A learning framework based on weighted knowledge transfer for holiday load forecasting

Zeng, Pan; Sheng, Chang; Jin, Min

doi:10.1007/s40565-018-0435-z

Cited by 27 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, it is found that some special days affect load trends rapidly in a short period based on the above analysis, which is also confirmed in the previous work [28], [32]. Accordingly, special days must be considered as an important factor in STLF, especially Chinese national legal holidays listed in Table 1.…”

Section: Features Selectionsupporting

confidence: 83%

“…It is easy that only 5 missing points are supplemented by linear interpolation because of that there is only one missing point in every breaking interval. Then, Pauta criteria [27] are used to identify outliers, which is similar to [28]. Assume x i is sample data set during a period of time, the process of detecting outlier by Pauta criteria can be listed as follows:…”

Section: A Data Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

A Multifactorial Short-Term Load Forecasting Model Combined With Periodic and Non-Periodic Features - A Case Study of Qingdao, China

et al. 2020

View full text Add to dashboard Cite

In this paper, the load time-series measured from 2016 to 2018 in Qingdao is investigated in order to make a prediction more accurately by using an artificial neural network model combined with some regular and irregular features. The results of spectral analysis show that several periodic variations in diurnal, semidiurnal and weekly frequencies are prominent, and considered as critical parts of predictior variables of the training and test sets in this forecasting model. However, a significant decline of load happens during the national statutory festivals in China, and is more obvious with the longer holidays, which should be taken into account as abnormal conditions. Moreover, both temperatuer and hummity filtered out by mutual information method are also added as two essential weather factors to improve the prediction accuracy, especially in the hot summer. Finally, the comparative results of five different experiments in term of mean absolute percent error show that the forecasting model combined with all periodic and non-periodic factors outperforms the others with one single or a few of factors. This multifactorial model, taking fully account of internal charateristics of load data and external important influences, is proved more suitable to predict the load trend in Qingdao. INDEX TERMS Short-term load forcasting, artificial neural network, periodic and non-periodic factors, mean absolute percent error.

show abstract

Section: Features Selectionsupporting

confidence: 83%

Section: A Data Preprocessingmentioning

confidence: 99%

A Multifactorial Short-Term Load Forecasting Model Combined With Periodic and Non-Periodic Features - A Case Study of Qingdao, China

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Natural factors include temperature, air pressure, weather, air quality, etc., and social factors include holidays, weekdays, GDP, etc. These factors are widely used as feature variables [22]- [24]. Additionally, the current load variation is closely related to the historical load.…”

Section: A Dataset Collection and Splittingmentioning

confidence: 99%

Short-Term Power Load Forecasting Based on Cross Multi-Model and Second Decision Mechanism

2020

Self Cite

View full text Add to dashboard Cite

Short-term load forecasting (STLF) plays a vital role in the reliable, secure, and efficient operation of power systems. Since electric load variation results from diverse factors, accurate and stable load forecasting remains a challenging task. To increase the forecasting accuracy and stability, in this paper, we newly propose a short-term load forecasting method based on the cross multi-model and second decision mechanism. First, we combine horizontal and longitudinal training set selection method to construct the cross training sets, which acquire both the horizontal and longitudinal characteristics of the load variation. Second, to improve the generalization ability and extend the application scope, we construct forecasting multi-models by training multiple forecasting algorithms with cross training sets. Finally, to aggregate the forecasting outputs obtained by the forecasting multi-models, we propose a second decision mechanism based on a decision multi-model and adaptive weight allocation strategy, which overcomes the limited learning ability shortcoming of single decision models and further improves the forecasting accuracy. Case studies based on electrical load data from the state of Maine, the region of New England, Singapore, and New South Wales of Australia show that both the accuracy and the stability of the proposed method are superior to the compared models. INDEX TERMS Short-term load forecasting, multi-model, cross training set, second decision mechanism, model aggregation

show abstract

“…Figure 18 explains the scenario of flexible and not flexible resources where the horizontal-axis represents cumulative quantity supplied in MWh, and the vertical-axis means the marginal cost in $/MWh. As has been seen, oil, in general, is costly and suggested not to use until it is of absolute necessity [89], [90].…”

Section: B Load Forecasting Techniquesmentioning

confidence: 99%

A Qualitative Study on the United States Internet of Energy: A Step Towards Computational Sustainability

2020

View full text Add to dashboard Cite

The burgeoning growth of Big Data not only matures and improves the data management efficiency and useful information extraction techniques, but also motivates the computational science researchers to come up with a new method or solution that can be repurposed for problems across the domain. Computational Sustainability joins this movement for a transferrable computational technique for sustainable development and a better future. Internet-of-energy (IoE)-leveraging IoT to smart grids associated with advanced analytics-is one of the prominent efforts in this regard. This paper presents a qualitative analysis on the elements of the energy and power management ecosystem in the United States. This qualitative study includes the Grid Overview of the United States; Weather and Climate and its impact on the entire energy generation and consumption dynamics; Peak Load Forecasting and its techniques and burgeoning challenges; Variable Renewable Energy, its reliability challenges and how we can take advantage of this variability; Commodity Prices and its criticality; Energy Disaggregation and its impact on consumptionawareness; and Generation Expansion and Decision Analysis. Besides, IoE integration, associated tradeoffs, challenges, research opportunities and transferable computational techniques are addressed in this communication. Furthermore, schematics and quantitative analysis are presented in support of this study.INDEX TERMS Computational sustainability, Internet of Things, smart grid, Internet of Energy, big data, transferable computational techniques.

show abstract

A learning framework based on weighted knowledge transfer for holiday load forecasting

Cited by 27 publications

References 28 publications

A Multifactorial Short-Term Load Forecasting Model Combined With Periodic and Non-Periodic Features - A Case Study of Qingdao, China

A Multifactorial Short-Term Load Forecasting Model Combined With Periodic and Non-Periodic Features - A Case Study of Qingdao, China

Short-Term Power Load Forecasting Based on Cross Multi-Model and Second Decision Mechanism

A Qualitative Study on the United States Internet of Energy: A Step Towards Computational Sustainability

Contact Info

Product

Resources

About