An evaluation of the artificial neural network based on the estimation of daily average global solar radiation in the city of Surabaya

Abstract

The estimation of the daily average global solar radiation is important since it increases the cost efficiency of solar power plant, especially in developing countries. Therefore, this study aims at developing a multi layer perceptron artificial neural network (ANN) to estimate the solar radiation in the city of Surabaya. To guide the study, seven (7) available meteorological parameters and the number of the month was applied as the input of network. The ANN was trained using five-years data of 2011-2015. Furthermore, the model was validated by calculating the mean average percentage error (MAPE) of the estimation for the years of 2016-2019. The results confirm that the aforementioned model is feasible to generate the estimation of daily average global solar radiation in Surabaya, indicated by MAPE of less than 15% for all testing years.

Distributed memory of neural networks and the problem of the intelligence`s essence

“…Further, with a large number of characters in the sequence, it is permissible to use the Stirling as shown in (5).…”

“…Until now, there are no algorithms that would allow calculating the weight coefficients of a specific ANNs, based on the requirements connected with the solving problem. Most of the results related to ANNs are in fact the results of various computer experiments [5], [6].…”

“…Namely, the question of how many images a neural network can recognize remains largely open [12], [13]. More precisely, the statistical properties of neural networks are still insufficiently studied, which, among other things, is since the overwhelming majority of the results obtained in this area are de facto an interpretation of computer experiments [5], [6]. Our proposed approach, which uses an analogy between neural networks and error-correcting coding algorithms, allows us to solve this problem.…”

Solving the trapezoidal fuzzy assignment problem using the novel Dhouib-Matrix-AP1 heuristic

“…Various methods have been developed in order to optimize the assignment problem, such as the ant colony optimization [1]- [14], the tabu search method [15]- [20], the red deer algorithm [21]- [28], the genetic algorithm [29]- [35], the neural network [36]- [39], the linear programming [37]- [41] and the Hungarian algorithm [42]- [47]. In this field, we invented a new column row heuristic entitled Dhouib-Matrix-AP1 (DM-AP1) in order to solve the assignment problem in certain environments [48].…”

“…Figure 10 depicts the generated solution using Python programming language. The total trapezoidal fuzzy assignment cost is 𝐹 ̃= (17,22,37,49). This solution is computed by: 𝐹 ̃= (3,4,6,9) + (2,3,5,7) + (6,7,9,10) + (4,5,7,9) + (2,3,10,14) = (17,22,37,49) Thus, for the decision maker, the total allocation cost will lie at [56] with a 100% level of satisfaction (lying at [61].…”