GHI
MARTIN SARMIENTO
2025-12-01
1 Configuración y Carga de Datos
##### UNIVERSIDAD CENTRAL DEL ECUADOR #####
#### AUTOR: MARTIN SARMIENTO ####
### CARRERA: INGENIERÍA EN PETRÓLEOS #####
#### VARIABLE GHI ####
## DATASET ##
setwd("~/R/GHI")
# Cargar dataset
Datos <- read.csv("DataSet_Mundial_Final.csv", sep = ";", dec = ",", fileEncoding = "latin1")
# Estructura de los datos
str(Datos)## 'data.frame': 58978 obs. of 29 variables:
## $ ï..OBJECTID : int 2 3 4 5 6 7 8 9 10 11 ...
## $ code : chr "00001-AFG-P" "00002-AFG-P" "00003-AFG-P" "00004-AFG-P" ...
## $ plant_name : chr "Badghis Solar Power Plant" "Balkh solar farm" "Behsood solar farm" "Dab Pal 4 solar farm" ...
## $ country : chr "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
## $ operational_status : chr "cancelled - inferred 4 y" "cancelled - inferred 4 y" "cancelled - inferred 4 y" "shelved - inferred 2 y" ...
## $ longitude : num 62.9 67.1 70.4 66.2 65.7 ...
## $ latitude : num 35.1 36.7 34.4 33.8 31.7 ...
## $ elevation : int 918 359 629 2288 1060 1060 1392 398 410 1012 ...
## $ area : num 6.74 10.72 487.73 111.8 1929.96 ...
## $ size : chr "Small" "Small" "Small" "Small" ...
## $ slope : num 7.38 0.49 1.1 6.16 1.23 ...
## $ slope_type : chr "Moderado" "Plano o casi plano" "Plano o casi plano" "Moderado" ...
## $ curvature : num -0.024 0 0 0.045 -0.005 -0.005 -0.015 0 0 -0.009 ...
## $ curvature_type : chr "Superficies cóncavas / Valles" "Superficies planas o intermedias" "Superficies planas o intermedias" "Superficies convexas / Crestas" ...
## $ aspect : num 96.8 358.5 36.2 305.8 248.4 ...
## $ aspect_type : chr "East" "North" "Northeast" "Northwest" ...
## $ dist_to_road : num 7037.1 92.7 112.1 1705.3 115.8 ...
## $ ambient_temperature : num 14.4 17.88 21.32 8.86 19.64 ...
## $ ghi : num 5.82 5.58 5.8 6.75 6.62 ...
## $ humidity : num 47.7 42.3 36.4 37.3 24.2 ...
## $ wind_speed : num 0.039 0.954 0.234 0.943 0.37 ...
## $ wind_direction : num 187.5 207.4 255.6 160.3 97.7 ...
## $ dt_wind : chr "South" "Southwest" "West" "South" ...
## $ solar_aptitude : num 0.72 0.635 0.685 0.659 0.819 0.819 0.818 0.642 0.63 0.374 ...
## $ solar_aptitude_rounded: int 7 6 7 7 8 8 8 6 6 4 ...
## $ solar_aptittude_class : chr "Alta" "Alta" "Alta" "Alta" ...
## $ capacity : num 32 40 60 3000 100 100 36 50 25 100 ...
## $ optimal_tilt : num 30 31 31.1 33 31 ...
## $ pv_potential : num 4.61 4.41 4.57 5.42 5.17 ...##
## Adjuntando el paquete: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union2 Cálculo de Intervalos y Frecuencias
# Extraer variable
Variable <- na.omit(Datos$ghi)
N <- length(Variable)
# CÁLCULO LÍMITES DECIMALES
min_dec <- min(Variable)
max_dec <- max(Variable)
k_dec <- floor(1 + 3.322 * log10(N))
rango_dec <- max(Variable) - min(Variable)
amplitud_dec <- rango_dec / k_dec
# Cortes exactos
cortes_dec <- seq(min(Variable), max(Variable), length.out = k_dec + 1)
cortes_dec[length(cortes_dec)] <- max(Variable) + 0.0001
# Frecuencias
inter_dec <- cut(Variable, breaks = cortes_dec, include.lowest = TRUE, right = FALSE)
ni_dec <- as.vector(table(inter_dec))
