On the usefulness of solar energy forecasting in the presence of asymmetric costs of errors

Khabibrakhmanov, I. Kh.; Lu, Siyuan; Hamann, Hendrik F.; Warren, K. W.

doi:10.1147/jrd.2015.2495001

Cited by 10 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the loss function was designed based on a simple retail market which likely does not scale to complex scenarios. Another asymmetric loss function for solar power forecasting was studied in [20], where the loss function was formulated by adding a linear term and a cubic term as perturbations to the MSE loss function. The coefficients of the two additional terms control the degree of asymmetry of the loss function.…”

Section: Introductionmentioning

confidence: 99%

Cost-Oriented Load Forecasting

Zhang¹,

Yi²,

Hug³

2021

Preprint

View full text Add to dashboard Cite

Accurate load prediction is an effective way to reduce power system operation costs. Traditionally, the mean square error (MSE) is a common-used loss function to guide the training of an accurate load forecasting model. However, the MSE loss function is unable to precisely reflect the real costs associated with forecasting errors because the cost caused by forecasting errors in the real power system is probably neither symmetric nor quadratic. To tackle this issue, this paper proposes a generalized cost-oriented load forecasting framework. Specifically, how to obtain a differentiable loss function that reflects real cost and how to integrate the loss function with regression models are studied. The economy and effectiveness of the proposed load forecasting method are verified by the case studies of an optimal dispatch problem that is built on the IEEE 30-bus system and the open load dataset from the Global Energy Forecasting Competition 2012 (GEFCom2012).

show abstract

Section: Introductionmentioning

confidence: 99%

Cost-Oriented Load Forecasting

Zhang¹,

Yi²,

Hug³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To solve the challenge, we use genetic algorithm (GA) to implement the proposed asymmetric error metric for training parameters of forecasting models. Although forecasting with AEP function has been studied in [8,[20][21][22][23], the forecasting problem is still formulated as an independent task with the objective of minimising statistical forecast errors. Different from [8,[20][21][22][23], we incorporate DAUC information into load forecasting procedure for improving economic values of load forecasts.…”

Section: Introductionmentioning

confidence: 99%

“…Although forecasting with AEP function has been studied in [8,[20][21][22][23], the forecasting problem is still formulated as an independent task with the objective of minimising statistical forecast errors. Different from [8,[20][21][22][23], we incorporate DAUC information into load forecasting procedure for improving economic values of load forecasts. Moreover, values of asymmetric penalty factors in [8,[20][21][22][23] are heuristically set via experience.…”

Section: Introductionmentioning

confidence: 99%

“…Different from [8,[20][21][22][23], we incorporate DAUC information into load forecasting procedure for improving economic values of load forecasts. Moreover, values of asymmetric penalty factors in [8,[20][21][22][23] are heuristically set via experience. In this paper, asymmetric penalty factors for over-and underprediction situations are optimally determined based on their historical DAUC performances.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving economic values of day‐ahead load forecasts to real‐time power system operations

Wang

2017

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Automating Value-Oriented Forecast Model Selection by Meta-learning: Application on a Dispatchable Feeder

Werling,

Beichter,

Heidrich

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

To successfully increase the share of renewable energy sources in the power system and for counteract their fluctuating nature in view of system stability, forecasts are required that suit downstream applications, such as demand side management or management of energy storage systems. However, whilst many forecast models to create these forecasts exist, the selection of the forecast model best suited to the respective downstream application can be challenging. The selection is commonly based on quality measures (such as mean absolute error), but these quality measures do not consider the value of the forecast in the downstream application. Thus, we introduce a meta-learning framework for forecast model selection, which automatically selects the forecast model leading to the forecast with the highest value in the downstream application. More precisely, we use a meta-learning approach that considers the selection task as a classification problem. Furthermore, we empirically evaluate the proposed framework on the downstream application of a smart building’s photovoltaic-battery management problem known as dispatchable feeder on building-level with a data set containing time series from 300 buildings. The results of our evaluation demonstrate that the proposed framework reduces the cost and improves the accuracy compared to existing forecast model selection heuristics. Furthermore, compared to a manual forecast model selection, it requires noticeably less computational effort and leads to comparable results.

show abstract

On the usefulness of solar energy forecasting in the presence of asymmetric costs of errors

Cited by 10 publications

References 14 publications

Cost-Oriented Load Forecasting

Cost-Oriented Load Forecasting

Improving economic values of day‐ahead load forecasts to real‐time power system operations

Automating Value-Oriented Forecast Model Selection by Meta-learning: Application on a Dispatchable Feeder

Contact Info

Product

Resources

About