<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The electric power industry has accumulated a large amount of historical data, and the analysis based on data mining can provide an effective reference for the electric power marketing of enterprises. In this paper, according to the analysis architecture of electric power marketing and its functional modules, the electric power marketing analysis system based on Bayesian algorithm is constructed through data extraction and transformation, modeling of Bayesian network, and simulation operation. At the same time, for the shortcomings of Bayesian algorithm with the large error of classification results under the condition of strong sample correlation, mutual information is introduced to modify the number of Laplace smoothing. The MI-NB model predicts the probability of electricity risk for company A to be 60% and the probability of electricity risk for company B to be 40%, with an error rate of 9.65% and 8.37%, respectively. In line loss rate analysis, the MI-NB model predicts an average line loss rate of 60.46% for station 1 and 60.43% for station 2, both in the high line loss rate range. The Bayesian algorithm based on mutual information can improve the practicality and intelligence of the power marketing decision analysis system, which makes the decision management of power supply enterprises more scientific and reasonable, and is of great practical significance in reducing the operational risk of enterprises.</p>
</abstract>

The electric power industry has accumulated a large amount of historical data, and the analysis based on data mining can provide an effective reference for the electric power marketing of enterprises. In this paper, according to the analysis architecture of electric power marketing and its functional modules, the electric power marketing analysis system based on Bayesian algorithm is constructed through data extraction and transformation, modeling of Bayesian network, and simulation operation. At the same time, for the shortcomings of Bayesian algorithm with the large error of classification results under the condition of strong sample correlation, mutual information is introduced to modify the number of Laplace smoothing. The MI-NB model predicts the probability of electricity risk for company A to be 60% and the probability of electricity risk for company B to be 40%, with an error rate of 9.65% and 8.37%, respectively. In line loss rate analysis, the MI-NB model predicts an average line loss rate of 60.46% for station 1 and 60.43% for station 2, both in the high line loss rate range. The Bayesian algorithm based on mutual information can improve the practicality and intelligence of the power marketing decision analysis system, which makes the decision management of power supply enterprises more scientific and reasonable, and is of great practical significance in reducing the operational risk of enterprises.

Application of Data Mining Algorithms in Power Marketing Predictive Analytics

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Application of Data Mining Algorithms in Power Marketing Predictive Analytics"}

The electric power industry has accumulated a large amount of historical data, and the analysis based on data mining can provide an effective reference for the...

Application of Data Mining Algorithms in Power Marketing Predictive Analytics

Online veröffentlicht: 28. Aug. 2023

Seitenbereich: -

Eingereicht: 04. Dez. 2022

Akzeptiert: 08. März 2022

DOI: https://doi.org/10.2478/amns.2023.2.00258

Schlüsselwörter
Data mining, MI-NB model, Electricity consumption risk, Line loss rate, Power marketing

© 2023 Wei Xu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Application of Data Mining Algorithms in Power Marketing Predictive Analytics

Online veröffentlicht: 28. Aug. 2023

Seitenbereich: -

Eingereicht: 04. Dez. 2022

Akzeptiert: 08. März 2022

DOI: https://doi.org/10.2478/amns.2023.2.00258

SchlüsselwörterData mining, MI-NB model, Electricity consumption risk, Line loss rate, Power marketing

© 2023 Wei Xu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Data mining, MI-NB model, Electricity consumption risk, Line loss rate, Power marketing