Abstract：This study proposes a new method to improve short-term load forecasting accuracy. The method is based on Variational Modal Decomposition (VMD) with consideration of VMD residuals and an Improved Northern Eagle Algorithm (INGO) optimized Bi-directional Long Short Term Memory (BiLSTM) network. The VMD is used to decompose historical load data into multiple eigenmode components (IMFs) and a residual quantity. The BiLSTM model is then constructed separately for each IMF and residual, as well as the associated meteorological parameters. To avoid the impact of poorly selected hyperparameters on prediction accuracy, the INGO algorithm optimizes the implied layer nodes, training times, and learning rates of the BiLSTM. Last but not least, the prediction results are superimposed to obtain the final results. By analyzing specific cases, this paper′s method has demonstrated a higher prediction precision when compared to alternative methods. This validation confirms the effectiveness of the method presented in this article.
[1] BOZORG M, BRACALE A, CARAMIA P, et al. Bayesian bootstrap quantile regression for probabilistic photovoltaic power forecasting[J]. Protection and Control of Modern Power Systems, 2020, 5(3):218-229. [2] SHA B, YNA C, MN A, et al. A comparative study of predictive approaches for load forecasting in smart buildings[J]. Procedia Computer Science, 2019, 160:173-180. [3] HE F F, ZHOU J Z, MO L, et al. Day-ahead short-term load probability density forecastingmethod with a decomposition based quantile regression forest[J]. Applied Energy, 2020, 262(9):234-246. [4] JUAN F, RENDON S.Structural combination of seasonal exponential smoothing forecasts applied to load forecasting[J]. European Journal of Operational Research, 2019, 275(3):916-924. [5] YU F, XU X. A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network[J]. Applied Energy, 2014, 134:102-113. [6] KIM Y, SON H, KIM S G. Short term electricity load forecasting for institutional buildings[J]. Energy Reports, 2019, 5:1270-1280. [7] XIA P P, XUE A H, LIAN T. Analysis and prediction regional electricity consumption based on BP neural network[J]. Journal of Quantum, 2020, 2(1):25-32. [8] WANG Y, GAN D, SUN M, et al. Probabilistic individual load forecasting using pinball loss guided LSTM[J]. Applied Energy, 2019, 235:10-20. [9] 刘亚珲,赵倩.基于聚类经验模态分解的CNN-LSTM超短期电力负荷预测[J].电网技术, 2021, 45(11):4444-4451. LIU Y H, ZHAO Q. Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM[J]. Power System Technology, 2021, 45(11):4444-4451. [10] 吕海灿,王伟峰,赵兵,等.基于Wide & Deep-LSTM模型的短期台区负荷预测[J].电网技术, 2020, 44(2):428-436. LÜ H C, WANG W F, ZHAO B, et al. Short-term stationload forecasting based on Wide & Deep-LSTM model[J]. Power System Technology, 2020, 44(2):428-436. [11] S.KOUHI, F.KEYNIA. A new cascade NN based method to short-trem load forecast in deregulated electricity market[J]. Energ Convers Mange, 2013, 71:76-83. [12] 刘建华,李锦程,杨龙月,等.基于EMD-SLSTM的家庭短期负荷预测[J].电力系统保护与控制, 2019, 47(6):40-47. LIU J H, LI J C, YANG L Y, et al. Short-term household load forecasting based on EMD-SLSTM[J]. Power System Protection and Control, 2019, 47(6):40-47. [13] 王子乐,王子谋,蔡莹,等.基于长短期记忆神经网络组合算法的短期电力负荷预测[J].现代电力, 2023, 40(2):201-209. WANG Z Y, WANG Z M, CAI Y, et al. Short-term load forecasting based on long short-term memory network combination algorithm[J]. Modern Electric Power, 2023, 40(2):201-209. [14] HE F F, ZHOU J Z,FENG Z K, et al. A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm[J]. Appl Energy, 2019,237:103-116. [15] 李秀昊,刘怀西,张智勇,等.基于VMD-LSTM的超短期风向多步预测[J].南方能源建设, 2023, 10(1):29-38. LI X H, LIU H X, ZHANG Z Y, et al. Very short-term wind direction multistep forecast based on VMD-LSTM[J]. Southern Energy Construction, 2023, 10(1):29-38. [16] 顾乾晖,曾斌,涂振宇.基于VMD-PSO-LSTM水质预测模型的应用研究[J].南昌工程学院学报, 2021,40(4):23-29. GU Q H, ZENG B, TU Z Y. Research on application of water quality prediction model based on VMD-PSO-LSTM[J]. Journal of Nanchang Institute of Technology, 2021,40(4):23-29. [17] ELDABAH M A, ELSEHIEMY R A, HASANIEN H M, et al. Photovoltaic model parameters identification using Northern Goshawk Optimization algorithm[J]. Energy, 2023, 262(5):125522-125540. [18] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactionson Signal Processing, 2014, 62(3):531-544. [19] DEHGHANI M, HUBALOVSKY S, TROJOVSKY P. Northerngoshawk optimization: a new swarm-based algorithm for solving optimi-zation problems[J]. IEEE Access, 2021, 9:162059-162080. [20] 班多晗,吕鑫,王鑫元.基于一维混沌映射的高效图像加密算法[J].计算机科学, 2020, 47(4):278-284. BAN D H, LÜ X, WANG X Y. Efficient lmage encryption algorithm based on 1d chaotic map[J]. Computer Science, 2020, 47(4):278-284. [21] MIRJALILI S. SCA:a sine cosine algorithm for solving optimization problems[J]. Knowledge-Based Systems, 2016, 96(5):120-133. [22] WANG JIESHENG. Improved whale optimization algorithm based on nonlinear adaptive weight and golden sine operator[J]. IEEE Access, 2020, 8:77013-77048. [23] CHEN B, WANG Y. Short-term electric load forecasting of integrated energy system considering nonlinear synergy between different loads[J]. IEEE Access, 2021, 9:43562-43573. [24] ZHANG H X, CHENG L L, DING T, et al. Hybrid method for short-term photovoltaic power forecasting based on deep convolutio-nal neural network[J]. IET Generation, Tran-smission & Distribution, 2018, 12(20), 4557-4567.
