Energy forecasting: Predictions, reality and analysis of causes of error

Utgikar, Vivek; Scott, J.

doi:10.1016/j.enpol.2005.06.006

Cited by 50 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Scenario analysis differs slightly from forecasts and predictions, as it examines the consequences of future energy trends whereas a forecast or prediction B. K. SOVACOOL 1184 attempts to decipher what will actually occur. An energy scenario is, in other words, 'a reasonably definite statement about the characteristic functional capabilities in the future, based upon well-founded analysis of status and development of existing technology' [6]. The scenario analysis presented here depicts what would happen if there were no new energy policy interventions by governments beyond those adopted by mid-2009.…”

Section: Methodsmentioning

confidence: 99%

Exploring the hypothetical limits to a nuclear and renewable electricity future

Sovacool

2009

Int. J. Energy Res.

View full text Add to dashboard Cite

SUMMARYThis article evaluates whether the world can transition to a future global electricity system powered entirely by nuclear power plants, wind turbines, solar panels, geothermal facilities, hydroelectric stations, and biomass generators by 2030. It begins by explaining the scenario method employed for predicting future electricity generation, drawn mostly from tools used by the International Energy Agency. The article projects that the world would need to build about 7744 Gigawatts (GW) of installed electricity capacity by 2030 to provide 37.2 thousand terawatt-hours (TWh). Synthesizing data from the primary literature, the article argues that meeting such a projection with nuclear and renewable power stations will be difficult. If constructed using commercially available and state-of-the-art nuclear and renewable power stations today, the capital cost would exceed $40 trillion, anticipated negative externalities would exceed $1 trillion per year, and immense strain would be placed on land, water, material, and human resources. Even if nuclear and renewable power technologies were much improved, trillions of dollars of investment would still be needed, millions of hectares of land set aside, quadrillions of gallons of water used, and material supplies of aluminum, concrete, silicon, and steel heavily utilized or exhausted. Because of these constraints, the only true path towards a more sustainable electricity system appears to be reducing demand for electricity and consuming less of it.

show abstract

Section: Methodsmentioning

confidence: 99%

Exploring the hypothetical limits to a nuclear and renewable electricity future

Sovacool

2009

Int. J. Energy Res.

View full text Add to dashboard Cite

show abstract

“…Many researchers [11][12][13][14][15][16][17][18][19][20][21][22][23][24] have made some important contributions to renewable energy technology foresight studies.…”

Section: Introductionmentioning

confidence: 99%

From potential forecast to foresight of Turkey's renewable energy with Delphi approach

Çeliktaş

Koçar

2010

Energy

View full text Add to dashboard Cite

“…The above-mentioned observations indicate that larger LSTM ensemble size does not always guarantee improved (generalization [24]) forecasting accuracy. Moreover, the least number of ensemble members is more beneficial for reducing the computational costs required, especially when our proposed LSTM ensemble is applied to forecast (predict) a large number of time series, which is common in energy-and finance-related forecasting applications [7][8][9].…”

Section: Effect Of Lstm Ensemble Size On Forecasting Accuracymentioning

confidence: 99%

“…Moreover, energy-related time series forecasting plays an important role in the planning and working of the power grid system [7,8]; for instance, accurate and stable wind speed forecast has primary importance in the wind power industry and make an influence on power-system management and the stability of market economics [11].…”

Section: Introductionmentioning

confidence: 99%

“…Time series forecasting has fundamental importance in numerous practical engineering fields such as energy, finance, geology, and information technology [7][8][9][10][11][12]. For instance, forecasting of electricity consumption is of great importance in deregulated electricity markets for all of the stakeholders: energy wholesalers, traders, retailers, and consumers [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting

Choi

Lee

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Time series forecasting is essential for various engineering applications in finance, geology, and information technology, etc. Long Short-Term Memory (LSTM) networks are nowadays gaining renewed interest and they are replacing many practical implementations of the time series forecasting systems. This paper presents a novel LSTM ensemble forecasting algorithm that effectively combines multiple forecast (prediction) results from a set of individual LSTM networks. The main advantages of our LSTM ensemble method over other state-of-the-art ensemble techniques are summarized as follows: (1) we develop a novel way of dynamically adjusting the combining weights that are used for combining multiple LSTM models to produce the composite prediction output; for this, our method is devised for updating combining weights at each time step in an adaptive and recursive way by using both past prediction errors and forgetting weight factor; (2) our method is capable of well capturing nonlinear statistical properties in the time series, which considerably improves the forecasting accuracy; (3) our method is straightforward to implement and computationally efficient when it comes to runtime performance because it does not require the complex optimization in the process of finding combining weights. Comparative experiments demonstrate that our proposed LSTM ensemble method achieves state-of-the-art forecasting performance on four real-life time series datasets publicly available.

show abstract

Energy forecasting: Predictions, reality and analysis of causes of error

Cited by 50 publications

References 27 publications

Exploring the hypothetical limits to a nuclear and renewable electricity future

Exploring the hypothetical limits to a nuclear and renewable electricity future

From potential forecast to foresight of Turkey's renewable energy with Delphi approach

Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting

Contact Info

Product

Resources

About