# Forecasting OPEC Electricity Generation Based on Elman Network Trained by Cuckoo Search Algorithm

## Abstract

All over the world, energy is vitally important because it affects life-standard economy, and social growth. Electricity is one of the main significant forms of energy which is usually needed to be generated and cannot be stored physically. It was the main goal to generate the required electricity to meet a future need in previous studies. To maintain the level of electricity needed constantly, a good system needs to be designed for avoiding waste or shortage. This paper proposes an alternative topology of neural network which is known as Elman network. In the case of Elman networks (ENs), majority techniques only identify topologies in which neurons are connected to each other from hidden to input layer. However, training algorithm of Elman network has a number of disadvantages, like network stagnation and getting stuck in a minimum and low local speed of convergence. This study suggests Cuckoo search algorithm (CS) to enhance training time of EN for high precision and fast convergence. Performance of Cuckoo search Elman (CSElman) is compared to artificial bee colony (ABC) and with similar hybrid techniques. Simulation results are displayed that prove the proposed CSElman is better than the other algorithms in this research with respect to accuracy and the speed of convergence.

## Keywords

Slow convergence Local minima Cuckoo search algorithm Artificial bee colony Elman network## Notes

### Acknowledgements

The researchers would like to say special thanks to “University of Agriculture Peshawar Pakistan for supporting this project.”

## References

- 1.Ozoh P et al (2014) A comparative analysis of techniques for forecasting electricity consumption. Int J Comput Appl 88(15)CrossRefGoogle Scholar
- 2.Günay ME (2016) Forecastingannualgrosselectricitydemandbyartificial neural networks using predicted values of socio-economic indicators and climatic conditions: case of Turkey. Energy Policy 2016(90):92–101CrossRefGoogle Scholar
- 3.Chujai P, Kerdprasop N, Kerdprasop K (2013) Time series analysis of household electric consumption with ARIMA and ARMA models. In Proceedings IMECS conference Hong Kong (2013)Google Scholar
- 4.Askarzadeh A (2014) Bird mating optimizer: an optimization algorithm inspired by bird mating strategies. Commun Nonlinear Sci Numer Simul 19(4):1213–1228MathSciNetCrossRefGoogle Scholar
- 5.Kucukali S, Baris K (2010) Turkey’s short-term gross annual electricity demand forecast by fuzzy logic approach. Energy Policy 38(5):2438–2445CrossRefGoogle Scholar
- 6.Zahedi B, Norum LE (2013) Modeling and simulation of all-electric ships with low-voltage DC hybrid power systems. IEEE Trans Power Electron 28(10):4525–4537CrossRefGoogle Scholar
- 7.Nawaz S, Iqbal N, Anwar S (2014) Modelling electricity demand using the STAR (Smooth Transition Auto-Regressive) model in Pakistan. Energy 78:535–542CrossRefGoogle Scholar
- 8.Kialashaki A, Reisel JR (2014) Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States. Energy 76:749–760CrossRefGoogle Scholar
- 9.Kavaklioglu K (2011) Modeling and prediction of Turkey’s electricity consumption using support vector regression. Appl Energy 88(1):368–375CrossRefGoogle Scholar
- 10.Zahedi G et al (2013) Electricity demand estimation using an adaptive neuro-fuzzy network: a case study from the Ontario province–Canada. Energy 49:323–328CrossRefGoogle Scholar
- 11.Nawi NM, Khan A, Rehman MZ (2013) A new cuckoo search based levenberg-marquardt (cslm) algorithm. In Computational science and its applications–ICCSA 2013, Springer, pp 438–451Google Scholar
- 12.Nawi NM, Khan A, Rehman MZ (2014) A new optimized cuckoo search recurrent neural network (CSRNN) Algorithm. In the 8th international conference on robotic, vision, signal processing and power applications, Springer, 2014Google Scholar
- 13.Nawi NM, Khan A, Rehman M (2014) CSLMEN: a new optimized method for training Levenberg Marquardt Elman network based cuckoo search algorithm, 2014Google Scholar
- 14.Nawi NM et al (2015) Weight optimization in recurrent neural networks with hybrid metaheuristic Cuckoo search techniques for data classification. Math Prob Eng 501:868375Google Scholar
- 15.Aziz M, Hamed HNA, Shamsuddin SMH (2008) Augmentation of elman recurrent network learning with particle swarm optimization. Modeling and simulation, 2008. AICMS 08. In: Second Asia international conference on, 2008: pp 625–630Google Scholar
- 16.Elman JL (1990) Finding structure in time. Cognitive Sci 14(2):179–211CrossRefGoogle Scholar
- 17.Pasila F, Lesmana T, Ferdinando H Elman neural network application with accelerated LMA training for east java-bali electrical load time series data forecastingGoogle Scholar
- 18.Toha SF, Tokhi MO (2008) MLP and Elman recurrent neural network modelling for the TRMS. In: 7th IEEE international conference on cybernetic intelligent systems CIS 2008, pp 1–6Google Scholar
- 19.Xin-She Y, Deb S (2009) Cuckoo search via levy flights. In: World congress on nature and biologically inspired computing, 2009, pp 210–214Google Scholar
- 20.Yang X.-S (2010) Nature-inspired metaheuristic algorithms, Luniver PressGoogle Scholar
- 21.Tuba M, Subotic M, Stanarevic N (2011) Modified cuckoo search algorithm for unconstrained optimization problems. In: Proceedings of the 5th European conference on European computing conference, 2011, pp 263–268Google Scholar
- 22.Rajabioun R (2011) Cuckoo optimization algorithm. Appl Soft Comput 11(8):5508–5518CrossRefGoogle Scholar
- 23.Valian E, Mohanna S, Tavakoli S (2011) Improved cuckoo search algorithm for feedforward neural network training. Int J Artif Intell Appl 2(3):36Google Scholar
- 24.Walton S et al (2011) Modified cuckoo search: a new gradient free optimisation algorithm. Chaos, Solitons Fractals 44(9):710–718CrossRefGoogle Scholar
- 25.Chiroma H et al (2016) A review on artificial intelligence methodologies for the forecasting of crude oil price. Intell Autom Soft Comput, pp 1–14Google Scholar