摘要
提出基于集合经验模态分解与能量熵的水库群蓄水时期梯级水电调度模型,以满足梯级水库群的蓄水、发电目标.对蓄水时期水库群的径流监测信号时间序列作集合经验模态分解,获得含有各尺度局部细节特征的IMF及剩余分量,基于能量熵理论完成各分量的重构,将重构结果作为最小二乘支持向量机的输入,利用粒子群算法优化预测模型参数,实现梯级水库群径流精准预测.依据径流预测结果,构建以发电量最高、蓄满率最大、弃水量最低作为优化目标,并满足蓄水量、泄水量、出力、水量平衡、关联方程约束的水电调度模型,实现水库群蓄水时期梯级水电调度优化.实验结果表明:该模型可实现径流监测信号时间序列的分解与重构,径流预测误差在[0.09,5.2]区间;优化调度后,梯级水库群的发电量提升了3.66%,弃水量降低了27.91%,蓄满率增大了1.85%.
A cascade hydropower operation model based on empirical mode decomposition and energy entropy is proposed to meet the water storage and power generation objectives of cascade reservoirs.The time series of runoff monitoring signals of reservoirs during the impoundment period are decomposed by collective empirical mode to obtain IMF components and residual components containing local details of each scale.The reconstruction of each component is completed based on the energy entropy theory.The reconstruction results are used as the input of the least squares support vector machine.Particle swarm optimization algorithm is used to optimize the prediction model parameters to achieve accurate prediction of runoff of cascade reservoirs.Based on the runoff prediction results,we build a hydropower operation model that takes the highest power generation,the largest storage rate,and the lowest waste water as the optimization objectives,and meets the constraints of storage,discharge,output,water balance,and correlation equation,so as to realize the optimization of cascade hydropower operation during the storage period of reservoirs.The experimental results show that the model can realize the decomposition and reconstruction of runoff monitoring signal time series,and the runoff prediction error is within[0.09,5.2];After optimized operation,the power generation of the cascade reservoirs has increased by 3.66%,the abandoned water has decreased by 27.91%,and the full storage rate has increased by 1.85%.
作者
郭希海
徐峥
安丰强
刘红叶
张淼
GUO Xihai;XU Zheng;AN Fengqiang;LIU Hongye;ZHANG Miao(Northeast Branch of State Grid Corporation of China,Shenyang 110180,China;Shenyang Institute of Computing Technology Co.Ltd.,CAS,Shenyang 110168,China;Beijing Kedong Electric Power Control System Co.Ltd,Nari Group Corporation,Beijing 100192,China)
出处
《河南科学》
2023年第6期801-808,共8页
Henan Science
基金
新能源网源协调能力在线监测与评价研究(52992620003P)。
关键词
集合经验模态分解
能量熵
水库群
水电调度模型
蓄满率
弃水量
ensemble empirical mode decomposition
energy entropy
reservoir group
hydropower dispatching model
full storage rate
surplus water