# CÁLCULOS MATEMÁTICOS
hi_dec <- (ni_dec / N) * 100
Ni_asc_dec <- cumsum(ni_dec)
Hi_asc_dec <- cumsum(hi_dec)
Ni_desc_dec <- rev(cumsum(rev(ni_dec)))
Hi_desc_dec <- rev(cumsum(rev(hi_dec)))
# Dataframe Decimal
TDF_Decimal <- data.frame(
Li = cortes_dec[1:k_dec],
Ls = cortes_dec[2:(k_dec+1)],
MC = (cortes_dec[1:k_dec] + cortes_dec[2:(k_dec+1)]) / 2,
ni = ni_dec,
hi = hi_dec,
Ni_asc = Ni_asc_dec,
Ni_desc = Ni_desc_dec,
Hi_asc = Hi_asc_dec,
Hi_desc = Hi_desc_dec)
# CÁLCULO LÍMITES ENTEROS (CORREGIDO PARA GHI)
BASE <- 1
min_int <- floor(min(Variable) / BASE) * BASE
max_int <- ceiling(max(Variable) / BASE) * BASE
k_int_sug <- floor(1 + 3.322 * log10(N))
Rango_int <- max_int - min_int
# Calculamos amplitud entera
Amplitud_int <- ceiling(Rango_int / k_int_sug)
if(Amplitud_int == 0) Amplitud_int <- 1
# Generamos la secuencia de cortes
cortes_int <- seq(from = min_int, by = Amplitud_int, length.out = k_int_sug + 1)
if(max(cortes_int) < max(Variable)) {
cortes_int <- c(cortes_int, max(cortes_int) + Amplitud_int)
}
while(length(cortes_int) > 2 && cortes_int[length(cortes_int)-1] >= max(Variable)) {
cortes_int <- cortes_int[-length(cortes_int)]
}
# Definimos los límites
K_real <- length(cortes_int) - 1
lim_inf_int <- cortes_int[1:K_real]
lim_sup_int <- cortes_int[2:(K_real+1)]
# Frecuencias
inter_int <- cut(Variable, breaks = cortes_int, include.lowest = TRUE, right = FALSE)
ni_int <- as.vector(table(inter_int))
# CÁLCULOS MATEMÁTICOS
hi_int <- (ni_int / N) * 100
Ni_asc_int <- cumsum(ni_int)
Hi_asc_int <- cumsum(hi_int)
Ni_desc_int <- rev(cumsum(rev(ni_int)))
Hi_desc_int <- rev(cumsum(rev(hi_int)))
# Dataframe Entero
TDF_Enteros <- data.frame(
Li = lim_inf_int,
Ls = lim_sup_int,
MC = (lim_inf_int + lim_sup_int) / 2,
ni = ni_int,
hi = hi_int,
Ni_asc = Ni_asc_int,
Ni_desc = Ni_desc_int,
Hi_asc = Hi_asc_int,
Hi_desc = Hi_desc_int)3 Tabla de Distribución de Frecuencias
3.1 Tabla con Límites Decimales
# Crear Dataframe
TDF_Dec_Final <- data.frame(
Li = as.character(round(TDF_Decimal$Li, 2)),
Ls = as.character(round(TDF_Decimal$Ls, 2)),
MC = as.character(round(TDF_Decimal$MC, 2)),
ni = as.character(TDF_Decimal$ni),
hi = as.character(round(TDF_Decimal$hi, 2)),
Ni_asc = as.character(TDF_Decimal$Ni_asc),
Ni_desc = as.character(TDF_Decimal$Ni_desc),
Hi_asc = as.character(round(TDF_Decimal$Hi_asc, 2)),
Hi_desc = as.character(round(TDF_Decimal$Hi_desc, 2))
)
# Calcular Totales
totales_dec <- c("TOTAL", "-", "-", sum(TDF_Decimal$ni), round(sum(TDF_Decimal$hi), 2), "-", "-", "-", "-")
TDF_Dec_Final <- rbind(TDF_Dec_Final, totales_dec)
# Generar GT
TDF_Dec_Final %>%
gt() %>%
tab_header(title = md("**Tabla N°1 de Distribución de Frecuencias de GHI (kWh/m²) de las Plantas Solares**")) %>%
cols_label(
Li = "Lim. Inf",
Ls = "Lim. Sup",
MC = "Marca Clase",
ni = "Frec. Abs (ni)",
hi = "Frec. Rel (%)",
Ni_asc = "Ni (Asc)",
Ni_desc = "Ni (Desc)",
Hi_asc = "Hi Asc (%)",
Hi_desc = "Hi Desc (%)"
) %>%
cols_align(align = "center", columns = everything()) %>%
tab_options(heading.title.font.size = px(14), column_labels.background.color = "#F0F0F0")| Tabla N°1 de Distribución de Frecuencias de GHI (kWh/m²) de las Plantas Solares | ||||||||
