Multicriteria evaluation of predictive analytics for electric utility service management

Raghav Goyal, Vivek Ananthakrishnan, Sharan Srinivas, Vittaldas V. Prabhu

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

114Any interruption in the electric service system could lead to major disruption of daily life and economic losses. Therefore, electric utility companies strive to maintain high customer service levels and try to make the best use of past power outage experiences. Increasing capabilities of analytics and improved accuracy of short-term weather forecasts present opportunities for electric utilities to leverage historic data to predict outages and proactively make decisions to minimize interruptions. As discussed in Chapter 3, analytics can be grouped into three types: descriptive analytics, predictive analytics, and prescriptive analytics. Electric utilities typically use descriptive analytics such as Pareto chart for descriptive statistics and data visualization to derive insights about most frequent cause of power interruptions. This chapter mainly focuses on predictive analytics that uses weather forecasts to predict power interruptions. In this chapter, prescriptive analytics is limited to formulating a multiple criteria mathematical programming model that minimizes staffing the cost and duration of power interruption. The objective of this chapter is to predict customer interruptions using historical data and hourly weather forecasts. Six different machine learning algorithms are evaluated and the best algorithm is chosen using multiple criteria ranking techniques to predict power interruptions. A case study using data of an electric utility covering 75 substations consisting of 19 fields and over 40,000 records collected over a 1-year period is used to illustrate the proposed methodology. Further, to illustrate the advantages of the prediction model, the prediction outputs are used as a key parameter to formulate a multicriteria mathematical programming model for workforce planning.

Original languageEnglish (US)
Title of host publicationBig Data Analytics Using Multiple Criteria Decision-Making Models
PublisherCRC Press
Pages113-134
Number of pages22
ISBN (Electronic)9781498753753
ISBN (Print)9781498753555
DOIs
StatePublished - Jan 1 2017

Fingerprint

Electric utilities
Mathematical programming
Outages
Data visualization
Learning algorithms
Learning systems
Statistics
Planning
Economics
Predictive analytics
Costs
Industry

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

Goyal, R., Ananthakrishnan, V., Srinivas, S., & Prabhu, V. V. (2017). Multicriteria evaluation of predictive analytics for electric utility service management. In Big Data Analytics Using Multiple Criteria Decision-Making Models (pp. 113-134). CRC Press. https://doi.org/10.1201/9781315152653
Goyal, Raghav ; Ananthakrishnan, Vivek ; Srinivas, Sharan ; Prabhu, Vittaldas V. / Multicriteria evaluation of predictive analytics for electric utility service management. Big Data Analytics Using Multiple Criteria Decision-Making Models. CRC Press, 2017. pp. 113-134
@inbook{8a1397d3d6d64a559a4faf27162d4673,
title = "Multicriteria evaluation of predictive analytics for electric utility service management",
abstract = "114Any interruption in the electric service system could lead to major disruption of daily life and economic losses. Therefore, electric utility companies strive to maintain high customer service levels and try to make the best use of past power outage experiences. Increasing capabilities of analytics and improved accuracy of short-term weather forecasts present opportunities for electric utilities to leverage historic data to predict outages and proactively make decisions to minimize interruptions. As discussed in Chapter 3, analytics can be grouped into three types: descriptive analytics, predictive analytics, and prescriptive analytics. Electric utilities typically use descriptive analytics such as Pareto chart for descriptive statistics and data visualization to derive insights about most frequent cause of power interruptions. This chapter mainly focuses on predictive analytics that uses weather forecasts to predict power interruptions. In this chapter, prescriptive analytics is limited to formulating a multiple criteria mathematical programming model that minimizes staffing the cost and duration of power interruption. The objective of this chapter is to predict customer interruptions using historical data and hourly weather forecasts. Six different machine learning algorithms are evaluated and the best algorithm is chosen using multiple criteria ranking techniques to predict power interruptions. A case study using data of an electric utility covering 75 substations consisting of 19 fields and over 40,000 records collected over a 1-year period is used to illustrate the proposed methodology. Further, to illustrate the advantages of the prediction model, the prediction outputs are used as a key parameter to formulate a multicriteria mathematical programming model for workforce planning.",
author = "Raghav Goyal and Vivek Ananthakrishnan and Sharan Srinivas and Prabhu, {Vittaldas V.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1201/9781315152653",
language = "English (US)",
isbn = "9781498753555",
pages = "113--134",
booktitle = "Big Data Analytics Using Multiple Criteria Decision-Making Models",
publisher = "CRC Press",

}

Goyal, R, Ananthakrishnan, V, Srinivas, S & Prabhu, VV 2017, Multicriteria evaluation of predictive analytics for electric utility service management. in Big Data Analytics Using Multiple Criteria Decision-Making Models. CRC Press, pp. 113-134. https://doi.org/10.1201/9781315152653

Multicriteria evaluation of predictive analytics for electric utility service management. / Goyal, Raghav; Ananthakrishnan, Vivek; Srinivas, Sharan; Prabhu, Vittaldas V.

