Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models

Load forecasting is an essential task which is executed by electricity retail companies. By predicting the demand accurately, companies can prevent waste of resources and blackouts.Load forecasting directly affect the financial of the company and the stability of the Turkish Electricity Market. This study is conducted with an electricity retail company, and main focus of the study is to build accurate models for load. Datasets with novel features are preprocessed, then deep learning models are built in order to achieve high accuracy for these problems. Furthermore, a novel method for solving regression problems with classification approach (discretization) is developed for this study. In order to obtain more robust model, an ensemble model is developed and the success of individual models are evaluated in comparison to each other.

Anahtar Kelime: regression by classification deep learning Load forecasting

Investigation of The Relationship Between Temporomandibular Joint Dysfunction and Factors Triggering Dysfunction in Health Science Students

Öz:

Objective The aim of this study is to assess the risk of developing Temporomandibular joint (TMJ) dysfunction in university students and to examine the relationship between trigger factors for dysfunction and quality of life, neck disability, and psychological status. ( Sakarya Med J 2019, 9(2):258-265 ). Materials and Methods According to the criteria of inclusion and exclusion, 197 volunteer students in the faculty of health sciences were evaluated. The risk of developing dysfunction, trigger factors for dysfunction, psychological status, quality of life and pain-related disability status were assessed. Kruskal Wallis and Spearman correlation analysis were used for statistical analysis. Results 197 university students (mean age: 20.79±2.13 years) were included in the study 81.7% of the students had at least one symptom related to TMJ disorders. There was a significant difference between disability level, psychological status and quality of life according to TMJ dysfunction risk level (p<0.01 for all values). In our study, there was a weak positive correlation between the number of symptoms of students and disability severity (r=0.397, p<0.001) and psychological status (r=0.279, p<0.001), there was a weak negative correlation with SF-36 physical (r=-0.328, p<0.001) and mental components (r=-0.305, p<0.001). Conclusion According to our research, at least one symptom of TMJ dysfunction is present in more than 80% of Health Science students in general. This increase in the risk of TMJ problems can be attributed to the fact that the joint biomechanically affects adjacent body segments and that the dysfunction is closely related to disability, quality of life, and deterioration in psychological condition.

Anahtar Kelime:

Sağlık Bilimleri Öğrencilerinde Temporomandibular Eklem Disfonksiyonu ile Disfonksiyonu Tetikleyen Faktörler Arasındaki İlişkinin Araştırılması

Öz:

Amaç Bu çalışmanın amacı, üniversite öğrencilerinde Temporomandibular eklem (TME) disfonksiyon gelişme riskini değerlendirmek; disfonksiyonu tetikleyen faktörler ileyaşam kalitesi, boyun disabilitesi ve psikolojik durum arasındaki ilişkiyi incelemektir. ( Sakarya Tıp Dergisi 2019, 9(2):258-265 )Gereç veYöntemlerDâhil edilme ve dışlanma kriterlerine göre sağlık bilimleri fakültesindeki 197 gönüllü öğrenci değerlendirildi. Değerlendirmede disfonksiyon gelişme riski TME ile ilişkilitetikleyici faktörlerin varlığı, psikolojik durumu Beck Depresyon Ölçeği, yaşam kalitesi SF-36 ve ağrıya dayalı disabilite durumu Northwick Park Boyun Ağrısı anketi iledeğerlendirildi. İstatistiksel analizlerde Kruskal Wallis ve Spearman Korelasyon analizinden yararlanıldı.Bulgular Çalışmaya 197 üniversite öğrencisi (yaş ort: 20.79±2.13 yıl) alındı. Öğrencilerin %81.7’sinde TME bozuklukları ile ilgili en az bir semptom taşıdığı saptandı. TMEdisfonksiyon risk düzeyine göre boyun ağrısına bağlı disabilite düzeyi, psikolojik durum ve yaşam kalitesi arasında anlamlı fark olduğu saptandı (bütün değerler içinp<0.01). Çalışmamızda öğrencilerin semptom sayısı ile boyun ağrısına bağlı disabilite şiddeti (r=0.397, p<0.001) ve psikolojik durum arasında (r=0.279, p<0.001) pozitifyönde zayıf korelasyon, SF-36 fiziksel (r=-0.328, p<0.001) ve mental komponentleri arasında (r=-0.305, p<0.001) negatif yönde zayıf korelasyon saptandı.Sonuç Araştırmamıza göre Sağlık Bilimleri Fakültesi öğrencilerinin genel olarak % 80’den fazlası en az bir TME disfonksiyon belirtisi göstermektedir. TME ile ilgili problemriskindeki bu artış eklemin biyomekanik olarak komşu vücut segmentlerini etkiliyor oluşu, disfonksiyonun disabilite, yaşam kalitesi ve psikolojik durumundaki bozulmaile olan yakın ilişkisine bağlanabilir.

Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

1. Robin O, Chiomento A. Prevalence of risk factors for temporomandibular disorders: a retrospective survey from 300 consecutive patients seeking care for TMD in a French dental School J. Stomat. Occ. Med 2010;3(4):179–186
[1] D. I. Stern, P. J. Burke & S. B. Bruns, “The Impact of Electricity on Economic Development: A Macroeconomic Perspective”, EEG State-of-Knowledge Paper Series, 1.1, 2017.
2. Olivo SA, Bravo J, Magee, DJ, Th ie NM, Major PW, Flores-Mir C. Th e association between head and cervical posture and temporomandibular disorders: a systematic review. Journal of Orofacial Pain 2006;20(1).
[2] About the U.S. Electricity System and its Impact on the Environment, https://www.epa.gov/energy/about-us-electricity-system-and-its-impact-environment
3. Scrivani SJ, Keith DA, Kaban LB. Temporomandibular disorders. New England Journal of Medicine 2008;359(25):2693-2705.
[3] Energy Exchange İstanbul, Elektrik Piyasaları, https://seffaflik.epias.com.tr/transparency/
4. Kulekcioglu S, Sivrioglu K, Ozcan O, Parlak M. Eff ectiveness of low‐level laser therapy in temporomandibular disorder. Scandinavian journal of rheumatology 2003;32(2):114-118.
[4] CRO Forum, “Power Blackout Risks, Risk Management Options”, Emerging Risk Initiative – Position Paper, 2011.
5. Hussein SA, Noori AJ, Amen FM. Temporomandibular joint disorders among a group of patients attending the Oral Diagnosis Clinic of the School of Dentistry at University of Sulaimani, Iraq. Sulaimani Dent J 2015;2(1):20-23.
[5] P. Szuromi, B. Jasny, D. Clery, J. Austin, & B. Hanson, “Energy for the long haul,”, 2007.
6. Friedman RP, Erez A, Peretz B, Birenboim-Wilensky R, Winocur E. (). Prevalence of bruxism and temporomandibular disorders among orphans in southeast Uganda: A gender and age comparison. CRANIO® 2018:36(4); 243-249.
[6] V. Lara-Fanego, J.A. Ruiz-Arias, D. Pozo-Vázquez, F.J. Santos-Alamillos, & J. Tovar-Pescador, “Evaluation of the WRF model solar irradiance forecasts in Andalusia (southern Spain),” Solar Energy, 86(8), 2200-2217, 2012.
7. Knutson GA, Jacob M. Possible manifestation of temporomandibular joint dysfunction on chiropractic cervical X-ray studies. Journal of manipulative and physiological therapeutics 1999;22(1):32-37.
[7] IEA, “Global energy technology perspectives” International Energy Agency, OECD Publication Service, OECD, Paris, 2006a.
8. Ware Jr, John E. SF-36 health survey update. Spine 2000;25(24):3130-3139.
[8] B. Espinar, J.L. Aznarte, R. Girard, A.M. Moussa, & G. Kariniotakis, “Photovoltaic Forecasting: A state of the art,” In 5th European PV-Hybrid and Mini-Grid Conference (pp. Pages-250). OTTI-Ostbayerisches Technologie-Transfer-Institut, 2010.
9. Pınar R. SF 36 Yaşam Kalitesi Ölçeği ve kullanımı: sağlık araştırmalarında yaşam kalitesi kavramı. Sendrom 1996;8:109-114.
[9] A. Azadeh, M. Saberi, S.F. Ghaderi, A. Gitiforouz, & V. Ebrahimipour, “Improved estimation of electricity demand function by integration of fuzzy system and data mining approach,” Energy Conversion and Man- agement, 49(8), 2165-2177, 2008.
10. Beck AT, Steer RA, Brown GK. Beck depression inventory-II. San Antonio, 1996;78(2):490- 8.
[10] B. Wang, N.L. Tai, H.Q. Zhai, J. Ye, J.D. Zhu, & L.B. Qi, “A new ARMAX model based on evolutionary algorithm and particle swarm optimization for short-term load forecasting,” Electric Power Systems Research, 78(10), 1679-1685, 2008.
11. Leak AM, Cooper J, Dyer S, Williams KA, Turner-Stokes L, Frank AO. Th e Northwick Park Neck Pain Questionnaire devised to measure neck pain and disability. Rheumatology 1994; 33(5):469-474.
[11] N. Amjady, “Short-term bus load forecasting of power systems by a new hybrid method,” IEEE Transactions on Power Systems, 22(1), 333-341, 2007.
12. Yıldız NÇ, Güneş MŞ. Örgütsel Stresin, Örgütsel Sessizlik Ve Tükenmişlik Üzerine Etkisi: Eczane Çalışanları Üzerinde Bir Araştırma. Uygulamalı Sosyal Bilimler Dergisi 2017;1(1):55.
[12] M. Khadem, “Application of kohonen neural network classifier to short term load forecasting,” In Panel Session on Application of Neural Networks to Short-term Load Forecasting, 1993 IEEE Winter Meeting, 1993.
13. Fillingim RB, Ohrbach R, Greenspan JD, Knott C, Dubner R, Bair E et al. Potential psychosocial risk factors for chronic TMD: descriptive data and empirically identified domains from the OPPERA case-control study. Th e Journal of Pain 2011;12(11):T46-T60.
[13] R.H. Inman, H.T. Pedro, & C.F. Coimbra, “Solar forecasting methods for renewable energy integration,” Progress in energy and combustion science, 39(6), 535-576, 2013.
14. Oakley, M. and A. Vieira, Th e many faces of the genetics contribution to temporomandibular joint disorder. Orthodontics & craniofacial research 2008;11(3):125-135.
[14] H.B. Barlow, “Unsupervised learning,” Neural computation, 1(3), 295-311, 1989.
