首页|融合GSO算法与AFSA算法的人工智能电力系统预测模型设计

融合GSO算法与AFSA算法的人工智能电力系统预测模型设计

扫码查看
为了解决传统统计模型在电力系统负荷预测中存在的稳定性差、使用率低等情况,研究将人工智能引入到了电力系统的统计模型中.研究创新地将人工萤火虫算法和人工鱼群算法进行优化和融合,将其用于构建电力系统负荷预测模型.首先对人工萤火虫算法进行优化,然后将优化后的人工萤火虫算法与人工鱼群算法进行融合用于构建电力负荷预测模型,最后利用仿真实验来验证预测模型的性能.结果表明,通过预测模型的归一化处理,节点电压的波动范围明显更平稳,其波动范围分布在[0.961~1.00pu].同时预测模型在迭代至66次获得了最优解,也明显优于对比算法.这说明融合人工萤火虫算法和人工鱼群算法的人工智能电力系统负荷预测模型在准确性和稳定性方面表现出优越性.
Design of Artificial Intelligence Power System Prediction Model by Fusing GSO Algorithm and AFSA Algorithm
In order to solve the poor stability and low utilization of traditional statistical models in power sys-tem load forecasting,the study introduces artificial intelligence into the statistical model of power system.The study innovatively optimizes and integrates the artificial firefly algorithm and the artificial fish swarm algorithm,and uses them to construct the power system load forecasting model.Firstly,the artificial firefly algorithm is opti-mized,and then the optimized artificial firefly algorithm is fused with the artificial fish swarm algorithm for con-structing the power load prediction model,and finally the performance of the prediction model is verified by u-sing simulation experiments.The results show that the fluctuation range of the node voltage is obviously smoother through the normalization of the prediction model,and its fluctuation range is distributed in[0.961-1.00].Meanwhile the prediction model obtained the optimal solution in iterations up to 66 times,which is also signifi-cantly better than the comparison algorithm.This indicates that the artificial intelligence power system load pre-diction model incorporating the artificial firefly algorithm and the artificial fish swarm algorithm shows superiority in terms of accuracy and stability.

GSO algorithmAFSA algorithmartificial intelligencepower systemload forecasting

郑志娴、郑晶

展开 >

福建船政交通职业学院信息与智慧交通学院,福建福州 350007

福建江夏学院电子信息科学学院,福建福州 350108

GSO算法 AFSA算法 人工智能 电力系统 负荷预测

福建省中青年教师教育科研项目

JAT210719

2024

黑龙江工业学院学报(综合版)
鸡西大学

黑龙江工业学院学报(综合版)

影响因子:0.211
ISSN:1672-6758
年,卷(期):2024.24(3)
  • 14