Abstract
New energy integration and flexible demand response make smart grid operation scenarios complex and changeable, which bring challenges to network planning. If every possible scenario is considered, the solution to the planning can become extremely time-consuming and difficult. This paper introduces statistical machine learning (SML) techniques to carry out multi-scenario based probabilistic power flow calculations and describes their application to the stochastic planning of distribution networks. The proposed SML includes linear regression, probability distribution, Markov chain, isoprobabilistic transformation, maximum likelihood estimator, stochastic response surface and center point method. Based on the above SML model, capricious weather, photovoltaic power generation, thermal load, power flow and uncertainty programming are simulated. Taking a 33-bus distribution system as an example, this paper compares the stochastic planning model based on SML with the traditional models published in the literature. The results verify that the proposed model greatly improves planning performance while meeting accuracy requirements. The case study also considers a realistic power distribution system operating under stressed conditions.
Highlights
The optimal placement of distributed energy resources (DERs) and capacitor banks is an important issue in power systems
The stochastic process model for PV generation can improve the probabilistic power flow (PPF) calculation results of distribution networks with inertia HVAC loads, while the stochastic process of weather conditions should be considered at the same time
Has an advantage over the point estimate method (PEM) in estimating the CDFs of power flow responses, since the CDF information of the PEM is from moments while for the proposed method, it is from power flow responses. (c) Both the PEM and proposed methods cannot exactly match the real results, while the extraction of key information based on statistical machine learning (SML) results in information loss
Summary
The optimal placement of distributed energy resources (DERs) and capacitor banks is an important issue in power systems. Nondeterministic characteristics of loads and DERs are important challenges for the economic and safe operation of power grids, and will greatly affect distribution network planning \* MERGEFORMAT [1]. To characterize the nondeterministic characteristics of power flows, the interval power flow is an effective method. Uncertainty brings challenges to power grid optimization. The interval model of power grid uncertainty faces the nonconvex nonlinear programming problem, known to be NP-hard. Energy storage allocation has become a popular method to solve uncertainty optimization problems of
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
