Multitask Bayesian Spatiotemporal Gaussian Processes for Short-Term Load Forecasting

Gilanifar, Mostafa; Wang, Hui; Sriram, Lalitha Madhavi Konila; Özgüven, Eren Erman; Arghandeh, Reza

doi:10.1109/tie.2019.2928275

Cited by 48 publications

(21 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to other practical and research applications, survey data similar to those collected for the current study can also be combined with technical data on disaster-related disruptions to city functioning and infrastructure in order to better understand citizen needs and the use of smart city functions [75]. Specifically, such survey data can be combined or cross-validated with data on infrastructure disruptions, such as power outages and roadway closures [76][77][78][79] as well as with city data on demographics and socioeconomics [80,81].…”

Section: Discussionmentioning

confidence: 99%

The Road toward Smart Cities: A Study of Citizens’ Acceptance of Mobile Applications for City Services

Hou

Arpan

et al. 2020

Energies

Self Cite

View full text Add to dashboard Cite

Many local governments have started using smartphone applications to more effectively inform and communicate with citizens. This trend is of interest, as cities can only be smart if they are responsive to their citizens. In this paper, the intention to use such a mobile application among adult residents (n = 420) of a mid-sized city in the southeastern United States was examined using hierarchical linear regression analysis. The regression model that was tested indicated significant predictors of the intention to use the app in order to report municipal problems, such as power outages, and to request services for one’s home or community, including: Performance expectancy (e.g., citizens’ beliefs that the app would be efficient, helpful, convenient), effort expectancy (citizens’ beliefs about difficulty of using the app), social influence, perceived cost (e.g., privacy loss, storage space, unwanted notifications), and prior use of city apps. Consistent with current research on technology adoption, performance expectancy had the strongest influence on app-use intentions. Additionally, citizens’ trust in their city government’s ability to effectively manage an app was a weak, positive predictor of app-use intentions; general trust in the city government did not predict app-use intentions. Implications for city governments and city app developers are discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

The Road toward Smart Cities: A Study of Citizens’ Acceptance of Mobile Applications for City Services

Hou

Arpan

et al. 2020

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors of [32] use multi-task learning to improve the neighborhood's forecast by using implicit betweencommunity knowledge transfer. The relatedness between communities is calculated from regression models' parameters to build the proposed multi-task learning model.…”

Section: B Load Forecasting For Multiple Households or Neighborhoodmentioning

confidence: 99%

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

Sakuma

Nishi

2022

IEEE Access

View full text Add to dashboard Cite

Short-term load forecasting plays an essential role in appliance control in households and demand response at the neighborhood or community level. When load forecasting is simultaneously performed at different levels in a smart community, a central method that directly aggregates raw household data may incur a security issue. However, an individual method that builds separate models for each level requires additional data collection. We propose a distributed load forecasting framework that is secure, data efficient, and resource efficient. Our proposed method shares the latent variables, the reduced expression of the input data, of the household models without revealing the raw data. The latent variables are aggregated and fed to the neighborhood model, and during inference, input data collection can be abbreviated in the neighborhood. Because household models provide informative latent variables, the number of model parameters for the neighborhood model can be reduced. Our proposed method is evaluated using real

show abstract

“…Shi et al (2018) proposed a short-term electricity, heating, and gas load forecasting method based on DBN and MTL, which proved that MTL had good adaptability to the coupling processing between multiple energy sources. Gilanifar et al (2020) proposed an MTL algorithm for a BSGP model to enhance the processing of relevant information in different residential communities. Since the correlation between load data is an external manifestation of the coupling between energy sources, considering the correlation processing of multienergy data by MTL can dig deeper into energy coupling.…”

Section: Introductionmentioning

confidence: 99%

Multienergy Load Forecasting for Regional Integrated Energy Systems Considering Multienergy Coupling of Variation Characteristic Curves

Wang

Zhao

et al. 2021

Front. Energy Res.

View full text Add to dashboard Cite

Multienergy load forecasting (MELF) is the premise of regional integrated energy systems (RIES) production planning and energy dispatch. The key of MELF is the consideration of multienergy coupling and the improvement of prediction accuracy. Therefore, a MELF method considering the multienergy coupling of variation characteristic curves (MELF_MECVCC) for RIES is proposed. The novelty of MELF_MECVCC lies in the following three aspects. 1) For the trend stripping and volatility extraction of multienergy load time series, the extreme-point symmetric mode decomposition-sample entropy (ESMD-SE) method is introduced to decompose and reconstruct the variation characteristic curves of multienergy, including trend curve and fluctuation curve. 2) The multienergy coupling of the variation characteristic curves is considered to reflect the variation characteristics of the multienergy loads. 3) Different methods are applied according to different variation characteristics; i.e., the combined method based on multitask learning and long short-term memory network (MTL-LSTM) is applied to predict the trend curve with strong correlation and the least square support vector regression (LSSVR) method is applied to predict the fluctuation curve with strong volatility and high complexity. Based on the actual data set of the University of Texas in Austin, the MELF_MECVCC model is simulated and verified, which shows that the model reduces the mean absolute percentage error (MAPE) and the root mean square error (RMSE) and fits better with the original load and has higher prediction accuracy, compared with current advanced algorithms.

show abstract

Multitask Bayesian Spatiotemporal Gaussian Processes for Short-Term Load Forecasting

Cited by 48 publications

References 33 publications

The Road toward Smart Cities: A Study of Citizens’ Acceptance of Mobile Applications for City Services

The Road toward Smart Cities: A Study of Citizens’ Acceptance of Mobile Applications for City Services

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

Multienergy Load Forecasting for Regional Integrated Energy Systems Considering Multienergy Coupling of Variation Characteristic Curves

Contact Info

Product

Resources

About