15. Ohrbach R, Fillingim R B, Mulkey F, Gonzalez Y, Gordon S, Gremillion H, et al. Clinical findings and pain symptoms as potential risk factors for chronic TMD: descriptive data and empirically identified domains from the OPPERA case-control study. Th e Journal of Pain 2011;12(11):T27-T45.
[15] Y. Gala, Á. Fernández, J. Díaz, & J.R. Dorronsoro, “Hybrid machine learning forecasting of solar radiation values,” Neurocomputing, 176, 48-59, 2016.
16. Auerbach SM, Laskin DM, Frantsve LME, Orr T. Depression, pain, exposure to stressful life events, and long-term outcomes in temporomandibular disorder patients. Journal of oral and maxillofacial surgery 2001; 59(6):628-633.
[16] V. Vapnik, “The nature of statistical learning theory,” Springer science & business media, 2013.
17. Kino K, Sugisaki M, Haketa T, Amemori Y, Ishikawa T, Shibuya T, et al. Th e comparison between pains, diff iculties in function, and associating factors of patients in subtypes of temporomandibular disorders. Journal of Oral Rehabilitation 2005;32(5):315-325.
[17] N. Sharma, P. Sharma, D. Irwin, & P. Shenoy, “Predicting solar generation from weather forecasts using machine learning,” In 2011 IEEE international conference on smart grid communications (SmartGridComm) (pp. 528-533). IEEE, 2011.
18. Meldolesi GN, Picardi A, Accivile E, di Francia RT, Biondi M. Personality and psychopathology in patients with temporomandibular joint pain-dysfunction syndrome. Psychotherapy and psychosomatics 2000;69(6);322-328.
[18] J. Shi, W.J. Lee, Y. Liu, Y. Yang, & P. Wang, “Forecasting power output of photovoltaic systems based on weather classification and support vector machines.” IEEE Transactions on Industry Applications, 48(3), 1064-1069, 2012.
19. Vimpari SS, Knuuttila ML, Sakki TK, Kivela S L. Depressive symptoms associated with symptoms of the temporomandibular joint pain and dysfunction syndrome. Psychosomatic medicine 1995;57(5):439-444.
[19] L. Breiman, “Random forests,” Machine learning, 45(1), 5-32, 2001.
20. Ciancaglini R, Testa M, Radaelli G. Association of neck pain with symptoms of temporomandibular dysfunction in the general adult population. Scandinavian journal of rehabilitation medicine 1999;31(1):17-22.
[20] J. Huertas Tato, & M. Centeno Brito, “Using Smart Persistence and Random Forests to Predict Photovoltaic Energy Production,” Energies, 12(1), 100, 2019.
21. Resende CMBMD, Alves ACDM, Coelho LT, Alchieri JC, Roncalli, Â, Barbosa GAS. Quality of life and general health in patients with temporomandibular disorders. Brazilian Oral Research 2013;27(2):116-121.
[21] C. Voyant, C. Paoli, M. Muselli, & M.L. Nivet, “Multi-horizon solar radiation forecasting for Mediterranean locations using time series models,” Renewable and Sustainable Energy Reviews, 28, 44-52, 2013.
22. Oliveira AS. Evaluation of quality of life and pain in Temporomandibular Disorders (TMD). Braz J Oral Sci 2005;4:646-50.
[22] R. Tibshirani, “Regression shrinkage and selection via the lasso,” Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267-288, 1996.
[23] J. Luo, T. Hong, & S.C. Fang, “Robust Regression Models for Load Forecasting,” IEEE Transactions on Smart Grid, 2018.
[24] M.Y. Ishik, T. Göze, İ. Özcan, V.Ç. Güngör, & Z. Aydın, “Short term electricity load forecasting: A case study of electric utility market in Turkey,” In 2015 3rd International Istanbul Smart Grid Congress and Fair (ICSG) (pp. 1-5). IEEE, 2015.
[25] W. Tan and B. Khoshnevis, “Integration of process planning and scheduling— a review,” Journal of Intelligent Manufacturing, vol. 11, no. 1, pp. 51–63, 2000.
[26] S. Ai, A. Chakravorty, and C. Rong. "Household Energy Consumption Prediction using Evolutionary Ensemble Neural Network." Engineering Assets and Public Infrastructures in the Age of Digitalization. Springer, Cham, 2020. 923-931.
[27] K. Bot, A. Ruano, and M.G. Ruano. "Forecasting electricity consumption in residential buildings for home energy management systems." International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems. Springer, Cham, 2020.
[28] S. Rahman, M.G. Rabiul Alam, and M. Mahbubur Rahman. "Deep Learning based Ensemble Method for Household Energy Demand Forecasting of Smart Home." 2019 22nd International Conference on Computer and Information Technology (ICCIT). IEEE, 2019.
[29] T. Panapongpakorn, and D. Banjerdpongchai. "Short-Term Load Forecast for Energy Management System Using Neural Networks with Mutual Information Method of Input Selection." 2019 SICE International Symposium on Control Systems (SICE ISCS). IEEE, 2019.
[30] S. Chan, I. Oktavianti, and V. Puspita. "A deep learning cnn and ai-tuned svm for electricity consumption forecasting: Multivariate time series data." 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). IEEE, 2019.
[31] M. Krishnan, Y.M. Jung, and S. Yun. "Prediction of Energy Demand in Smart Grid using Hybrid Approach." 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC). IEEE, 2020.
[32] H. S. Hippert, C. E. Pedreira, R. C. Souza, “Neural networks for short-term load forecasting: A review and evaluation”, IEEE Transactions on power systems, 16 (1) 44–55, 2001.

