Active distribution networks utilize advanced sensors

communication

and control technologies to achieve flexible and intelligent power distribution management. Reliable state estimation (SE) is crucial for distribution management systems to monitor these networks. Historically

the scarcity of measurement resources has hindered the application of SE technology in distribution networks. Establishing a dependable pseudo-measurement model for active distribution networks can significantly enhance the feasibility of SE. This paper proposes a pseudo-measurement model that aligns with the actual operating status of the distribution network

considering the uncertainty in output from distributed generations (DGs) such as wind turbines and photovoltaics. Firstly

it analyzes and models the uncertainty of high-penetration DG output

establishing a reliable output model that incorporates the physical characteristics of wind and photovoltaic output. Secondly

it proposes a pseudo-measurement modeling method based on support vector machine (SVM)

where the kernel function of the SVM is weighted according to the information entropy of fluctuations in historical operating data. This weighting ensures that the established pseudo-measurement model better reflects the actual operating status of the active distribution network. Finally

a mathematical model for optimizing pseudo-measurement selection is developed

with the minimum state estimation error as the objective function and the observability of the active distribution network system as the constraint. Case studies demonstrate the accuracy and effectiveness of this approach.