ABSTRACT
In this study, a new power prediction system named Pattern Similarity Graph based Model (PSGM) based on time sequential prediction algorithm and graphical neural network (GNN) structure is proposed. The proposed GNN architecture extracts the deep information of each power node and is used to predict the short-term power by using the sequential convolutional network (TCN) based on serial model. In the study, the electric junction is the high-tech campus. The number of enterprises in the electric campus, the total area of the campus, the time of operation of the campus and the daily average temperature data were selected as the inherent attributes of the electric campus. After constructing the graph model by taking the similarity of the power sequence of the campus as the correlation between the campuses, the feature vector of depth information of each node is combined with the feature vector of its sequence for the final prediction of short-term power consumption. The experiment compares the results of adding temperature conditions and obtains the influence degree of temperature on electricity consumption. The results are compared with baseline regression algorithm, LSTM, and ARIMA. The experimental results show that this method is superior to the traditional regression algorithm, and reveals the effective results with its competitive performance.
- Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst,Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, MateuszMalinowski, Andrea Tacchetti, David Raposo, AdamSantoro, and Ryan Faulkner. Relational inductive bi-ases, deep learning, and graph networks. 2018.Google Scholar
- Deniz Korkmaz, Hakan Acikgoz, Ceyhun Yildiz, A Novel Short-Term Photovoltaic Power Forecasting Approach based on Deep Convolutional Neural Network,INTERNATIONAL JOURNAL OF GREEN ENERGY,2020 .Google Scholar
- Zhao Qian and Zheng Guilin, “Short-term load forecasting based on WD-LSSVM-LSTM model, Electrical Measurement & Instrumentation, 2021.Google Scholar
- WEI Mingkui, YE Wei, SHEN Jing, Short-Term Load Forecasting Method Based on Self-Organizing Feature Mapping Neural Network and GA-Least Square SVC Model, Modern Electric Power, 2021.Google Scholar
- Jie Zhou, Ganqu Cui, Zhengyan Zhang, Graph Neural Networks: A Review of Methods and Applications, 2018.Google Scholar
- Detection and root cause analysis of multiple plant-wide oscillations using multivariate nonlinear chirp mode decomposition and multivariate Granger causalityQ Chen, X Lang, S Lu, N ur Rehman, L Xie, H SuComputers & Chemical Engineering 147, 107231 2021Google Scholar
- Shaojie Bai 1 J. Zico Kolter 2 Vladlen Koltun 3, An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling, 2018.Google Scholar
- Hochreiter, Schmidhuber, Long short-term memory, MIT-Press, 1997.Google Scholar
- Detection and diagnosis of oscillations in process control by fast adaptive chirp mode decompositionQ Chen, J Chen, X Lang, L Xie, S Lu, H SuControl Engineering Practice 97, 104307 9 2020Google Scholar
- Multivariate intrinsic chirp mode decompositionQ Chen, X Lang, L Xie, H SuSignal Processing 183, 108009 2021Google Scholar
- CHEN Mingfan, NING Guangtao, LI Linwei, Monthly electricity forecasting based on K-L information and ARIMA error correction, Academic Journal Electronic Publishing House, 2021.Google Scholar
- SHI Xuemei, GE Fei, XIAO Xilin. Prediction of industrial power consumption in Anhui Province based on K-L information method.. Power System and Clean Energy,2015.Google Scholar
- Detecting nonlinear oscillations in process control loop based on an improved VMDQ Chen, X Lang, L Xie, H SuIEEE Access 7, 91446-91462 14 2019Google Scholar
- Zhou Yongsheng. PM2.5 prediction based on LSTM neural network .Changsha: Hunan University, 2018Google Scholar
- Zhang Ben, Shao Changning, Zhao Huo. Short term load forecastingmethod based on error correction [J]. Electric power autoation equipment, 2015, 35 (11): 152-157.Google Scholar
- Huang Chaobin, Cheng Ximing, Research on stock price prediction based on LSTM neural network, Journal of Beijing Information Science, 2021.Google Scholar
- Han Luying, Xu Yong. Short term load forecasting based on support vector machine. Computer programming skills and maintenance, 2019 (6):16-18.Google Scholar
- He Ye, Zou Xiaosong, Li Zhuo, Huang Youjin, Xiong Wei, Yuan X ufeng. A short-term load forecasting method oriented for operation reliability. Electrical Measurement & Instrumentation, 2019, 56 (10): 93-98.Google Scholar
- Raza, M. Q., M. Nadarajah, and C. Ekanayake. 2016. On recent advances in PV output power forecast. Solar Energy Elsevier Ltd. doi:10.1016/j. solener.2016.06.073Google Scholar
- Yildiz, C., and H. Acikgoz. 2020. A kernel Extreme learning machine-based neural network to forecast very short-term power output of an on-grid photovoltaic power plant. Energy Sources, Part A: Recovery, Utilization and Environmental Effects 43 (4):395–412. Taylor & Francis. doi:10.1080/15567036.2020.1801899.Google Scholar
- Sun, Y., V. Venugopal, and A. R. Brandt. 2019. Short-term solar power forecast with deep learning: Exploring optimal input and output configuration. Solar Energy 188 (May):730–41. Elsevier. doi:10.1016/j. solener.2019.06.041.Google Scholar
- Detecting nonlinear oscillations in process control loop based on an improved VMDQ Chen, X Lang, L Xie, H SuIEEE Access 7, 91446-91462 14 2019Google Scholar
- Liao Jinping, Mo Yuchang, Yan Ke, Model and application of short-term electricity consumption forecast base on C-LSTM, Journal of ShanDong University, 2021.Google Scholar
- Jure, Aditya, node2vec: Scalable Feature Learning for Networks, KDD, 2016.Google Scholar
Recommendations
Based on Time Sequence of ARIMA Model in the Application of Short-Term Electricity Load Forecasting
ICRCCS '09: Proceedings of the 2009 International Conference on Research Challenges in Computer ScienceShort-term electricity load is effected by various factors, It has the certain difficulty to make prediction accurate, but we can improve prediction precise by continuously optimizing forecasting methods. This paper carried out the combination of ARIMA ...
ANNSTLF-a neural-network-based electric load forecasting system
A key component of the daily operation and planning activities of an electric utility is short-term load forecasting, i.e., the prediction of hourly loads (demand) for the next hour to several days out. The accuracy of such forecasts has significant ...
Study of neural networks for electric power load forecasting
ISNN'06: Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part IIElectric Power Load Forecasting is important for the economic and secure operation of power system, and highly accurate forecasting result leads to substantial savings in operating cost and increased reliability of power supply. Conventional load ...
Comments