A Surrogate-Enhanced Scheme in Decision Making under Uncertainty in Power Systems
A Surrogate-Enhanced Scheme in Decision Making under Uncertainty in Power Systems
复制标题
DOI：
10.1109/pesgm46819.2021.9637922
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Yijun Xu;L. Mili;M. Korkali;Xiao Chen;J. Valinejad;Long Peng
中科院分区：
文献类型：
--
作者：
Yijun Xu;L. Mili;M. Korkali;Xiao Chen;J. Valinejad;Long Peng
随着可再生能源发电的普及，电力系统负荷的随机变化使得不确定性条件下的在线决策成为电力系统研究的热点。为了解决这个问题，同时实现系统安全和经济目标之间的良好平衡，我们提出了一个代理增强计划下的联合机会约束（JCC）最优潮流（OPF）框架。从随机抽样过程出发，我们首先利用Copula理论来模拟多变量不确定输入之间的依赖关系。然后，为了减少传统的蒙特-卡罗（MC）方法所需的计算时间，我们建议使用一个多项式混沌为基础的代理，使我们能够有效地评估电力系统模型在非高斯分布的采样值与一个可以忽略不计的计算成本。通过对MC模拟样本的学习，我们进一步提出了一种混合自适应方法，利用系统状态的相关性克服了传统Boole不等式中忽略的JCC-OPF的保守性。在修改后的Illinois测试系统上进行的仿真表明了该方法的优良性能。
Facing stochastic variations of the loads due to an increasing penetration of renewable energy generation, online decision making under uncertainty in modern power systems is capturing power researchers' attention in recent years. To address this issue while achieving a good balance between system security and economic objectives, we propose a surrogate-enhanced scheme under a joint chance-constrained (JCC) optimal power-flow (OPF) framework. Starting from a stochastic-sampling procedure, we first utilize the copula theory to simulate the dependence among multivariate uncertain inputs. Then, to reduce the prohibitive computational time required in the traditional Monte-Carlo (MC) method, we propose to use a polynomial-chaos-based surrogate that allows us to efficiently evaluate the power-system model at non-Gaussian distributed sampled values with a negligible computing cost. Learning from the MC simulated samples, we further proposed a hybrid adaptive approach to overcome the conservativeness of the JCC-OPF by utilizing correlation of the system states, which is ignored in the traditional Boole's inequality. The simulations conducted on the modified Illinois test system demonstrate the excellent performance of the proposed method.