Demand-side improvement of short-term load forecasting using a proactive load management – a supermarket use case

Glavan, Miha; Gradišar, Dejan; Moscariello, Salvatore; Juričić, Đani; Vrančić, Damir

doi:10.1016/j.enbuild.2019.01.016

Cited by 17 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their centralized approach resulted in good forecasting results. A very limited number of studies [17] have been conducted in regards to energy load forecasting between control centres and REPs.…”

Section: A Load Forecasting At Repsmentioning

confidence: 99%

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Husnoo¹,

Anwar²,

Hosseinzadeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

As Smart Meters are collecting and transmitting household energy consumption data to Retail Energy Providers (REP), the main challenge is to ensure the effective use of fine-grained consumer data while ensuring data privacy. In this manuscript, we tackle this challenge for energy load consumption forecasting in regards to REPs which is essential to energy demand management, load switching and infrastructure development. Specifically, we note that existing energy load forecasting is centralized, which are not scalable and most importantly, vulnerable to data privacy threats. Besides, REPs are individual market participants and liable to ensure the privacy of their own customers. To address this issue, we propose a novel horizontal privacy-preserving federated learning framework for REPs energy load forecasting, namely FedREP. We consider a federated learning system consisting of a control centre and multiple retailers by enabling multiple REPs to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security and scalability. For forecasting, we use a state-of-theart Long Short-Term Memory (LSTM) neural network due to its ability to learn long term sequences of observations and promises of higher accuracy with time-series data while solving the vanishing gradient problem. Finally, we conduct extensive data-driven experiments using a real energy consumption dataset. Experimental results demonstrate that our proposed federated learning framework can achieve sufficient performance in terms of MSE ranging between 0.3 to 0.4 and is relatively similar to that of a centralized approach while preserving privacy and improving scalability.

show abstract

Section: A Load Forecasting At Repsmentioning

confidence: 99%

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Husnoo¹,

Anwar²,

Hosseinzadeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the proposed approach, it is not considered any type of forecasting in level of load at the demand-side [24] as the industrial process is defined in advanced based on production orders.…”

Section: Energy Balancingmentioning

confidence: 99%

Increase of capacity in electric arc-furnace steel mill factories by means of a demand-side management strategy and ampacity techniques

Canteli

Zobaa

Vaccaro

et al. 2021

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

An electric arc-furnace is a complex industry which demands high levels of electrical energy in order to heat iron materials and other additives needed for the production of cast iron and/or steelmaking. The cost of the electrical energy demanded by the factory during the production can be greater than 20% of the overall cost. This kind of arc-furnace allows the production of steel with levels of scrap metal feedstock up to 100%. From an electrical point of view, the factory size in terms of its maximum apparent power demanded from the grid is designed to make use of the static capacity of the transmission line that supplies the energy. In that case, it is not possible to increase the power of the factory above the static rating by adding new facilites without installing new transmission infrastructures. This paper presents a methodology that allows an increase in net power of an arc-furnace factory without installing new transmission lines.The solution is based on a mix strategy that combines Demand-Side Management (DSM) methodologies and the use of ampacity techniques according IEEE 738 and CIGRE TB601.The application of DSM methodologies provides an improvement in the sustainability of not only the industrial customer but also in the overall grid. As a

show abstract

“…The AI allows efficient preparation and management of the bulk energy while the effects of the model are much quicker than traditional knowledge discovery and computational neuroscience-based models [38]. Different studies have been performed on demand-side load management and then its effects calculated in real-time predictions [39], microgrid load with deep learning and solar power prediction [40], short-term demand-side planning load prediction [41], and a new hybrid approach commonly used in the prediction of load demand and electricity levels throughout the smart grid infrastructure [42]. The AI is a mixture of neural networks, Fuzzy logic [43], vector supporting computer, genetic algorithms, and ML-based methods [44], used in load planning and control.…”

Section: A Existing Literaturementioning

confidence: 99%

Efficient Energy Planning With Decomposition-Based Evolutionary Neural Networks

2020

View full text Add to dashboard Cite

Load forecasting/prediction is a challenging task in the energy markets that require adequate attention in generating stable and reliable load demand to deal with energy management and planning strategies. Accurate load prediction is critical for electrical power systems operations, but nonlinear loads involve high volatility. Forecasting these kinds of complex load characteristics requires highly accurate forecasting devices. It is generally accomplished by constructing models on relative details, including weather and previous data on load demand. This study proposes six decomposition-based evolutionary neural networks for city-scale and building energy forecasting. These evolutionary neural networks have also been trained using historical load data, and weather records are already considered to have a significant effect on energy usage (for example, wind speed, precipitation, dry-dew point temperature, relative humidity, clouds fraction and mean sea level perception). The network structure of the model is built and based on error estimation, trend map, and appropriate method of measuring evolutionary neural networks efficiency. The model's hidden layers and neurons network structure is selected based on recent smart models to enhance its accuracy. Several measures were used to improve performance, such as seasonal smoothing changes, coarsegraining of the humidity ratio, load-oriented day-type classification monitoring, outlier removal, and complex climate information. Results show that used models have a very high fitting accuracy and low error rate for short, medium, and long-term forecasting/planning tasks. These models have the potential to reduce overfitting issues, thereby improving load forecasting efficiency. Further, proposed models may also use for forecasting solar and wind demand. The efficiency of the model compared to the existing two models. Forecast results show superiority and efficiency in short, medium and long-term energy forecasting and offer the ability to manage unbalanced utility loads.

show abstract

Demand-side improvement of short-term load forecasting using a proactive load management – a supermarket use case

Cited by 17 publications

References 33 publications

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Increase of capacity in electric arc-furnace steel mill factories by means of a demand-side management strategy and ampacity techniques

Efficient Energy Planning With Decomposition-Based Evolutionary Neural Networks

Contact Info

Product

Resources

About