTML ( 2)

PDF (1309KB) ( 28 )

Figures and Tables | References | Related Articles | Metrics

Building upon the demand for energy self-sufficiency of highways，particularly within weak grid networks， this study proposes an engineering-oriented dual-layer optimization algorithm model for scientific configuration of photovoltaic and energy storage systems for typical microgrids with multiple transformer areas in highway service zones.In the inner layer，an operational optimization scheduling model was established with the objective of minimizing energy consumption costs and reverse power flow to the grid. This model simulated the optimal annual scheduling of the system based on specific photovoltaic and energy storage capacity parameters and calculated indicators such as electricity purchase costs. It also accounted for safety constraints within multiple distribution systems. The outer layer integrated the annual electricity purchase costs with the investment and operational costs of the photovoltaic and energy storage system， aiming to minimize the annualized equivalent cost. It also considered installation capacity limitations to generate the optimal photovoltaic and energy storage capacity configuration scheme in service areas. The algorithm solving process was designed using an improved particle swarm optimization （PSO） algorithm and mixed-integer programming solver for solving constraint interger programs（SCIP） for efficient model solution. A case demonstrated that the proposed model could effectively achieve the optimal configuration of photovoltaic and energy storage capacity， resulting in an annual saving of 27.4% in electricity purchase costs. Moreover， the payback period for the photovoltaic storage system investment was 47.6% shorter than the planned operational lifespan， significantly reducing the overall system cost.

Research on voltage control of distribution networks with high-proportion household photovoltaics based on cluster division

FENG Kan, WEI Libao, WU Zhaobin, LIU Wenjin, XU Qing, HAO Guojie

2025, 47(2): 60-70. doi:10.3969/j.issn.2097-0706.2025.02.006

Asbtract ( 53 )

HTML ( 1)

PDF (1085KB) ( 28 )

Figures and Tables | References | Related Articles | Metrics

In a distribution network with a high proportion of household photovoltaic access， changes in source and load characteristics lead to numerous over-limit voltages， necessitating an effective voltage control method for distribution networks. In this study， a comprehensive division index， considering electrical modularity index， coupling degree index and power balance index， was established to realize the cluster division of a distribution network with a high proportion of household photovoltaics. Among the nodes with energy storage systems in each cluster， key control nodes in each cluster were selected using active-voltage sensitivity. Considering energy storage for voltage regulation， under the constraints of energy storage charging and discharging operations， a voltage control model based on cluster division was constructed with the minimum voltage deviation and network loss as the objectives. According to the power demand of the clusters containing the nodes with over-limit voltage， the energy storage systems at the key control nodes were preferentially regulated to realize effective voltage control. The IEEE 33 node system with a high proportion of household photovoltaics and energy storage system access was analyzed to verify the effectiveness of the voltage control method for the distribution network based on cluster division.

Photovoltaic power prediction based on K-means clustering and the LSTM-SVR-DE model

ZHANG Yuanxi, YANG Guohua, YANG Na, LI Zhen, MA Xin, LIU Haorui, NAN Shaoshuai

2025, 47(2): 71-78. doi:10.3969/j.issn.2097-0706.2025.02.007

Asbtract ( 56 )

HTML ( 6)

PDF (980KB) ( 34 )

Figures and Tables | References | Related Articles | Metrics

To improve the accuracy of photovoltaic power prediction， a combined prediction model based on Long Short-Term Memory（LSTM） neural networks and Support Vector Regression（SVR） was proposed. Both the LSTM and SVR models were used separately to predict photovoltaic power. On this basis， a Stacking ensemble strategy was employed to linearly combine the predictions of these two models， with the Differential Evolution（DE） algorithm optimizing the weight coefficients. Simulations and comparative analyses were conducted using real data from a photovoltaic power station in Ningxia. The results showed that the proposed method reduced prediction errors by approximately 70% compared to the LSTM and SVR models.

Research on multi-scale load prediction in parks based on CNN-LSTM-Self attention

YANG Lanqian, GUO Jinmin, TIAN Huili, HUANG Chang, LIU Min, CAI Yang

2025, 47(2): 79-87. doi:10.3969/j.issn.2097-0706.2025.02.008

Asbtract ( 105 )

HTML ( 5)

PDF (1224KB) ( 51 )

Figures and Tables | References | Related Articles | Metrics

Accurate load prediction is critical for improving the energy efficiency and profitability of zero-carbon smart parks. However， the application of conventional load prediction techniques faces two main challenges which are the difficulty in obtaining hourly numerical weather forecast data and the need for predictions across different time scales. In the absence of weather forecast data， a method using Convolutional Neural Networks（CNN） was proposed to extract the coupled spatial features between multiple loads. The reconstructed features were input into a Long Short-Term Memory（LSTM） network to extract temporal features of the load， followed by the application of a self-attention mechanism to enhance the model's ability to extract feature information. A fully connected network was then employed for load prediction， resulting in a multi-variable-load， multi-time-scale prediction model based on CNN-LSTM-Self attention. A case study of a park was used to predict its cooling， heating， and electrical loads for the next 1 hour， 1 day， and 1 week. Experimental results showed that the CNN-LSTM-Self attention model outperformed the CNN， LSTM， and CNN-LSTM models in terms of prediction accuracy across multiple time scales. Specifically， the CNN-LSTM-Self attention model showed a more significant advantage in predicting the 1-hour load， with the mean absolute percentage error（MAPE） of cooling， heating， and electrical load predictions improved by 16.25%， 19.16%， and 10.24%， respectively， compared to the CNN-LSTM model.

Application and prospects of deep neural network in new energy systems

SHI Xin, LIU Qiyang, GAO Feng

2025, 47(2): 88-101. doi:10.3969/j.issn.2097-0706.2025.02.009

Asbtract ( 80 )

HTML ( 2)

PDF (1247KB) ( 39 )

Figures and Tables | References | Related Articles | Metrics

Driven by the "dual carbon" goal， new energy sources such as wind and solar energy are developing rapidly. However， challenges such as wind and solar curtailment， resource waste， and low storage efficiency persist in energy production， consumption， and storage processes. Therefore， it is imperative to develop more intelligent new energy systems. Deep neural network（DNN）， a key technology in the development of next-generation artificial intelligence， has powerful capabilities in fitting complex functions due to its deep structure. It addresses the problem that traditional machine learning algorithms face when modeling and analyzing big data due to their limited ability to extract the most representative features from the data. The focus is on the application of DNN in new energy systems， providing an overview of DNN， the demand for DNN in new energy system， its applications in modeling and simulation， planning and optimization， operation and maintenance， operational control， and system management of new energy systems. The challenges of applying DNN in new energy systems are summarized and prospects for future development are outlined， aiming to provide reference for professionals in related industries.

Table of Content