1. |
- Heydari, A., et al.
(författare)
-
A combined fuzzy gmdh neural network and grey wolf optimization application for wind turbine power production forecasting considering scada data
- 2021
-
Ingår i: Energies. - : MDPI AG. - 1996-1073. ; 14:12
-
Tidskriftsartikel (refereegranskat)abstract
- A cost-effective and efficient wind energy production trend leads to larger wind turbine generators and drive for more advanced forecast models to increase their accuracy. This paper proposes a combined forecasting model that consists of empirical mode decomposition, fuzzy group method of data handling neural network, and grey wolf optimization algorithm. A combined K-means and identifying density-based local outliers is applied to detect and clean the outliers of the raw supervisory control and data acquisition data in the proposed forecasting model. Moreover, the empirical mode decomposition is employed to decompose signals and pre-processing data. The fuzzy GMDH neural network is a forecaster engine to estimate the future amount of wind turbines energy production, where the grey wolf optimization is used to optimize the fuzzy GMDH neural network parameters in order to achieve a lower forecasting error. Moreover, the model has been applied using actual data from a pilot onshore wind farm in Sweden. The obtained results indicate that the proposed model has a higher accuracy than others in the literature and provides single and combined forecasting models in different time-steps ahead and seasons.
|
|
2. |
- Billinton, R., et al.
(författare)
-
Bibliography on the application of probability methods in power system reliability evaluation 1996-1999
- 2001
-
Ingår i: IEEE Transactions on Power Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 0885-8950 .- 1558-0679. ; 16:4, s. 595-602
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a bibliography of papers on the subject of power system reliability evaluation. Papers in such areas as: probabilistic load flow, probabilistic production costing, probabilistic transient stability evaluation etc. have not been included except where they specifically address power system reliability evaluation. It includes material which has been made available since the publication of six previous papers Bibliography on the Application of Probability Methods in Power System Reliability Evaluation, IEEE Transactions on Power Apparatus and Systems PAS-91, 1972, pp. 649-660, Pas-97, 1978, pp. 2235-2242, PAS-103, 1984, pp. 275-282, IEEE Transactions on Power Systems, Vol. 3, no. 4, Nov. 1988, pp. 1555-1564, Vol. 9, No. 1, Feb. 1994, pp. 41-49, and Vol. 14, no. 1, Feb. 1999, pp. 51-57.
|
|
3. |
- Ribrant, Johan, et al.
(författare)
-
Survey of failures in wind power systems with focus on Swedish wind power plants during 1997-2005
- 2007
-
Ingår i: IEEE transactions on energy conversion. - : Institute of Electrical and Electronics Engineers (IEEE). - 0885-8969 .- 1558-0059. ; 22:1, s. 167-173
-
Tidskriftsartikel (refereegranskat)abstract
- The wind power industry has expanded greatly during the past few years, has served a growing market, and has spawned the development of larger wind turbines. Different designs and technical advances now make it possible to erect wind turbines offshore. The fast expansion of the wind power market faces some problems. The new designs are not always fully tested, and the designed 20-year lifetime is typically never achieved before the next generation of turbines are erected. This paper presents results from an investigation of failure statistics from four sources, i.e., two separate sources from Sweden, one from Finland, and one from Germany. Statistics reveal reliability performance of the different components within the wind turbine. The gearbox is the most critical, because downtime per failure is high compared to the other components. The statistical data for larger turbines also show trends toward higher, ever-increasing failure frequency when compared to small turbines, which have a decreasing failure rate over the operational years.
|
|
4. |
- Bertling, Lina M., et al.
(författare)
-
A reliability-centered asset maintenance method for assessing the impact of maintenance in power distribution systems
- 2005
-
Ingår i: IEEE Transactions on Power Systems. - : Institute of Electrical and Electronics Engineers (IEEE). - 0885-8950 .- 1558-0679. ; 20:1, s. 75-82, s. 2649-2649
-
Tidskriftsartikel (refereegranskat)abstract
- This paper proposes a method for comparing the effect of different maintenance strategies on system reliability and cost. This method relates reliability theory with the experience gained from statistics and practical knowledge of component failures and maintenance measures. The approach has been applied to rural and urban distribution systems. In particular, a functional relationship between failure rate and maintenance measures has been developed for a cable component. The results show the value of using a systematic quantitative approach for investigating the effect of different maintenance strategies.
|
|
5. |
- Bertling, Lina M.
(författare)
-
On evaluation of RCM for maintenance management of electric power systems
- 2005
-
Ingår i: 2005 IEEE POWER ENGINEERING SOCIETY GENERAL MEETING. ; , s. 2638-2640
-
Konferensbidrag (refereegranskat)abstract
- This panel presentation aims to propose a possible solution for how to evaluate the effect of RCM as a tool for maintenance management. The starting point is a general understanding of the RCM methodology. Further on, a quantitative approach for relating the impact of component maintenance on system reliability and total cost is introduced. The method, referred to as reliability-centred asset maintenance method (RCAM) is being developed within a research group at KTH in Sweden. Finally the presentation comments on ongoing research to evaluate the introduction of RCM. The aim of RCM is to optimize the maintenance achievements in a systematic way.
|
|
6. |
- Chowdhury, A. A., et al.
(författare)
-
Causal and seasonal analysis of bulk transmission line forced outages using the MAPP outage database
- 2006
-
Ingår i: 2006 International Conference on Probabilistic Methods Applied to Power Systems. - NEW YORK : IEEE. ; , s. 847-853
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- This paper describes the Mid-Continent Area Power Pool (MAPP), transmission equipment outage data collection scheme and presents bulk transmission line average outage statistics for forced outage category for the 230 kV and above systems computed using the data for the ten-year operating period from 1991 to 2000. In addition, a causal and seasonal contribution to forced outages of bulk transmission line is analyzed that helps to identify appropriate remedial actions to improve transmission line reliability. This paper presents selected applications of transmission line forced outage statistics by different MAPP member utilities.
|
|
7. |
- Chowdhury, A. A., et al.
