Smart Trends in Computing and Communications pp 267-275 | Cite as
Load and Renewable Energy Forecasting for System Modelling, an Effort in Reducing Renewable Energy Curtailment
Abstract
Every day, humanity is achieving a big feat in the field of technology, and in doing so the most fundamental thing that comes to them as aid, is energy. With the invention of generators, fossil fuels have been integrated for the generation of this energy. But this process gave breeding ground for the carbon footprints. Hence, the traditional means of energy sources like wind, solar, hydro, etc. were integrated extensively all around the world to curb this deterioration of the environment. These sources have indeed helped in mitigating the problem of increasing carbon footprint. But even these Renewable Energy (RE) sources cannot be considered as the impeccable source of energy, as even these sources have got some issues related to the sustainability and the usability. The problem of curtailment of these variable sources of energy has been there since the rise in penetration of these sources in the world market. Due to uncertainty in the generation of power from renewables, various problems related to grid integration appear. Hence to maintain the real time balance between load and generation, some of the RE is wasted which is called as the RE curtailment. This paper, hence majorly focuses on reducing such power losses due to this imbalance in the power management system. At first, the literature survey was conducted on the subject, to get aware of the problem and its severity, and various system strategies earlier used to solve it. In this paper, the conception of day-ahead RE power supply and day-ahead Demand forecasting to ensure the day-ahead planning of the power demand–supply management was integrated. These forecasting models were designed using the concepts of Artificial Neural Network. These forecasted entities were used to schedule a day-ahead power demand and supply strategies. In case of system imbalance, i.e. during excess supply or excess demand the utilities can be maintained using day-ahead power transactions with electricity market. Practically, these forecasting methods may also have some modelling errors, which may affect the accuracy in the balance of the system. To mitigate this problem of system inaccuracy the concept of two-settlement strategy to balance the day-ahead market and the real time market was used.
Keywords
Renewable energy curtailment Load forecasting Renewable energy forecasting Artificial neural network Grid balancingReferences
- 1.Ming, Z., Kun, Z., Jun, D.: Overall review of China’s wind power industry: status quo, existing problems and perspective for future development. Int. J. Electr. Power Energy Syst. 76, 768–774 (2007)Google Scholar
- 2.Wind and Solar energy curtailment: Experience and practices in the United States by National Renewable Energy Laboratory (NREL)Google Scholar
- 3.Golden, R., Paulos, B.: Curtailment of renewable energy in California and beyond. Electr. J. 28(6), 36–50 (2015)CrossRefGoogle Scholar
- 4.Li, C., Shi, H., Cao, Y., Wang, J., Kuang, Y., Tan, Y., Wei, J.: Comprehensive review of RE curtailment and avoidance: a specific example in China. Renew. Sustain. Energy Rev. 41, 1067–1079 (2015)CrossRefGoogle Scholar
- 5.Debnath, K.B., Mourshed, M.: Forecasting methods in energy planning models. Renew. and Sustain. Energy Rev. 88, 297–325 (2018)CrossRefGoogle Scholar
- 6.Hernández, L., Baladrón, C., Aguiar, J.M. Carro, B., Sánchez-Esguevillas, A.: Improved short-term load forecasting based on two-stage predictions with artificial neural networks in a microgrid environment, Energies 6, 4489–4507 (2013)CrossRefGoogle Scholar
- 7.Hsiao, Y.-H.: Household electricity demand forecast based on context information and user daily schedule analysis from meter data. IEEE Trans. Ind. Inform. 11(1), 33–43 (2015)MathSciNetCrossRefGoogle Scholar
- 8.Marvuglia, A., Messineo, A.: Using recurrent artificial neural networks to forecast household electricity consumption. Energy Procedia 14, 45–55 (2012)CrossRefGoogle Scholar
- 9.Twanabasu, S.R., Bremdal, B.A.: Load forecasting in a smart grid-oriented building. In: 22nd International Conference and Exhibition on Electricity Distribution (CIRED 2013), Institution of Engineering and Technology (2013)Google Scholar
- 10.Custer, C., Rezgui, Y., Mourshed, M.: Electrical load forecasting model: a critical systematic review. Sustain. Cities Soc. 35 (2017)Google Scholar
- 11.Pradhan, R.: Z score estimation for banking sector. Int. J. Trade Econ. Financ. 5(6), 516–520 (2014)Google Scholar
- 12.Mustaffa, Z., Yusof, Y.: A comparison of normalization techniques in predicting dengue outbreak. In: International Conference on Business and Economic Research, vol. 1, pp. 345–349 (2010)Google Scholar
- 13.Karsoliya, S.: Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. Int. J. Eng. Trends Technol. 3(6), 714–717 (2012)Google Scholar
- 14.Panchal, F.S., Panchal, M.: Review on methods of selecting number of hidden nodes in artificial neural network. Int. J. Comput. Sci. Mob. Comput. 3(11), 455–464 (2014)Google Scholar
- 15.Ghofrani, M., Alolayan, M.: Time series and renewable energy forecasting. IntechOpen (2017)Google Scholar
- 16.Dobbs, Alex: Short-Term Solar Forecasting Performance of Popular Machine Learning Algorithms. National Renewable Energy Laboratory Golden, Colorado (2017)Google Scholar
- 17.Tarigan, J., Diedan, R., Suryana, Y.: Plate recognition using backpropagation neural network and genetic algorithm. Procedia Comput. Sci. 116, 365–372 (2017)CrossRefGoogle Scholar
- 18.Counsell, L.K., Evans, L.T.: Day ahead electricity markets: is there a place for a day ahead market in NZEM?. New Zealand Institute for the Study of Competition and RegulationsGoogle Scholar
- 19.Veit, Daniel J., Weidlich, Anke, Yao, Jian, Oren, Shmuel S.: Simulating the dynamics in two-settlement electricity markets via an agent-based approach. Int. J. Manag. Sci. Eng. Manag. 1(2), 83–97 (2006)Google Scholar