Academic Journal of Engineering and Technology Science, 2024, 7(4); doi: 10.25236/AJETS.2024.070416.
Yiting Chang1, Suli Zhang2, Guanghao You1
1School of Energy and Power Engineering, Changchun Institute of Technology, Changchun, China
2School of Computer Technology and Engineering, Changchun Institute of Technology, Changchun, China
In response to the challenge of low energy prediction accuracy caused by complicated parameter settings and the stochastic nature of LSTM networks used in electric heating energy consumption prediction, this study introduces an enhanced LSTM attention model. This model combines the Sparrow Search Algorithm (SSA) with Long Short-Term Memory (LSTM) neural networks and incorporates an attention mechanism to optimize predictions of electric heating energy consumption. The experimental findings indicate that the SSA-LSTM-Attention model achieves notable advancements in both prediction efficiency and accuracy when contrasted with traditional baseline models like SVR, RF, BP, LSTM, and LSTM-Attention, especially when dealing with complex scenarios involving highly dynamic changes in electric heating data.
Electric Heating; Energy Consumption Prediction; Long Short-term Memory Neural Network; Sparrow Search Algorithm
Yiting Chang, Suli Zhang, Guanghao You. Research on Electric Heating Energy Consumption Prediction Based on SSA-LSTM-Attention. Academic Journal of Engineering and Technology Science (2024) Vol. 7, Issue 4: 105-113. https://doi.org/10.25236/AJETS.2024.070416.
[1] Mei Shengwei, Guo Yongqing, Si Yang, et al. Solar thermal air flow power generation technology and its application prospects [J]. High Voltage Technology, 2019, 45(11):3401-3412.
[2] Guidance on Promoting Electric Energy Substitution [C]// Nuclear Industry Survey and Design (No.2, 2016, Total No.93). National Development and Reform Commission; National Energy Administration; Ministry of Finance; Ministry of Environmental Protection; Ministry of Housing and Urban-Rural Development; Ministry of Industry and Information Technology; Ministry of Transport; Civil Aviation Administration of China; , 2016:4.
[3] Li Xianglong, Zhang Baoqun, Ma Longfei, et al. Bayesian Electric Heating Load Prediction Based on Hidden data Information Mining [J]. Electrical Measurement & Instrumentation, 2018,55(24):88-93.
[4] Huang Yafeng, Zhu Yujie, Mu Gang, et al. Evaluation of adjustable capacity of household heating load based on temperature forecast [J]. Power Grid Technology, 2018, 42(08):2487-2493.
[5] Wei Xiaochuan, Wang Xingang. Big based on meteorological data of urban power load prediction [J]. Electric measurement and instrument, 2021, 58 (02): 90-95.
[6] Guo Zhanwu, Zhang Zeya, Zhou Xinghua, et al. Meteorological factors of electric heating load prediction research [J]. Electric measurement and instrumentation, 2022, 59 (02): 154-158.
[7] Chen Qifang, Xia Mingchao, Guo Min, et al. Based on data mining electric heating area of short-term load forecasting method [J]. Power supply, 2019, 4 (12): 48-54.
[8] Shi Jiaqi, Zhang Jianhua. Load Forecasting Method Based on Multi-model Fusion Stacking Ensemble Learning Method [J]. Proceedings of the CSEE, 2019, 39(14):4032-4042.
[9] Li Xianglong, Ma Longfei, Zhao Xiangyang, et al. Time scales based on LSTM networks [J]. Electric heating load forecasting of power system and its automation, 2021 (4): 71-75.