A prediction method for power grid carbon emission factor based on T-Graphormer

doi:10.3969/j.issn.2097-0706.2025.06.004

Abstract

Abstract:

The carbon emission factor of the power grid is an important indicator for assessing the environmental impact of electricity consumption. Accurate prediction of the power grid carbon emission factor for future time periods is crucial for guiding users to actively participate in demand-side response and achieving clean and low-carbon electricity utilization. Based on the typical spatio-temporal fusion characteristics of the power grid's energy flow，a prediction model for hourly power grid carbon emission factor is proposed，utilizing the T-Graphormer graph neural network. The model incorporates topological information from power grid nodes and historical carbon emission factor data. Through a gated temporal convolution block，the carbon emission factor is mapped into a high-dimensional space，with central and positional encodings embedded into node features. An encoder-decoder structure is then employed for spatio-temporal data mining，and the predicted power grid carbon emission factor is obtained through a multi-layer perceptron. The performance of the proposed model is validated using carbon emission factor data from regions of the UK national grid. The results demonstrates that the prediction model outperforms traditional graph neural network prediction models.

Key words: power grid carbon emission factor, T-Graphormer, graph neural network, Transformer, time series, demand-side response

CLC Number:

TP18：TM711

ZHAN Guohua, ZHANG Xianyong, WEI Shengying, ZHANG Xiaoshun, LI Li. A prediction method for power grid carbon emission factor based on T-Graphormer[J]. Integrated Intelligent Energy, 2025, 47(6): 30-36.

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Table 1

Table 2

Comparison of predicted results

模型	3 h		6 h		12 h		24 h		平均值
模型	$k M A E$	$k R M S E$	$k M A E$	$k R M S E$	$k M A E$	$k R M S E$	$k M A E$	$k R M S E$	$k M A E$	$k R M S E$
STGCN	0.163 2	0.191 6	0.191 7	0.221 6	0.197 0	0.226 0	0.213 5	0.240 6	0.191 4	0.220 0
STGCN-Cheb	0.156 6	0.187 7	0.189 0	0.219 1	0.196 2	0.224 7	0.206 0	0.236 0	0.186 9	0.216 9
ASTGCN	0.143 4	0.171 3	0.186 5	0.211 1	0.194 8	0.223 3	0.203 1	0.230 4	0.182 0	0.208 9
T-Graphormer	0.135 2	0.164 1	0.168 4	0.199 3	0.193 9	0.222 8	0.198 0	0.225 8	0.172 7	0.201 8

