Forecasting Hoabinh Reservoir’s Incoming Flow: An Application of Neural Networks with the Cuckoo Search Algorithm

Abstract

The accuracy of reservoir flow forecasting has the most significant influence on the assurance of stability and annual operations of hydro-constructions. For instance, accurate forecasting on the ebb and flow of Vietnam's Hoabinh Reservoir can aid in the preparation and prevention of lowland flooding and drought, as well as regulating electric energy. This raises the need to propose a model that accurately forecasts the incoming flow of the Hoabinh Reservoir. In this study, a solution to this problem based on neural network with the Cuckoo Search (CS) algorithm is presented. In particular, we used hydrographic data and predicted total incoming flows of the Hoabinh Reservoir over a period of 10 days. The Cuckoo Search algorithm was utilized to train the feedforward neural network (FNN) for prediction. The algorithm optimized the weights between layers and biases of the neuron network. Different forecasting models for the three scenarios were developed. The constructed models have shown high forecasting performance based on the performance indices calculated. These results were also compared with those obtained from the neural networks trained by the particle swarm optimization (PSO) and back-propagation (BP), indicating that the proposed approach performed more effectively. Based on the experimental results, the scenario using the rainfall and the flow as input yielded the highest forecasting accuracy when compared with other scenarios. The performance

Meteorological Drought Analysis Using Artificial Neural Networks for Bursa City, Turkey

“…R and MSE values calculated were in the acceptable range (Sinha and Das, 2015;Yonar and Yalili Kilic, 2014). MSE values in this study were found smaller than some water quality studies (Chen et al, 2014). This showed that hydrological and meteorological parameters were modeled well with ANN (Daliakopoulos and …”

“…The output y at a linear output node can be calculated as Equation 9: where R is the number of inputs, z is the number of hidden neurons, ωi.j(1) is the first layer weight between the input j and the i th hidden neuron, ω1,i(2) is the second layer weight between the i th hidden neuron and output neuron, bi(1) is a biased weight for the ith hidden neuron and b1(2) is a biased weight for the output neuron (Chen et al, 2014) The learning algorithms using in ANN are heuristics, partial Newton methods, matched gradient methods and Levenberg Marquardt methods. In this study feed forward neural network structure was used and Levenberg Marquardt training algorithm supervised training algorithms was preferred for training.…”

“…The Pearson correlation coefficient is one of the most commonly used performance in selecting proper inputs for the ANN (Chen et al, 2014 (Eq.13) (Eq.14)…”

Deep Learning: Ứng Dụng Cho Dự Báo Lưu Lượng Nước Đến Hồ Chứa Hòa Bình

“…Các số liệu quan trắc mưa, lưu lượng Q đo đạc được của ngày hiện tại và những ngày trước đó đều được xem xét và đưa vào mô hình. Việc lựa chọn các tiêu chí cần kinh nghiệm chuyên gia và thử nghiệm các kịch bản để lựa chọn, trong nghiên cứu này chúng tôi sử dụng kịch bản tốt nhất được trình bày trong nghiên cứu của Chen và đồng nghiệp [10].…”

Development of a gas detector by using ultrasonic sensor integrated with artificial neural network

“…ANN has been applied for various application such as identification, infer a function from observations, forecasting, spatial data analysis, etc. [15][16][17][18].…”