基于迁移模糊系统的短期电力负荷预测建模
Short-Term Power Load Forecasting Modeling Based on Transfer Fuzzy System
摘要: 针对电力负荷数据缺失导致预测精度降低的问题，本文提出基于TSK迁移模糊系统(TSK-TFS)结合变分模态分解(VMD)、迁移成分分析(TCA)和改进斑马优化算法(IZOA)的短期电力负荷预测模型(IZOA-VMD-TSK-TFS-TCA)。首先利用VMD将电力负荷数据分解为若干子序列，并利用TCA将与电力负荷相关的因素降维；其次对斑马优化算法进行改进，利用改进后的斑马优化算法(IZOA)对TSK-TFS的参数寻优，并利用减法聚类算法得到聚类个数，把源域中的数据输入TSK模糊系统训练得到前件参数和后件参数并保留，继承参数并利用一部分目标域数据训练得到后件参数；最后根据得到的后件参数并经过计算得到测试集(另一部分目标域数据)若干子序列的预测值，将各个子序列的预测值叠加得到短期电力负荷的预测值。仿真实验结果表明，本文提出的IZOA-VMD-TSK-TFS-TCA短期电力负荷预测模型具有较高的预测精度，经过统计检验也证实了该模型具有较优的预测性能。
Abstract: To address the issue of reduced prediction accuracy caused by missing power load data, this paper proposes a short-term power load prediction model (IZOA-VMD-TSK-TFS-TCA) based on TSK Transfer Fuzzy System (TSK-TFS) combined with Variational Mode Decomposition (VMD), Transfer Component Analysis (TCA) and Improved Zebra Optimization Algorithm (IZOA). Firstly, VMD is used to decompose the power load data into several subsequences and TCA is used to reduce the dimensionality of factors related to power load. Secondly, IZOA is used to optimize the parameters of TSK-TFS and Subtractive Clustering Algorithm is used to obtain the number of clusters. The data in the source domain is input into the TSK fuzzy system to obtain the predecessor parameters and successor parameters and retain them. The parameters are inherited and the successor parameters are obtained using some of the target domain data. Finally, the predicted values of several subsequences of the test set (another portion of the target domain data) are obtained according to the obtained parameters of the subsequent components and calculated, and the predicted values of each subsequence are superimposed to obtain the predicted values of short-term power load. The experimental results show that the IZOA-VMD-TSK-TFS-TCA short-term power load prediction model has higher prediction accuracy. Statistical tests also confirmed that the model had superior predictive performance.
文章引用：李秋琰. 基于迁移模糊系统的短期电力负荷预测建模[J]. 应用数学进展, 2024, 13(4): 1671-1689. https://doi.org/10.12677/aam.2024.134159

