Noise-Aware Bayesian Optimization Approach for Capacity Planning of the Distributed Energy Resources in an Active Distribution Network

TL;DR

The paper addresses capacity planning in active distribution networks (ADNs) in the presence of RES variability. It introduces a noise-aware Bayesian optimization (NBO) framework with a Gaussian-process surrogate and Noisy Expected Improvement to explicitly model and cope with simulation noise, optimizing the total annual cost $C_T = C_{op} + C_{inv}$. The approach jointly considers DER coordination (wind, PV, ESS) and network constraints (bidirectional flows, voltage, and dispatchable demand response), and is validated on 33- and 118-node networks, showing faster convergence and lower costs than baseline BO and PSO. The findings highlight the benefits of collaborative, distributed planning for enhanced RES accommodation and operational efficiency in ADNs.

Abstract

The growing penetration of renewable energy sources (RESs) in active distribution networks (ADNs) leads to complex and uncertain operation scenarios, resulting in significant deviations and risks for the ADN operation. In this study, a collaborative capacity planning of the distributed energy resources in an ADN is proposed to enhance the RES accommodation capability. The variability of RESs, characteristics of adjustable demand response resources, ADN bi-directional power flow, and security operation limitations are considered in the proposed model. To address the noise term caused by the inevitable deviation between the operation simulation and real-world environments, an improved noise-aware Bayesian optimization algorithm with the probabilistic surrogate model is proposed to overcome the interference from the environmental noise and sample-efficiently optimize the capacity planning model under noisy circumstances. Numerical simulation results verify the superiority of the proposed approach in coping with environmental noise and achieving lower annual cost and higher computation efficiency.

Figures (9)

• Figure 1: The structure of a typical type of ADN.
• Figure 2: The framework of the proposed NBO based DERs collaborative capacity planning approach
• Figure 3: The influence rendered by the simulation deviation caused by the RES variability on the annual cost.
• Figure 4: The optimal capacity allocation scheme of Model 1-4 derived by the NBO.
• Figure 5: The convergence curves of the three algorithms in different capacity planning models.