A machine learning based stochastic optimization framework for a wind and storage power plant participating in energy pool market

Crespo-Vazquez, Jose L.; Carrillo, C.; Diaz-Dorado, E.; Martínez-Lorenzo, José Ángel; Noor‐E‐Alam, Md.

doi:10.1016/j.apenergy.2018.09.195

Cited by 44 publications

(29 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SO based models [12][13][14][15][16][17][18][19][20][21][22] Describing uncertainties of wind power and/or prices by using stochastic scenarios, pursuing the maximization of expected profit and/or profit CVaR while considering operational constraint under each stochastic scenario etc.…”

Section: Representative Literature Main Features Shortcomingsmentioning

confidence: 99%

“…Formulations for Uncertainties. According to [13][14][15][16], parameters in all operational constraints of a WF-ESS are irrelevant to day-ahead and balancing clearing prices, which means uncertainties of day-ahead and balancing clearing prices would not cause violations of operational constraints for a specific combination of day-ahead/balancing offering ({ } =1 /{ } =1 ) and real-time operating ({ , , } =1 ) strategies. That is to say, if using a number of joint stochastic scenarios to only represent uncertainties of day-ahead and balancing prices, there would be no increase in the number of WF-ESS's operational constraints.…”

Section: Wf-ess's Offering and Operating Models Based On Progressive mentioning

confidence: 99%

“…Reference [15] added a risk-aversion term in form of conditional value at risk (CVaR) in SO based model to additionally provide flexibility in finding a trade-off between profit maximization and risk management of WF-ESS operation under EM circumstances. In [16], machine learning was leveraged to define scenarios; then a two-stage convex SO model was formulated for WF-ESS to participate in pool market. Reference [17] introduced the demand response (DR) for integration with WF-ESS, and a SO based day-ahead offering decision-making model was proposed for this DR-WF-ESS.…”

Section: Introductionmentioning

confidence: 99%

“…In summary, SO and RO are popular approaches to address WF-ESS's offering and operating decision-making problems nowadays. In those SO related methodologies ( [13][14][15][16][17][18][19][20][21][22], etc. ), uncertainties are forecasted and formulated by applying multiple stochastic scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimal Offering and Operating Strategies for Wind‐Storage System Participating in Spot Electricity Markets with Progressive Stochastic‐Robust Hybrid Optimization Model Series

Wang

Zhao

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the increase of wind power installed capacity and the development of energy storage technologies, it is gradually accepted that integrating wind farms with energy storage devices to participate in spot electricity market (EM) is a promising way for improving wind power uncertainty accommodation and bringing considerable profit. Hence, research on reasonable offering and operating strategies for integrated wind farm-energy storage system (WF-ESS) under spot EM circumstances has important theoretical and practical significance. In this paper, a newly progressive stochastic-robust hybrid optimization model series is proposed for yielding such strategies. In the day-ahead stage, day-ahead and balancing prices uncertainties are formulated by applying joint stochastic scenarios, and real-time available wind power uncertainties are modeled by using the seasonal auto-regression (AR) based dynamic uncertainty set. Then, the first model of this model series is established and utilized for cooptimizing both the day-ahead offering and nominal real-time operating strategies. In the balancing stages, wind power uncertainty set and balancing prices stochastic scenarios are dynamically updated with the newly realized data. Then, each model from the remaining of this model series is established and utilized period by period for obtaining the optimal balancing/real-time offering/operating strategies adjusted from the nominal ones. Robust optimization (RO) in this progressive framework makes the operation of WF-ESS dynamically accommodate wind power uncertainties while maintaining relatively low computational complexity. Stochastic optimization (SO) in this progressive framework makes the WF-ESS avoid pursuing profit maximization strictly under the worst-case scenarios of prices uncertainties. Moreover, by adding a risk-aversion term in form of conditional value at risk (CVaR) into the objective functions of this model series, the optimization models additionally provide flexibility in reaching a trade-off between profit maximization and risk management. Simulation and profit comparisons with other existing methods validate the scientificity, feasibility, and effectiveness of applying our proposed model series.

show abstract

Section: Representative Literature Main Features Shortcomingsmentioning

confidence: 99%

Section: Wf-ess's Offering and Operating Models Based On Progressive mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimal Offering and Operating Strategies for Wind‐Storage System Participating in Spot Electricity Markets with Progressive Stochastic‐Robust Hybrid Optimization Model Series

Wang

Zhao

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The needed flexibility could be achieved with grid friendly wind energy generation, improved flexibility in conventional generation, transmission expansion, operational enhancement and demand response. Energy storage can be an important player in adding flexibility as it can act both as generation and load [7][8][9].…”

Section: Wind Energy Integrationmentioning

confidence: 99%

Benefit Analysis of Wind Energy Storage by Time Shift Simulation

Andor¹,

Aquino²,

Cámara³

et al. 2018

SNE

View full text Add to dashboard Cite

Currently there exist several energy storage technologies that are suitable for wind energy integration services. Energy prices in several countries (such as in Spain) are set for the day ahead market, which means the hourly prices are known the day before. This represents an opportunity for wind power plant owners. Wind energy generated in hours when demand and prices are the lowest could be stored and sold in hours when demand and prices are higher. This paper analyses the benefit of wind energy storage by time shift depending on climatological (wind), technological (storage facilities), and market (power prices) factors for the Spanish case, as exemplification of a methodology to be used in any other country. Wind energy time shift has been simulated for periods of time of 1 hour up to 9 hours considering two scenarios, a day with low wind energy generation and a day with high wind generation, in order to determine in which moments a beneficial exists with the different energy storage technologies. According to the results, on a day with high wind energy levels the gain obtained by time shifting wind energy from low to high demand hours could reach 68,1%, and on a day with low wind energy levels, the gain obtained by time shifting wind energy could reach 19,3%.

show abstract

Selected Applications

Archetti¹,

Candelieri²

2019

SpringerBriefs in Optimization

View full text Add to dashboard Cite

A machine learning based stochastic optimization framework for a wind and storage power plant participating in energy pool market

Cited by 44 publications

References 34 publications

Optimal Offering and Operating Strategies for Wind‐Storage System Participating in Spot Electricity Markets with Progressive Stochastic‐Robust Hybrid Optimization Model Series

Optimal Offering and Operating Strategies for Wind‐Storage System Participating in Spot Electricity Markets with Progressive Stochastic‐Robust Hybrid Optimization Model Series

Benefit Analysis of Wind Energy Storage by Time Shift Simulation

Selected Applications

Contact Info

Product

Resources

About