Higher Granular Sectoral Demand Forecast Under Data Scarcity: An Integrated Physics-Based Top–Down and Bottom–Up Approach

Angizeh, Farhad; Ghofrani, Ali; Jafari, Mohsen A.

doi:10.1109/jsyst.2022.3146359

Cited by 2 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this approach could forecast load consumption for the entire residential group, it is computationally extensive due to the requirement for multiple forecast models. In contrast, Angizeh et al combined the TD and BU approaches to estimate regional-level consumption [35]. This approach employs a simulator based on the physical characteristics of the building to model the consumption of each sector.…”

Section: Related Workmentioning

confidence: 99%

End-to-End Top-Down Load Forecasting Model for Residential Consumers

Parkash,

Lie,

et al. 2024

Energies

View full text Add to dashboard Cite

This study presents an efficient end-to-end (E2E) learning approach for the short-term load forecasting of hierarchically structured residential consumers based on the principles of a top-down (TD) approach. This technique employs a neural network for predicting load at lower hierarchical levels based on the aggregated one at the top. A simulation is carried out with 9 (from 2013 to 2021) years of energy consumption data of 50 houses located in the United States of America. Simulation results demonstrate that the E2E model, which uses a single model for different nodes and is based on the principles of a top-down approach, shows huge potential for improving forecasting accuracy, making it a valuable tool for grid planners. Model inputs are derived from the aggregated residential category and the specific cluster targeted for forecasting. The proposed model can accurately forecast any residential consumption cluster without requiring any hyperparameter adjustments. According to the experimental analysis, the E2E model outperformed a two-stage methodology and a benchmarked Seasonal Autoregressive Integrated Moving Average (SARIMA) and Support Vector Regression (SVR) model by a mean absolute percentage error (MAPE) of 2.27%.

show abstract

Section: Related Workmentioning

confidence: 99%

End-to-End Top-Down Load Forecasting Model for Residential Consumers

Parkash,

Lie,

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…The projected demand and RESs generations are two main input parameters with inherent stochasticity. The nodal hourly demand profiles are forecasted over the planning target years using our in-house high-resolution demand forecasting tool [7]. The NREL's PVWatts Calculator [8] is utilized to generate a set of preliminary hourly profiles for on-land wind and solar photovoltaic (PV) powers in different locations across the two states.…”

Section: B Uncertainty Characterizationmentioning

confidence: 99%

“…Both models were implemented and solved using CPLEX 12 solver under GAMS [13] on a desktop computer with a Core i7-11800H processor at 2.30 GHz and 16 GB of RAM. The above-mentioned demand-side parameters are fed into the net-load forecasting tool to estimate the hourly nodal demand profiles over the planning years, which is elaborated in [7].…”

Section: Case Study and Numerical Experimentsmentioning

confidence: 99%

Impact Assessment Framework for Grid Integration of Energy Storage Systems and Renewable Energy Sources Toward Clean Energy Transition

Angizeh,

Bae,

Chen

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

This paper proposes a two-stage decision-making tool to assess the impacts of energy storage systems (ESSs) and offshore wind farms (OSW) integration in the power grid. To quantify the potential impacts, various key performance indicators (KPIs) are incorporated. These KPIs gage the environmental, technical, and economical attributes of the integrated system. The proposed framework uses a unit commitment (UC) mixed-integer linear programming (MILP) model. Two case studies (one for New Jersey and one for New York) are examined with clean power transition targets. The uncertainties of the net-load and power generation from renewable energy sources (RESs) are characterized by Gaussian Process Regression (GPR) models. These models are fine-tuned using the base forecasts generated using our in-house load forecasting tool and the National Renewable Energy Laboratory's (NREL) publicly available generation calculator. The results show that ESS installations almost always improve the performance of the grid, regardless of the location and configuration. Furthermore, the unequally distributed ESS installations show better impacts than standalone centralized ESSs; and the mixed ESS technologies outperform single-type ESS deployments.INDEX TERMS Clean energy transition, net-zero energy system, 100% renewable energy, sustainability, offshore wind (OSW), energy storage system (ESS), planning and operation optimization.

show abstract

Higher Granular Sectoral Demand Forecast Under Data Scarcity: An Integrated Physics-Based Top–Down and Bottom–Up Approach

Cited by 2 publications

References 25 publications

End-to-End Top-Down Load Forecasting Model for Residential Consumers

End-to-End Top-Down Load Forecasting Model for Residential Consumers

Impact Assessment Framework for Grid Integration of Energy Storage Systems and Renewable Energy Sources Toward Clean Energy Transition

Contact Info

Product

Resources

About