APA	SÜTÇÜ M, TANHAN A, Şahin K, Yıldız Ozer A, Koloğlu Y, demirbüken i, Çelikel M, POLAT M, GÜLBAHAR İ (2022). Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. , 91 - 104. 10.16984/saufenbilder.982639
Chicago	SÜTÇÜ MUHAMMED,TANHAN ABDURRAHMAN,Şahin Kübra Nur,Yıldız Ozer Aysel,Koloğlu Yunus,demirbüken ilkşan,Çelikel Mevlüt Emirhan,POLAT MINE GÜLDEN,GÜLBAHAR İBRAHİM TÜMAY Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. (2022): 91 - 104. 10.16984/saufenbilder.982639
MLA	SÜTÇÜ MUHAMMED,TANHAN ABDURRAHMAN,Şahin Kübra Nur,Yıldız Ozer Aysel,Koloğlu Yunus,demirbüken ilkşan,Çelikel Mevlüt Emirhan,POLAT MINE GÜLDEN,GÜLBAHAR İBRAHİM TÜMAY Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. , 2022, ss.91 - 104. 10.16984/saufenbilder.982639
AMA	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. . 2022; 91 - 104. 10.16984/saufenbilder.982639
Vancouver	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. . 2022; 91 - 104. 10.16984/saufenbilder.982639
IEEE	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ "Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models." , ss.91 - 104, 2022. 10.16984/saufenbilder.982639
ISNAD	SÜTÇÜ, MUHAMMED vd. "Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models". (2022), 91-104. https://doi.org/10.16984/saufenbilder.982639

