Abstract
This paper proposes a support vector regression (SVR)-based model predictive control (MPC) for the volt-var optimization (VVO) of electrical distribution systems. First, measurement data from a few days of operation of a distribution system, gathered using advanced metering infrastructure (AMI), are used to train an SVR model of the system. The trained model is then employed by the MPC in a closed-loop control scheme to control capacitor banks and tap changers of the distribution system so that the power loss is minimized, and voltage profiles are maintained within a specific range. In contrast to the many existing VVO methods, the proposed scheme does not require any circuit-based simulations for its operation, nor does it assume that the distribution system is radial. The simulation results of applying the proposed SVR-based MPC to IEEE123 bus test feeder proves that despite its measurement-based feature, the proposed approach is capable of providing close to optimal solutions to the VVO problem. The simulation results also suggest a satisfactory outcome of the proposed approach in controlling meshed grids or in the presence of distributed energy resources (DERs).
Highlights
The main objectives of the Volt-Var Optimization (VVO) are to minimize power loss in the distribution system and keep voltage profiles at acceptable levels under different load conditions
The first step in the proposed control scheme is to build an support vector regression (SVR) model of the system. This is performed by the SVR builder unit in which the measurement data from advanced metering infrastructure (AMI), tap positions of On-Load Tap Changing (OLTC) and reactive power injections of capacitor banks are fed to the unit as the inputs
SIMULATION RESULTS The effectiveness of the proposed SVR-based model predictive control (MPC) is evaluated by conducting several simulation studies
Summary
The main objectives of the Volt-Var Optimization (VVO) are to minimize power loss in the distribution system and keep voltage profiles at acceptable levels under different load conditions. Advanced Metering Infrastructure (AMI) is a set of technologies including smart meters and communication networks that collect time-based data such as power consumption and voltage amplitude across distribution grid [13] The availability of such data allows for another type of power system analytics called data-driven approaches in which measurement data is fed to statistical or machine learning algorithms to build a data-driven model of the distribution system. An example of a data-driven method for Volt-Var optimization is [11] where K-nearest neighbor alongside principal component analysis are utilized to build a model of radial distribution feeders and generate proper decisions for controlling their capacitors and OLTCs. This paper proposes a novel data-driven approach for solving the VVO problem of distribution networks.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
