Electricity Market Price-spike Classification in the Smart Grid

被引：0

作者：

Datta, Aditi R. ^{[1
]}

Datta, Sohom ^{[2
]}

机构：

[1] Arizona State Univ, WP Carey Sch Business, Tempe, AZ 85281 USA

[2] Arizona State Univ, Sch Elect Comp & Energy Engn, Tempe, AZ USA

来源：

2016 IEEE POWER & ENERGY SOCIETY INNOVATIVE SMART GRID TECHNOLOGIES CONFERENCE (ISGT) | 2016年

关键词：

Data mining; electricity market price forecasting; meter data; naive-bayes classifier; random forest classifier; price spike; price forecasting; smart grid;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Accurate electricity market price forecasting is essential for the market participants in the present competitive deregulated electric power industry. In this research, the smart meter data is concomitantly used with the market data to improve price spike forecast. Modern data mining tools like Naive- Bayesian classifier, Random Forest and Artificial Neural Network algorithms have been used for price-spike forecasting. The Australian Energy Market Operator (AEMO) data of Victorian region has been used to train and test the price-spike forecasting methodology. The results show that the usage of smart meter data can have a significant impact on the accuracy of the price-spike forecasts.

引用

页数：5

共 50 条

[41] Demand-side response model to avoid spike of electricity price [J].

Marwan, Marwan ;

Ledwich, Gerard ;

Ghosh, Arindam .

JOURNAL OF PROCESS CONTROL, 2014, 24 (06) :782-789

[42] Price forecasting in the day-ahead electricity market [J].

Monroy, JJR ;

Kita, H ;

Tanaka, E ;

Hasegawa, J .

UPEC 2004: 39th International Universitities Power Engineering Conference, Vols 1-3, Conference Proceedings, 2005, :1303-1307

[43] Economic valuation of smart grid investments on electricity markets [J].

De Oliveira-De Jesus, P. M. ;

Henggeler Antunes, C. .

SUSTAINABLE ENERGY GRIDS & NETWORKS, 2018, 16 :70-90

[44] A Multi-stage Model Based on Association Rule Analysis for Forecasting and Modifying Electricity Demand and Price in a Smart Grid [J].

Liu, Huan ;

Han, Ying-Hua ;

Liu, Jiao-Rao .

FUZZY SYSTEM AND DATA MINING, 2016, 281 :337-345

[45] Day-ahead deregulated electricity market price classification using neural network input featured by DCT [J].

Anbazhagan, S. ;

Kumarappan, N. .

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2012, 37 (01) :103-109

[46] Application of Impulse Control in Smart Grid Price System [J].

Du, Peng ;

Li, Huimin ;

Fan, Youping .

Journal of Engineering Science and Technology Review, 2013, 6 (02) :57-61

[47] Making a smart city for the smart grid? The urban material politics of actualising smart electricity networks [J].

Bulkeley, Harriet ;

McGuirk, Pauline M. ;

Dowling, Robyn .

ENVIRONMENT AND PLANNING A-ECONOMY AND SPACE, 2016, 48 (09) :1709-1726

[48] An optimized model of electricity price forecasting in the electricity market based on fuzzy time series [J].

Safarinejadian, Behrooz ;

Gharibzadeh, Masihollah ;

Rakhshan, Mohsen .

SYSTEMS SCIENCE & CONTROL ENGINEERING, 2014, 2 (01) :677-683

[49] Electricity Market Design for the Incorporation of Various Demand-Side Resources in the Jeju Smart Grid Test-bed [J].

Park, Man-Guen ;

Cho, Seong-Bin ;

Chung, Koo-Hyung ;

Moon, Kyeong-Seob ;

Roh, Jae-Hyung .

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2014, 9 (06) :1851-1863

[50] Short-term price forecasting for competitive electricity market [J].

Mandal, Paras ;

Senjyu, Tomonobu ;

Urasaki, Naomitsu ;

Funabashi, Toshihisa ;

Srivastava, Anurag K. .

2006 38TH ANNUAL NORTH AMERICAN POWER SYMPOSIUM, NAPS-2006 PROCEEDINGS, 2006, :137-+

← 1 2 3 4 5 →