Forecasting customers' response to incentives during peak periods: A transfer learning approach

Cai, Long; Wen, Honglin; Gu, Jun; Ma, Jinghuan; Jin, Zhijian

doi:10.1002/2050-7038.12251

Cited by 8 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has shown great success, particularly when the source data is plentily available and the target one scarce. Recently it has even found applications for electricity load forecasting to transfer information from one set of customers to another one [23] . In our case our source data will be the data before the lockdown and the target one the data during the lockdown in the country of interest (France in our study), or even a similar one where the lockdown came before (e.g.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Obst

Vilmarest

Goude

2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic has urged many governments in the world to enforce a strict lockdown where all nonessential businesses are closed and citizens are ordered to stay at home. One of the consequences of this policy is a significant change in electricity consumption patterns. Since load forecasting models rely on calendar or meteorological information and are trained on historical data, they fail to capture the significant break caused by the lockdown and have exhibited poor performances since the beginning of the pandemic. In this paper we introduce two methods to adapt generalized additive models, alleviating the aforementioned issue. Using Kalman filters and fine-tuning allows to adapt quickly to new electricity consumption patterns without requiring exogenous information. The proposed methods are applied to forecast the electricity demand during the French lockdown period, where they demonstrate their ability to significantly reduce prediction errors compared to traditional models. Finally, expert aggregation is used to leverage the specificities of each predictions and enhance results even further.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Obst

Vilmarest

Goude

2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

show abstract

“…Second, the mean absolute percentage error (E MAPE ), mean squared error (E MSE ), and root mean squared error (E RMSE ) are also considered as performance assessment indicators for electrical demand predictions. 59,60 E MAPE , E MSE , and E RMSE are presented by Equations ( 26)-( 28) as follows:…”

Section: Metrics For Performance Evaluationmentioning

confidence: 99%

“…First, the absolute percentage error is formulated by Equation (25) as

E_{AE} = (||, \frac{t_{y} - o_{y}}{t_{y}}) \times 100 %

where t y and o y represent the actual electric load and electric load predictions by using LF approach, respectively. Second, the mean absolute percentage error (E MAPE ) , mean squared error (E MSE ) , and root mean squared error (E RMSE ) are also considered as performance assessment indicators for electrical demand predictions 59,60 . E MAPE , E MSE , and E RMSE are presented by Equations (26)‐(28) as follows:

E_{MAPE} = \frac{1}{N} \sum_{y = 1}^{N} (||, \frac{t_{y} - o_{y}}{t_{y}}) \times 100 %

E_{MSE} = \frac{1}{N} \sum_{y = 1}^{N} {(t_{y} - o_{y})}^{2}

E_{RMSE} = \sqrt{\frac{1}{N} \sum_{y = 1}^{N} {(t_{y} - o_{y})}^{2}}

…”

Section: Optimal Bra‐based Lf Strategy Incorporating Pccmentioning

confidence: 99%

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Waseem

Liu

Zhang

et al. 2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

With the grid's evolution, the end-users demand becomes more vital for demand side management (DSM). Accurate load forecasting (LF) is critical for power system planning and using advanced demand response (DR) strategies.To design efficient and precise LF, information about various factors that influence end-users demand is required. In this paper, the impact of different factors on electrical demand and capacity of climatic factors existence and their variation is discussed and analysed. The Pearson correlation coefficient (PCC) is utilized to express the degree of electric demand correlation with metrological and calendar factors. Then, the optimal-Bayesian regularization algorithm (BRA) based on ANN for LF is presented. The effect of the number of neurons in hidden layers on output is observed to select the most appropriate option. Additionally, heating degree days (HDDs) and cooling degree days (CDDs) indices are investigated to consider the impact of air conditioners' (ACs) loads in different seasons. Case studies on data from Dallas, Texas, USA, are used to

show abstract

“…It has shown great success, particularly when the source data is plentily available and the target one scarce. Recently it has even found applications for electricity load forecasting to transfer information from one set of customers to another one [22]. In our case our source data will be the data before the lockdown and the target one the data during the lockdown in the country of interest (France in our study), or even a similar one where the lockdown came before (e.g.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Obst¹,

Vilmarest²,

Goude³

2020

Preprint

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic has urged many governments in the world to enforce a strict lockdown where all nonessential businesses are closed and citizens are ordered to stay at home. One of the consequences of this policy is a significant change in electricity consumption patterns. Since load forecasting models rely on calendar or meteorological information and are trained on historical data, they fail to capture the significant break caused by the lockdown and have exhibited poor performances since the beginning of the pandemic. This makes the scheduling of the electricity production challenging, and has a high cost for both electricity producers and grid operators. In this paper we introduce adaptive generalized additive models using Kalman filters and fine-tuning to adjust to new electricity consumption patterns. Additionally, knowledge from the lockdown in Italy is transferred to anticipate the change of behavior in France. The proposed methods are applied to forecast the electricity demand during the French lockdown period, where they demonstrate their ability to significantly reduce prediction errors compared to traditional models. Finally expert aggregation is used to leverage the specificities of each predictions and enhance results even further.

show abstract

Forecasting customers' response to incentives during peak periods: A transfer learning approach

Cited by 8 publications

References 30 publications

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France

Contact Info

Product

Resources

About