Time Series-Based GHG Emissions Prediction for Smart Homes

Riekstin, Ana Carolina; Langevin, Antoine; Dandres, Thomas; Gagnon, Ghyslain; Cheriet, Mohamed

doi:10.1109/tsusc.2018.2886164

Cited by 25 publications

(22 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AEF involves the least complexity of all methods, which is an advantage when access to complex tools or detailed information is limited. 35 Some prior work uses AEF as their main method 36,37 or compares it with other emission factor methods. 18,22 Demand Marginal Emission Factor�Regression of Total Electricity Generation on Grid Emissions.…”

Section: ■ Materials and Methodsmentioning

confidence: 99%

How Well Do Emission Factors Approximate Emission Changes from Electricity System Models?

Elenes

Williams

Hittinger

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

Multiple forms of marginal and average emission factors have been developed to estimate the carbon emissions of adding technologies, such as electric vehicles or solar panels, to the electricity grid. Different methods can produce very different results and conclusions, indicating that choosing between methods is not trivial. Researchers would therefore like to know how well these emission factors can approximate emission changes in the actual power grid. This question remains unanswered because of the difficulty in characterizing the accuracy of these methods. Ideally, estimates would be compared to measured emission changes, but it is implausible to measure these changes on an actual grid. Instead, we propose testing these emission factor methods in a controlled environment, using an electricity system dispatch model as a reference for comparison. We find that average emission factors have lower accuracy when estimating emissions from demand shifts and observe the same for demand-based marginal emission factors at an hourly resolution. In contrast, incremental and thermal marginal emission factors can reproduce the emission changes of a power grid model under many testing conditions and scenarios. We also find that easier-to-use annual time averages offer similar results to finer time resolutions for marginal and average factors, except demand-based.

show abstract

Section: ■ Materials and Methodsmentioning

confidence: 99%

How Well Do Emission Factors Approximate Emission Changes from Electricity System Models?

Elenes

Williams

Hittinger

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…A company could schedule its production plan in advance to reduce the specific environmental impact indicators by consuming cleaner electricity, if the varied LCA impacts of electricity consumption can be tackled through LCA data of higher resolution, across both space and time. This has been demonstrated with various case studies, such as electricity storage systems (Elzein et al, 2019), households (Roux et al, 2016;Kopsakangas-Savolainen et al, 2017;Riekstin et al, 2020), electric vehicles (Zivin et al, 2014), and data centers (Dandres et al, 2017).…”

mentioning

confidence: 87%

Machine learning to forecast electricity hourly LCA impacts due to a dynamic electricity technology mix

Portolani¹,

Vitali²,

Cornago³

et al. 2022

Front. Sustain.

View full text Add to dashboard Cite

Conventional Life Cycle Assessment (LCA) that relies on static coefficients is usually based on yearly averages. However, the impacts of electricity supply vary remarkably on an hourly basis. Thus, a company production plan is reassessed to reduce selected LCA impacts due to electricity consumption. To achieve this, the company will need a forecast of hourly LCA impacts due to electricity consumption, which can be directly forecast with the Direct Forecasting (DF) approach. Alternatively, the Electricity Technological Mix Forecasting (ETMF) forecasts the electricity production of the technologies in the mix and subsequently linearly combines it with unitary LCA impact indicators. Here, we assessed different machine learning models to forecast two LCA impact indicators for the consumption of electricity in the Italy-North control zone. The feed-forward neural network (NN) with the ETMF approach was the best perfomer among the assessed forecasting models. In our dataset, recurrent neural networks (RNNs) performed worse than feed-forward neural networks. Due to its better forecasting performance, the ETMF approach was preferred over the DF approach. This was due to its flexibility and scalability with easy updates or expansion of the selected forecast indicators, and due to its ability to assess technology-specific errors in the forecasting. Finally, we propose to adopt the correlation of LCA impact indicators within the dataset to select indicators while avoiding unconscious burden-shifting.

show abstract

“…Recently Riekstin et al . ( 2018 ) considered control of PV-battery systems to minimise emissions ignoring costs, while a few studies have considered the problem of minimising both emissions and costs. For example, Nojavan et al .…”

Section: Previous Workmentioning

confidence: 99%

“…Typically these systems are used for minimising the cost of electricity via peak load shaving and energy arbitrage, sometimes in addition to providing reliability and backup functions. Recently Riekstin et al (2018) considered control of PV-battery systems to minimise emissions ignoring costs, while a few studies have considered the problem of minimising both emissions and costs. For example, Nojavan et al (2017) employed ε-constraint method and fuzzybased selection of the optimal solutions for optimizing a hybrid system of PV-batteryfuel cell in terms of emission and cost.…”

Section: Previous Workmentioning

confidence: 99%

Controlling electricity storage to balance electricity costs and greenhouse gas emissions in buildings

Aryai

Goldsworthy

2022

Energy Inform

View full text Add to dashboard Cite

The optimal management of flexible loads and generation sources such as battery storage systems in buildings is often concerned with minimizing electricity costs. There is an increasing need to managed flexible resources in a way that minimises both costs and carbon emissions. Minimising emissions of grid consumed electricity requires quantification of the carbon emissions intensity of the electricity grid, so first we develop a real-time emission intensity model of the Australian National Energy Market using a power-flow tracing approach. This model reveals that electricity price signals currently do not drive consumers toward using electricity at times of lower emissions. For example, the mean and peak emissions intensity during low electricity tariff periods are the same or slightly higher than those during high tariff periods, while the 30-min wholesale electricity price in each region has no significant correlation with the emissions intensity of electricity consumed in that region. The emissions model is then used to investigate the extent to which controlling a battery storage system to minimise costs under existing electricity tariff structures also leads to minimisation of greenhouse gas emissions for a case study commercial office building. Results show that reducing emissions does indeed come at the expense of increasing costs. For example, annual operating cost savings reduced from 31% to 20% when the battery control was changed from minimising costs to minimising emissions. This has important implications for buildings seeking to reduce emissions as well as for the design of electricity tariffs.

show abstract

Time Series-Based GHG Emissions Prediction for Smart Homes

Cited by 25 publications

References 39 publications

How Well Do Emission Factors Approximate Emission Changes from Electricity System Models?

How Well Do Emission Factors Approximate Emission Changes from Electricity System Models?

Machine learning to forecast electricity hourly LCA impacts due to a dynamic electricity technology mix

Controlling electricity storage to balance electricity costs and greenhouse gas emissions in buildings

Contact Info

Product

Resources

About