参考文献

[1] Yin, C. and Mao, S. (2023) Fractional Multivariate Grey Bernoulli Model Combined with Improved Grey Wolf Algorithm: Application in Short-Term Power Load Forecasting. Energy, 269, Article ID: 126844. [Google Scholar] [CrossRef] 
[2] Kong, X., Wang, Z., Xiao, F., et al. (2023) Power Load Forecasting Method Based on Demand Response Deviation Correction. International Journal of Electrical Power & Energy Systems, 148, Article ID: 109013. [Google Scholar] [CrossRef] 
[3] 万成德. 基于深度学习和迁移学习的短期电力负荷预测[D]: [硕士学位论文]. 大庆: 东北石油大学, 2022.
[4] 黄睿, 朱玲俐, 高峰, 等. 基于变分模态分解的卷积长短时记忆网络短期电力负荷预测方法[J]. 现代电力, 2024, 41(1): 97-105.
[5] 王宝财. 基于温度近因效应的多元线性回归电力负荷预测[J]. 水电能源科学, 2018, 36(10): 201-205.
[6] 陈培垠, 方彦军. 基于卡尔曼滤波预测节假日逐点增长率的电力系统短期负荷预测[J]. 武汉大学学报(工学版), 2020, 53(2): 139-144.
[7] 李毅, 彭晋卿, 廖维, 等. 一种基于时间序列的集成电力负荷预测方法研究[J]. 建筑科学, 2022, 38(10): 190-197.
[8] 刘静. 最小二乘SVM在电力推进船舶电力负荷短期预测的应用[J]. 舰船科学技术, 2021, 43(24): 61-63.
[9] 曾林俊, 许加柱, 王家禹, 等. 考虑区间构造的改进极限学习机短期电力负荷区间预测[J]. 电网技术, 2022, 46(7): 2555-2563.
[10] 李艳波, 尹镨, 陈俊硕, 等. 结合改进残差网络和Bi-LSTM的短期电力负荷预测[J]. 哈尔滨工业大学学报, 2023, 55(8): 79-86.
[11] 徐岩, 向益锋, 马天祥. 基于粒子群算法优化参数的VMD-GRU短期电力负荷预测模型[J]. 华北电力大学学报(自然科学版), 2023, 50(1): 38-47.
[12] Zadeh, L.A. (1965) Fuzzy Sets. Information and Control, 8, 338-353. [Google Scholar] [CrossRef] 
[13] Zadeh, L.A. (1975) The Concept of a Linguistic Variable and Its Application to Approximate Reasoning-I. Information Sciences, 8, 199-249. [Google Scholar] [CrossRef] 
[14] 张雄涛, 李水苗, 翁江玮, 等. 基于视角-规则的深度TSK模糊分类器及其在多元癫痫脑电信号识别中的应用[J]. 控制与决策, 2024, 39(4): 1315-1324.
[15] Mukhopadhyay, P., Mitra, G., Banerjee, S., et al. (2017) Electricity Load Forecasting Using Fuzzy Logic: Short Term Load Forecasting Factoring Weather Parameter. 2017 7th International Conference on Power Systems (ICPS) IEEE, Pune, 21-23 December 2017, 812-819. [Google Scholar] [CrossRef] 
[16] Trojovská, E., Dehghani, M. and Trojovský, P. (2022) Zebra Optimization Algorithm: A New Bio-Inspired Optimization Algorithm for Solving Optimization Algorithm. IEEE Access, 10, 49445-49473. [Google Scholar] [CrossRef] 
[17] 赵一鸣, 吉月辉, 刘俊杰, 等. 基于EMD-IPSO-LSTM模型的短期电力负荷预测[J]. 国外电子测量技术, 2023, 42(1): 132-137.
[18] 曹广华, 陈前, 齐少栓, 等. 基于EEMD-SSA组合模型的短期电力负荷预测[J]. 吉林大学学报(信息科学版), 2022, 40(3): 362-370.
[19] 张未, 余成波, 王士彬, 等. 基于VMD-LSTM-LightGBM的多特征短期电力负荷预测[J]. 南方电网技术, 2023, 17(2): 74-81.
[20] 欧阳福莲, 王俊, 周杭霞. 基于改进迁移学习和多尺度CNN-BiLSTM-Attention的短期电力负荷预测方法[J]. 电力系统保护与控制, 2023, 51(2): 132-140.
[21] 孙晓燕, 李家钊, 曾博, 等. 基于特征迁移学习的综合能源系统小样本日前电力负荷预测[J]. 控制理论与应用, 2021, 38(1): 63-72.
[22] 姜建国, 万成德, 陈鹏, 等. 基于1DCNN-LSTM和迁移学习的短期电力负荷预测[J]. 吉林大学学报(信息科学版), 2023, 41(1): 124-130.
[23] 蒋亦樟, 邓赵红, 王士同. 0阶L2型TSK迁移学习模糊系统[J]. 电子学报, 2013, 41(5): 897-904.
[24] Juang, C.F. and Lo, C. (2008) Zero-Order TSK-Type Fuzzy System Learning Using a Two-Phase Swarm Intelligence Algorithm. Fuzzy Sets and Systems, 159, 2910-2926. [Google Scholar] [CrossRef] 
[25] Konstantin, D. and Dominique, Z. (2014) Variational Mode Decomposition. IEEE Transactions on Signal Processing, 62, 531-544. [Google Scholar] [CrossRef] 
[26] Pan, S.J., Tsang, I.W., Kwok, J.T., et al. (2010) Domain Adaptation via Transfer Component Analysis. IEEE Transactions on Neural Networks, 22, 199-210. [Google Scholar] [CrossRef] 

为你推荐