Load Forecasting Based Distribution System Network Reconfiguration -- A Distributed Data-Driven Approach

Huaiguang Jiang; Yingchen Zhang; Eduard Muljadi; Yi Gu; Jun Zhang; Francisco Solis

doi:10.1109/ACSSC.2017.8335576

Load Forecasting Based Distribution System Network Reconfiguration -- A Distributed Data-Driven Approach

Huaiguang Jiang, Yingchen Zhang, Eduard Muljadi, Yi Gu, Jun Zhang, Francisco Solis

Research output: Contribution to conference › Paper

7 Scopus Citations

Abstract

In this paper, a short-term load forecasting approach based network reconfiguration is proposed in a parallel manner. Specifically, a support vector regression (SVR) based short-term load forecasting approach is designed to provide an accurate load prediction and benefit the network reconfiguration. Because of the nonconvexity of the three-phase balanced optimal power flow, a second-order cone program (SOCP) based approach is used to relax the optimal power flow problem. Then, the alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed manner. Considering the limited number of the switches and the increasing computation capability, the proposed network reconfiguration is solved in a parallel way. The numerical results demonstrate the feasible and effectiveness of the proposed approach.

Original language	American English
Pages	1358-1362
Number of pages	5
DOIs	https://doi.org/10.1109/ACSSC.2017.8335576
State	Published - 2018
Event	2017 51st Asilomar Conference on Signals, Systems, and Computers - Pacific Grove, California Duration: 29 Oct 2017 → 1 Nov 2017

Conference

Conference	2017 51st Asilomar Conference on Signals, Systems, and Computers
City	Pacific Grove, California
Period	29/10/17 → 1/11/17

NREL Publication Number

NREL/CP-5D00-71665

Keywords

alternating direction method of multipliers
convex optimization
electrical distribution system
network reconfiguration
optimal power flow
semidefinite relaxation programming
short-term load forecasting
support vector regression

Access to Document

10.1109/ACSSC.2017.8335576

Cite this

@conference{712f4760c4d947238938724c3b37766c,

title = "Load Forecasting Based Distribution System Network Reconfiguration -- A Distributed Data-Driven Approach",

abstract = "In this paper, a short-term load forecasting approach based network reconfiguration is proposed in a parallel manner. Specifically, a support vector regression (SVR) based short-term load forecasting approach is designed to provide an accurate load prediction and benefit the network reconfiguration. Because of the nonconvexity of the three-phase balanced optimal power flow, a second-order cone program (SOCP) based approach is used to relax the optimal power flow problem. Then, the alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed manner. Considering the limited number of the switches and the increasing computation capability, the proposed network reconfiguration is solved in a parallel way. The numerical results demonstrate the feasible and effectiveness of the proposed approach.",

keywords = "alternating direction method of multipliers, convex optimization, electrical distribution system, network reconfiguration, optimal power flow, semidefinite relaxation programming, short-term load forecasting, support vector regression",

author = "Huaiguang Jiang and Yingchen Zhang and Eduard Muljadi and Yi Gu and Jun Zhang and Francisco Solis",

year = "2018",

doi = "10.1109/ACSSC.2017.8335576",

language = "American English",

pages = "1358--1362",

note = "2017 51st Asilomar Conference on Signals, Systems, and Computers ; Conference date: 29-10-2017 Through 01-11-2017",

}

TY - CONF

T1 - Load Forecasting Based Distribution System Network Reconfiguration -- A Distributed Data-Driven Approach

AU - Jiang, Huaiguang

AU - Zhang, Yingchen

AU - Muljadi, Eduard

AU - Gu, Yi

AU - Zhang, Jun

AU - Solis, Francisco

PY - 2018

Y1 - 2018

N2 - In this paper, a short-term load forecasting approach based network reconfiguration is proposed in a parallel manner. Specifically, a support vector regression (SVR) based short-term load forecasting approach is designed to provide an accurate load prediction and benefit the network reconfiguration. Because of the nonconvexity of the three-phase balanced optimal power flow, a second-order cone program (SOCP) based approach is used to relax the optimal power flow problem. Then, the alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed manner. Considering the limited number of the switches and the increasing computation capability, the proposed network reconfiguration is solved in a parallel way. The numerical results demonstrate the feasible and effectiveness of the proposed approach.

AB - In this paper, a short-term load forecasting approach based network reconfiguration is proposed in a parallel manner. Specifically, a support vector regression (SVR) based short-term load forecasting approach is designed to provide an accurate load prediction and benefit the network reconfiguration. Because of the nonconvexity of the three-phase balanced optimal power flow, a second-order cone program (SOCP) based approach is used to relax the optimal power flow problem. Then, the alternating direction method of multipliers (ADMM) is used to compute the optimal power flow in distributed manner. Considering the limited number of the switches and the increasing computation capability, the proposed network reconfiguration is solved in a parallel way. The numerical results demonstrate the feasible and effectiveness of the proposed approach.

KW - alternating direction method of multipliers

KW - convex optimization

KW - electrical distribution system

KW - network reconfiguration

KW - optimal power flow

KW - semidefinite relaxation programming

KW - short-term load forecasting

KW - support vector regression

U2 - 10.1109/ACSSC.2017.8335576

DO - 10.1109/ACSSC.2017.8335576

M3 - Paper

SP - 1358

EP - 1362

T2 - 2017 51st Asilomar Conference on Signals, Systems, and Computers

Y2 - 29 October 2017 through 1 November 2017

ER -

Load Forecasting Based Distribution System Network Reconfiguration -- A Distributed Data-Driven Approach

Abstract

Conference

NREL Publication Number

Keywords

Access to Document

Fingerprint

Cite this