(författare)
-
Determining distribution substation transformer optimal loadings using a reliability cost-benefit approach
- 2006
-
Ingår i: 2006 International Conference on Probabilistic Methods Applied to Power Systems, Vols 1 and 2. - NEW YORK : IEEE. ; , s. 1201-1209
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a novel reliability cost-benefit approach, taking into account customer value of reliability, to compare different transformer loading philosophies while concurrently considering varying levels of transformer emergency capability. Using this cost benefit approach, guidelines for loading existing transformers can be determined. The developed methodology can also be used to establish standard emergency rating criteria for purchasing new transformers, which will optimize reliability performance versus cost. The methodology is illustrated using practical system examples.
|
|
8. |
- Du, M., et al.
(författare)
-
A som based anomaly detection method for wind turbines health management through scada data
- 2016
-
Ingår i: International Journal of Prognostics and Health Management. - : Prognostics and Health Management Society. - 2153-2648. ; 7:4
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, a data driven method for Wind Turbine system level anomaly detection and root sub-component identification is proposed. Supervisory control and data acquisition system (SCADA) data of WT is adopted and several parameters are selected based on physical knowledge in this domain and correlation coefficient analysis to build a normal behavior model. This model which is based on Self-organizing map (SOM) projects higher-dimensional SCADA data into a two-dimension-map. Afterwards, the Euclidean distance based indicator for system level anomalies is defined and a filter is created to screen out suspicious data points based on quantile function. Moreover, a failure data pattern based criterion is created for anomaly detection from system level. In order to track which sub-component should be responsible for an anomaly, a contribution proportion (CP) index is proposed. The method is tested with a two-month SCADA dataset with the measurement interval as 20 seconds. Results demonstrate capability and efficiency of the proposed method.
|
|
9. |
- Nilsson, Julia, et al.
(författare)
-
Maintenance management of wind power systems using condition monitoring systems - Life cycle cost analysis for two case studies
- 2007
-
Ingår i: IEEE transactions on energy conversion. - : Institute of Electrical and Electronics Engineers (IEEE). - 0885-8969 .- 1558-0059. ; 22:1, s. 223-229
-
Tidskriftsartikel (refereegranskat)abstract
- The large growth in the wind power industry in the past years. mainly focuses on a growing market and the development of large turbines and offshore farms. The high technical availability of wind turbines comes with a greater need for frequent maintenance. Current maintenance planning is not optimized, and it is possible to make maintenance more efficient. Condition monitoring systems (CMS) could resolve the growing wind power industry's need for better maintenance management and increased reliability. Such systems are commonly used in other industries. CMS could continuously monitor the performance of the wind turbine parts and could help determine specific maintenance timing. This paper presents a life cycle cost (LCC), analysis with strategies where CMS improved maintenance planning for a single wind turbine onshore and a wind farm offshore. Case studies are based on real data from Olsvenne2 at Nasudden (Gotland, Sweden) and Kentish Flats, in the U.K. The main conclusion is that CMS benefits maintenance management of wind power systems. Improvements can be especially shown for offshore wind farm maintenance planning.
|
|
10. |
- Ribrant, Johan, et al.
(författare)
-
Survey of failures in wind power systems with focus on Swedish wind power plants during 1997-2005
- 2007
-
Ingår i: 2007 IEEE POWER ENGINEERING SOCIETY GENERAL MEETING. ; , s. 3896-3903
-
Konferensbidrag (refereegranskat)abstract
- The wind power industry has expanded greatly during the past few years, has served a growing market, and has spawned the development of larger wind turbines. Different designs and technical advances now make it possible to put wind turbines off shore. The fast expansion of the wind power market comes with problems. The new designs are not always fully tested, and the designed 20 year lifetime is typically never achieved before the next generation of turbines is erected. This paper presents results from an investigation of failure statistics from four sources, i.e. two separate sources from Sweden, one from Finland, and one from Germany. Statistics reveal reliability performance of the different components within the wind turbine. The gearbox is the most critical because downtime, per failure, is high compared to the other components in the wind power turbine. The statistical data for larger turbines also show trends toward higher, ever increasing failure frequency when compared to small turbines, which have a decreasing failure rate over the operational years.
|
|
11. |
- Wallnerström, Carl Johan, et al.
(författare)
-
Investigation of the robustness of the Swedish network performance assessment model
- 2008
-
Ingår i: IEEE Transactions on Power Systems. - : IEEE. - 0885-8950 .- 1558-0679. ; 23:2, s. 773-780
-
Tidskriftsartikel (refereegranskat)abstract
- The Swedish energy agency (STEM) has developed a regulatory model to supervise the revenues of the distribution system operators (DSO). The model is referred to as the network performance assessment model (NPAM). The NPAM calculates customer values for a fictive electrical distribution system, with a total cost referred to as the network performance assessment (NPA). The debiting rate for a DSO is defined by the quotient of the revenue and the NPA. If the debiting rate is higher than a certain value, the DSO is placed under review and could be forced to pay back revenue to customers. A lawsuit is currently in progress on this use of the NPAM. This paper shows results from a comprehensive sensitiveness study of the NPAM investigating the robustness of the model. The investigation shows that the model is not robust, since small stochastic variations in input data could lead to larger differences in the results than those from the model. For example, it is shown that a five-meter difference in the coordinates of the nodes in the reference system could result in a difference of 5 million Euros, i.e., approximately US $6.5 million. The understanding of weaknesses in the NPAM presented in this paper provides an important means for future developments of regulatory models in the world.
|
|