Table 2

Fig.5

Fig.6

References 24

[1]	康重庆, 杜尔顺, 李姚旺, 等. 新型电力系统的“碳视角”:科学问题与研究框架[J]. 电网技术, 2022, 46(3): 821-833.
	KANG Chongqing, DU Ershun, LI Yaowang, et al. Key scientific problems and research framework for carbon perspective research of new power systems[J]. Power System Technology, 2022, 46(3): 821-833.
[2]	孔慧超, 黄学劲, 王文钟, 等. 园区受端新型电力系统电力电量再平衡方法[J]. 综合智慧能源, 2024, 46(2):68-74.
	KONG Huichao, HUANG Xuejin, WANG Wenzhong, et al. Electric power and energy rebalancing method for new power systems at receiving ends of industrial parks[J]. Integrated Intelligent Energy, 2024, 46(2): 68-74.
[3]	喻小宝, 赵雯婧, 孙艺新. 计及双重不确定性的综合能源系统运行优化模型研究[J]. 综合智慧能源, 2023, 45(10): 10-17.
	YU Xiaobao, ZHAO Wenjing, SUN Yixin. Integrated energy system operation optimization model considering double uncertainties[J]. Integrated Intelligent Energy, 2023, 45(10): 10-17.
[4]	RE100 Members. Over 400 RE100 companies have made a commitment to go '100% renewable'[EB/OL]. (2020-12-08)[2024-06-01]. https://www.there100.org/re100-members.
[5]	魏夕凯, 谭效时, 林明, 等. 2005—2035年全国电网碳排放因子的计算与预测[J]. 综合智慧能源, 2024, 46(3): 72-78.
	WEI Xikai, TAN Xiaoshi, LIN Ming, et al. Calculation and prediction of carbon emission factors for the national power grid from 2005 to 2035[J]. Integrated Intelligent Energy, 2024, 46(3): 72-78.
[6]	SUN W, REN C M. Short-term prediction of carbon emissions based on the EEMD-PSOBP model[J]. Environmental Science and Pollution Research International, 2021, 28(40): 56580-56594.
[7]	张宁, 李姚旺, 黄俊辉, 等. 电力系统全环节碳计量方法与碳表系统[J]. 电力系统自动化, 2023, 47(9): 2-12.
	ZHANG Ning, LI Yaowang, HUANG Junhui, et al. Carbon measurement method and carbon meter system for whole chain of power system[J]. Automation of Electric Power Systems, 2023, 47(9): 2-12.
[8]	杨雨瑶, 潘峰, 钟立华, 等. 基于神经网络的电力系统节点碳排放因子预测方法[J]. 广东电力, 2023, 36(10): 2-9.
	YANG Yuyao, PAN Feng, ZHONG Lihua, et al. Study on prediction method of node carbon emission factors in power system based on neural network[J]. Guangdong Electric Power, 2023, 36(10): 2-9.
[9]	雷景生, 李冉, 杨胜英, 等. 融合社交信息的多图神经网络会话推荐方法[J]. 计算机工程与应用, 2023, 59(15): 264-273.
	LEI Jingsheng, LI Ran, YANG Shengying, et al. Session-based recommendation based on multi-graph neural network incorporating social information[J]. Computer Engineering and Applications, 2023, 59(15): 264-273.
[10]	SHUI Z R, KARYPIS G. Heterogeneous molecular graph neural networks for predicting molecule properties[C]//Proceedings of 2020 IEEE International Conference on Data Mining (ICDM). IEEE, 2020: 492-500.
[11]	姜山, 丁治明, 徐馨润, 等. 面向路网交通流态势预测的图神经网络模型[J]. 计算机科学与探索, 2021, 15(6): 1084-1091.
	JIANG Shan, DING Zhiming, XU Xinrun, et al. Graph neural network for traffic flow situation prediction[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 1084-1091.
[12]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. (2017-02-22)[2024-06-01]. https://arxiv.org/abs/1609.02907v4.
[13]	朱子意, 孙晓燕, 柳先彪, 等. 基于相似用电单元及图卷积神经网络的电力负荷预测[J]. 电力科学与工程, 2023, 39(7): 9-23.
	ZHU Ziyi, SUN Xiaoyan, LIU Xianbiao, et al. Power load forecasting based on similar power units and graph convolution neural network[J]. Electric Power Science and Engineering, 2023, 39(7): 9-23.
[14]	VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J/OL]. ICLR,(2018-02-04)[2024-06-01]. https://arxiv.org/abs/1710.10903.
[15]	荣沛, 苏凡军. 基于知识图注意网络的个性化推荐算法[J]. 计算机应用研究, 2021, 38(2): 398-402.
	RONG Pei, SU Fanjun. Personalized recommendation algorithm based on knowledge graph attention network[J]. Application Research of Computers, 2021, 38(2): 398-402.
[16]	YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting[J]. ArXiv e-Prints, 2017: arXiv: 1709.04875.
[17]	GUO S N, LIN Y F, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 922-929.
[18]	林琳, 邓国新, 樊浩. 基于天气模式识别与时空图神经网络的新能源发电功率预测[J]. 电气自动化, 2023, 45(3): 30-33.
	LIN Lin, DENG Guoxin, FAN Hao. New energy generation power prediction based on weather pattern recognition and spatiotemporal graph neural network[J]. Electrical Automation, 2023, 45(3): 30-33.
[19]	YAN H Y, MA X L, PU Z Y. Learning dynamic and hierarchical traffic spatiotemporal features with transformer[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11): 22386-22399.
[20]	YING C, CAI T, LUO S, et al. Do transformers really perform badly for graph representation?[C]// Advances in Neural Information Processing Systems, Cambridge, MA: MITPress, 2021:28877-28888.
[21]	周天睿, 康重庆, 徐乾耀, 等. 电力系统碳排放流的计算方法初探[J]. 电力系统自动化, 2012, 36(11): 44-49.
	ZHOU Tianrui, KANG Chongqing, XU Qianyao, et al. Preliminary investigation on a method for carbon emission flow calculation of power system[J]. Automation of Electric Power Systems, 2012, 36(11): 44-49.
[22]	RAMCHOUN H, AMINE M, IDRISSI J, et al. Multilayer perceptron: architecture optimization and training[J]. International Journal of Interactive Multimedia and Artificial Intelligence, 2016, 4(1): 26.
[23]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017,30: 5998-6008.
[24]	HE K M, ZHANG X G, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016: 770-778.

名称	描述
ASTGCN	带注意力机制的时空图卷积神经网络
STGCN-Cheb	基于切比雪夫多项式逼近的时空图卷积网络
STGCN	时空图卷积神经网络