Forecasting Electricity Prices with Historical Statistical Information using Neural Networks and Clustering Techniques

Azevedo, Filipe; Vale, Zita

doi:10.1109/psce.2006.296247

Cited by 18 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trying to overcome this problem, a method was developed [14], [15] based on historical data that allows finding a maximum and a minimum value for the SMP for the period in question. A certain confidence level is associated to the forecasted interval.…”

Section: Optimization Problemmentioning

confidence: 99%

“…The authors' previous work [14], [15], an interval for the SMP is determined with a certain confidence level , revealed to be useful for the mean variance formulation because it requires not only the expected value of the total return but also its variance.…”

Section: Optimization Problemmentioning

confidence: 99%

“…Developed through the short-term method presented in [14] to increase the accuracy, the method presented in [15] is used in this example to forecast the price range between that period (August to December). Real load and price data from mainland Spanish market were used as historical data.…”

Section: E Penalty Functionsmentioning

confidence: 99%

“…Due to the characteristics of mean variance formulation, we developed a method [14], [15] based on historical data that allows to forecast a maximum and a minimum value for each period of the system marginal price (SMP), with a certain confidence level , which is useful to calculate the mean and variance of the total return.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Decision-Support System Based on Particle Swarm Optimization for Multiperiod Hedging in Electricity Markets

Azevedo

Vale

Oliveira

2007

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

This paper proposes a particle swarm optimization (PSO) approach to support electricity producers for multiperiod optimal contract allocation. The producer risk preference is stated by a utility function (U) expressing the tradeoff between the ex-pectation and variance of the return. Variance estimation and ex-pected return are based on a forecasted scenario interval deter-mined by a price range forecasting model developed by the au-thors. A certain confidence level is associated to each forecasted scenario interval. The proposed model makes use of contracts with physical (spot and forward) and financial (options) settlement. PSO performance was evaluated by comparing it with a genetic algo-rithm-based approach. This model can be used by producers in deregulated electricity markets but can easily be adapted to load serving entities and retailers. Moreover, it can easily be adapted to the use of other type of contracts.

show abstract

Section: Optimization Problemmentioning

confidence: 99%

Section: Optimization Problemmentioning

confidence: 99%

Section: E Penalty Functionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Decision-Support System Based on Particle Swarm Optimization for Multiperiod Hedging in Electricity Markets

Azevedo

Vale

Oliveira

2007

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…A way to modify the historical SMP price to simulate the existence of renewable generation is required, hence a neural network employing an evolutionary algorithm is used to predict new SMP prices. This is a common method used to forecast SMP prices (6), (7), (8) .…”

Section: Introductionmentioning

confidence: 99%

Optimizing the Electricity Price Revenue of Wind Power Generation Captures in the South Korean Electricity Market

Byrne¹,

Kim²,

Yong-Heack³

et al. 2016

Journal of the Korean Solar Energy Society

View full text Add to dashboard Cite

: How effectively a wind farm captures high market prices can greatly influence a wind farm's viability.This research identifies and creates an understanding of the effects that result in various capture prices (average revenue earned per unit of generation) that can be seen among different wind farms, in the current and future competitive SMP (System Marginal Price) market in South Korea. Through the use of a neural network to simulate changes in SMP caused by increased renewables, based on the Korea Institute of Energy Research's extensive wind resource database for South Korea, the variances in current and future capture prices are modelled and analyzed for both onshore and offshore wind power generation. Simulation results shows a spread in capture price of 5.5% for the year 2035 that depends on both a locations wind characteristics and the generations' correlation with other wind power generation. Wind characteristics include the generations' correlation with SMP price, diurnal profile shape, and capacity factor. The wind revenue cannibalization effect reduces the capture price obtained by wind power generation that is located close to a substantial amount of other wind power generation. In onshore locations wind characteristics can differ significantly/ Hence it is recommended that possible wind development sites have suitable diurnal profiles that effectively capture high SMP prices. Also, as increasing wind power capacity becomes installed in South Korea, it is recommended that wind power generation be located in regions far from the expected wind power generation 'hotspots' in the future. Hence, a suitable site along the east mountain ridges of South Korea is predicted to be extremely effective in attaining high SMP capture prices. Attention to these factors will increase the revenues obtained by wind power generation in a competitive electricity market.

show abstract

Reinventing the Energy Bill in Smart Cities with NoSQL Technologies

Costa

Santos

2016

Transactions on Engineering Technologies

View full text Add to dashboard Cite

Forecasting Electricity Prices with Historical Statistical Information using Neural Networks and Clustering Techniques

Cited by 18 publications

References 19 publications

A Decision-Support System Based on Particle Swarm Optimization for Multiperiod Hedging in Electricity Markets

A Decision-Support System Based on Particle Swarm Optimization for Multiperiod Hedging in Electricity Markets

Optimizing the Electricity Price Revenue of Wind Power Generation Captures in the South Korean Electricity Market

Reinventing the Energy Bill in Smart Cities with NoSQL Technologies

Contact Info

Product

Resources

About