APA	SÜTÇÜ M, TANHAN A, Şahin K, Yıldız Ozer A, Koloğlu Y, demirbüken i, Çelikel M, POLAT M, GÜLBAHAR İ (2022). Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 9(2), 91 - 104. 10.16984/saufenbilder.982639
Chicago	SÜTÇÜ MUHAMMED,TANHAN ABDURRAHMAN,Şahin Kübra Nur,Yıldız Ozer Aysel,Koloğlu Yunus,demirbüken ilkşan,Çelikel Mevlüt Emirhan,POLAT MINE GÜLDEN,GÜLBAHAR İBRAHİM TÜMAY Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi 9, no.2 (2022): 91 - 104. 10.16984/saufenbilder.982639
MLA	SÜTÇÜ MUHAMMED,TANHAN ABDURRAHMAN,Şahin Kübra Nur,Yıldız Ozer Aysel,Koloğlu Yunus,demirbüken ilkşan,Çelikel Mevlüt Emirhan,POLAT MINE GÜLDEN,GÜLBAHAR İBRAHİM TÜMAY Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol.9, no.2, 2022, ss.91 - 104. 10.16984/saufenbilder.982639
AMA	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi. 2022; 9(2): 91 - 104. 10.16984/saufenbilder.982639
Vancouver	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi. 2022; 9(2): 91 - 104. 10.16984/saufenbilder.982639
IEEE	SÜTÇÜ M,TANHAN A,Şahin K,Yıldız Ozer A,Koloğlu Y,demirbüken i,Çelikel M,POLAT M,GÜLBAHAR İ "Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models." Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 9, ss.91 - 104, 2022. 10.16984/saufenbilder.982639
ISNAD	SÜTÇÜ, MUHAMMED vd. "Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models". Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi 9/2 (2022), 91-104. https://doi.org/10.16984/saufenbilder.982639