Big Data Analytics Using Multiple Criteria Decision-Making Models. CRC Press, 2017. p. 113-134.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Multicriteria evaluation of predictive analytics for electric utility service management

AU - Goyal, Raghav

AU - Ananthakrishnan, Vivek

AU - Srinivas, Sharan

AU - Prabhu, Vittaldas V.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 114Any interruption in the electric service system could lead to major disruption of daily life and economic losses. Therefore, electric utility companies strive to maintain high customer service levels and try to make the best use of past power outage experiences. Increasing capabilities of analytics and improved accuracy of short-term weather forecasts present opportunities for electric utilities to leverage historic data to predict outages and proactively make decisions to minimize interruptions. As discussed in Chapter 3, analytics can be grouped into three types: descriptive analytics, predictive analytics, and prescriptive analytics. Electric utilities typically use descriptive analytics such as Pareto chart for descriptive statistics and data visualization to derive insights about most frequent cause of power interruptions. This chapter mainly focuses on predictive analytics that uses weather forecasts to predict power interruptions. In this chapter, prescriptive analytics is limited to formulating a multiple criteria mathematical programming model that minimizes staffing the cost and duration of power interruption. The objective of this chapter is to predict customer interruptions using historical data and hourly weather forecasts. Six different machine learning algorithms are evaluated and the best algorithm is chosen using multiple criteria ranking techniques to predict power interruptions. A case study using data of an electric utility covering 75 substations consisting of 19 fields and over 40,000 records collected over a 1-year period is used to illustrate the proposed methodology. Further, to illustrate the advantages of the prediction model, the prediction outputs are used as a key parameter to formulate a multicriteria mathematical programming model for workforce planning.

AB - 114Any interruption in the electric service system could lead to major disruption of daily life and economic losses. Therefore, electric utility companies strive to maintain high customer service levels and try to make the best use of past power outage experiences. Increasing capabilities of analytics and improved accuracy of short-term weather forecasts present opportunities for electric utilities to leverage historic data to predict outages and proactively make decisions to minimize interruptions. As discussed in Chapter 3, analytics can be grouped into three types: descriptive analytics, predictive analytics, and prescriptive analytics. Electric utilities typically use descriptive analytics such as Pareto chart for descriptive statistics and data visualization to derive insights about most frequent cause of power interruptions. This chapter mainly focuses on predictive analytics that uses weather forecasts to predict power interruptions. In this chapter, prescriptive analytics is limited to formulating a multiple criteria mathematical programming model that minimizes staffing the cost and duration of power interruption. The objective of this chapter is to predict customer interruptions using historical data and hourly weather forecasts. Six different machine learning algorithms are evaluated and the best algorithm is chosen using multiple criteria ranking techniques to predict power interruptions. A case study using data of an electric utility covering 75 substations consisting of 19 fields and over 40,000 records collected over a 1-year period is used to illustrate the proposed methodology. Further, to illustrate the advantages of the prediction model, the prediction outputs are used as a key parameter to formulate a multicriteria mathematical programming model for workforce planning.

UR - http://www.scopus.com/inward/record.url?scp=85052591120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052591120&partnerID=8YFLogxK

U2 - 10.1201/9781315152653

DO - 10.1201/9781315152653

M3 - Chapter

SN - 9781498753555

SP - 113

EP - 134

BT - Big Data Analytics Using Multiple Criteria Decision-Making Models

PB - CRC Press

ER -

Goyal R, Ananthakrishnan V, Srinivas S, Prabhu VV. Multicriteria evaluation of predictive analytics for electric utility service management. In Big Data Analytics Using Multiple Criteria Decision-Making Models. CRC Press. 2017. p. 113-134 https://doi.org/10.1201/9781315152653