A hybrid machine learning model for forecasting a billing period’s peak electric load days

Saxena, Harshit; Aponte, Omar; McConky, Katie

doi:10.1016/j.ijforecast.2019.03.025

Cited by 41 publications

(37 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We can conclude that machine learning algorithms could provide better accuracy and less computational cost for demand forecasting than traditional forecasting models. This finding is supported by some of the reported studies in the literature, including Golshani et al (2018), Jiang et al (2018), Saloux & Candanedo (2018), Cheng et al (2019), Saxena et al (2019). Besides, based on our review, one of the trends in the machine learning applications in demand forecasting included is the application of neural network algorithms when using machine learning in demand forecasting in the context of supply chain management.…”

Section: Service-oriented Manufacturing Demand 1 4%supporting

confidence: 81%

“…Artificial Neural Network (Aksoy et al, 2012(Aksoy et al, , 2014Badri et al, 2012;Bekkari and Zeddouri, 2019;Chu et al, 2011;Çunkaş and Altun, 2010;Ertugrul, 2016;Eseye et al, 2019;Golshani et al, 2018;Jebaraj et al, 2011;Kialashaki and Reisel, 2014;King et al, 2014;Kofinas et al, 2014;Puchalsky et al, 2018;Saloux and Candanedo, 2018;Saxena et al, 2019;Vijai and Bagavathi Sivakumar, 2018) 17 22%…”

Section: Service-oriented Manufacturing Demand 1 4%mentioning

confidence: 99%

See 1 more Smart Citation

Data Analytics in the Supply Chain Management: Review of Machine Learning Applications in Demand Forecasting

Aamer

Yani

Priyatna

2020

OSCM: An Int. Journal

View full text Add to dashboard Cite

Section: Service-oriented Manufacturing Demand 1 4%supporting

confidence: 81%

Section: Service-oriented Manufacturing Demand 1 4%mentioning

confidence: 99%

Data Analytics in the Supply Chain Management: Review of Machine Learning Applications in Demand Forecasting

Aamer

Yani

Priyatna

2020

OSCM: An Int. Journal

View full text Add to dashboard Cite

“…Most of the published research on electric load forecasting focuses on generating accurate electric load forecasts for both utilities and consumers, but there is limited research on the application of these forecasts to avoid the peak load charges described earlier. Saxena et al 9 noted that studies focusing on forecasting a billing period's PELDs in order to trigger demand response actions to reduce peak load charges are scarce. These authors developed an ensemble (also referred to as hybrid) machine‐learning model focused specifically on predicting if the next day will be a PELD for a billing period.…”

Section: Introductionmentioning

confidence: 99%

“…As the Saxena et al 9 methodology was being prepared for implementation at a university in the USA, the university's electricity infrastructure underwent a reconfiguration. The university's electricity infrastructure was divided into two main circuits.…”

Section: Introductionmentioning

confidence: 99%

Peak electric load days forecasting for energy cost reduction with and without behind the meter renewable electricity generation

Aponte

McConky

2021

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

Summary Many electricity consumers around the world are billed electric peak load charges. In the United States, these demand charges can contribute up to 70% of a consumer's electricity bill. Research has shown that the financial impact of these charges to the consumers can be reduced by acting on the intelligence provided by peak electric load day (PELD) forecasts. Unfortunately, published research detailing PELDs forecasting methodologies for facilities adopting behind the meter renewable electricity generation (BTMREG) is non‐existent. This paper contributes: (a) a PELD forecasting methodology applicable to consumers with BTMREG. A case study demonstrates the methodology's ability to achieve 93% of the potential savings in kW, translating to demand charge reductions of approximately US$ 142 129 per year. (b) The first side‐by‐side performance comparisons of electric load and PELD forecasting models for scenarios with and without BTMREG. (c) The first PELD forecasting model savings comparison for scenarios with and without BTMREG. Experimental results suggest that counterintuitively, BTMREG adoption can translate into higher peak load savings for electricity consumers.

show abstract

“…In the recent past physics informed data science has become a focus of research activities, e.g., [9]. It appears under different names e.g., physics informed [12]; hybrid learning [13]; physics-based [17], etc. ; but with the same basic idea of embedding physical principles into the data science algorithms.…”

Section: Introductionmentioning

confidence: 99%

Detection of Derivative Discontinuities in Observational Data

Ninevski

O’Leary

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents a new approach to the detection of discontinuities in the n-th derivative of observational data. This is achieved by performing two polynomial approximations at each interstitial point. The polynomials are coupled by constraining their coefficients to ensure continuity of the model up to the (n − 1)-th derivative; while yielding an estimate for the discontinuity of the n-th derivative. The coefficients of the polynomials correspond directly to the derivatives of the approximations at the interstitial points through the prudent selection of a common coordinate system. The approximation residual and extrapolation errors are investigated as measures for detecting discontinuity. This is necessary since discrete observations of continuous systems are discontinuous at every point. It is proven, using matrix algebra, that positive extrema in the combined approximation-extrapolation error correspond exactly to extrema in the difference of the Taylor coefficients. This provides a relative measure for the severity of the discontinuity in the observational data. The matrix algebraic derivations are provided for all aspects of the methods presented here; this includes a solution for the covariance propagation through the computation. The performance of the method is verified with a Monte Carlo simulation using synthetic piecewise polynomial data with known discontinuities. It is also demonstrated that the discontinuities are suitable as knots for B-spline modelling of data. For completeness, the results of applying the method to sensor data acquired during the monitoring of heavy machinery are presented.

show abstract

A hybrid machine learning model for forecasting a billing period’s peak electric load days

Cited by 41 publications

References 23 publications

Data Analytics in the Supply Chain Management: Review of Machine Learning Applications in Demand Forecasting

Data Analytics in the Supply Chain Management: Review of Machine Learning Applications in Demand Forecasting

Peak electric load days forecasting for energy cost reduction with and without behind the meter renewable electricity generation

Detection of Derivative Discontinuities in Observational Data

Contact Info

Product

Resources

About