| Lim. Inf | Lim. Sup | Marca Clase | Frec. Abs (ni) | Frec. Rel (%) | Ni (Asc) | Ni (Desc) | Hi Asc (%) | Hi Desc (%) |
|---|---|---|---|---|---|---|---|---|
| 0 | 0.5 | 0.25 | 3 | 0.01 | 3 | 58978 | 0.01 | 100 |
| 0.5 | 1.01 | 0.75 | 0 | 0 | 3 | 58975 | 0.01 | 99.99 |
| 1.01 | 1.51 | 1.26 | 0 | 0 | 3 | 58975 | 0.01 | 99.99 |
| 1.51 | 2.01 | 1.76 | 0 | 0 | 3 | 58975 | 0.01 | 99.99 |
| 2.01 | 2.52 | 2.26 | 0 | 0 | 3 | 58975 | 0.01 | 99.99 |
| 2.52 | 3.02 | 2.77 | 219 | 0.37 | 222 | 58975 | 0.38 | 99.99 |
| 3.02 | 3.52 | 3.27 | 6150 | 10.43 | 6372 | 58756 | 10.8 | 99.62 |
| 3.52 | 4.02 | 3.77 | 13445 | 22.8 | 19817 | 52606 | 33.6 | 89.2 |
| 4.02 | 4.53 | 4.28 | 11774 | 19.96 | 31591 | 39161 | 53.56 | 66.4 |
| 4.53 | 5.03 | 4.78 | 9885 | 16.76 | 41476 | 27387 | 70.32 | 46.44 |
| 5.03 | 5.53 | 5.28 | 7675 | 13.01 | 49151 | 17502 | 83.34 | 29.68 |
| 5.53 | 6.04 | 5.78 | 7134 | 12.1 | 56285 | 9827 | 95.43 | 16.66 |
| 6.04 | 6.54 | 6.29 | 1938 | 3.29 | 58223 | 2693 | 98.72 | 4.57 |
| 6.54 | 7.04 | 6.79 | 523 | 0.89 | 58746 | 755 | 99.61 | 1.28 |
| 7.04 | 7.54 | 7.29 | 165 | 0.28 | 58911 | 232 | 99.89 | 0.39 |
| 7.54 | 8.05 | 7.8 | 67 | 0.11 | 58978 | 67 | 100 | 0.11 |
| TOTAL | - | - | 58978 | 100 | - | - | - | - |
3.2 Tabla con Límites Enteros
# Crear Dataframe
TDF_Int_Final <- data.frame(
Li = as.character(TDF_Enteros$Li),
Ls = as.character(TDF_Enteros$Ls),
MC = as.character(TDF_Enteros$MC),
ni = as.character(TDF_Enteros$ni),
hi = as.character(round(TDF_Enteros$hi, 2)),
Ni_asc = as.character(TDF_Enteros$Ni_asc),
Ni_desc = as.character(TDF_Enteros$Ni_desc),
Hi_asc = as.character(round(TDF_Enteros$Hi_asc, 2)),
Hi_desc = as.character(round(TDF_Enteros$Hi_desc, 2))
)
# Calcular Totales
totales_int <- c("TOTAL", "-", "-", sum(TDF_Enteros$ni), round(sum(TDF_Enteros$hi), 2), "-", "-", "-", "-")
TDF_Int_Final <- rbind(TDF_Int_Final, totales_int)
# Generar GT
TDF_Int_Final %>%
gt() %>%
tab_header(title = md("**Tabla N°2 de Distribución de Frecuencias de GHI (kWh/m²) de las Plantas Solares**")) %>%
cols_label(
Li = "Lim. Inf",
Ls = "Lim. Sup",
MC = "Marca Clase",
ni = "Frec. Abs (ni)",
hi = "Frec. Rel (%)",
Ni_asc = "Ni (Asc)",
Ni_desc = "Ni (Desc)",
Hi_asc = "Hi Asc (%)",
Hi_desc = "Hi Desc (%)"
) %>%
cols_align(align = "center", columns = everything()) %>%
tab_options(heading.title.font.size = px(14), column_labels.background.color = "#F0F0F0")| Tabla N°2 de Distribución de Frecuencias de GHI (kWh/m²) de las Plantas Solares | ||||||||
| Lim. Inf | Lim. Sup | Marca Clase | Frec. Abs (ni) | Frec. Rel (%) | Ni (Asc) | Ni (Desc) | Hi Asc (%) | Hi Desc (%) |
|---|---|---|---|---|---|---|---|---|
| 0 | 1 | 0.5 | 3 | 0.01 | 3 | 58978 | 0.01 | 100 |
| 1 | 2 | 1.5 | 0 | 0 | 3 | 58975 | 0.01 | 99.99 |
| 2 | 3 | 2.5 | 199 | 0.34 | 202 | 58975 | 0.34 | 99.99 |
| 3 | 4 | 3.5 | 19150 | 32.47 | 19352 | 58776 | 32.81 | 99.66 |
| 4 | 5 | 4.5 | 21739 | 36.86 | 41091 | 39626 | 69.67 | 67.19 |
| 5 | 6 | 5.5 | 14813 | 25.12 | 55904 | 17887 | 94.79 | 30.33 |
| 6 | 7 | 6.5 | 2803 | 4.75 | 58707 | 3074 | 99.54 | 5.21 |
| 7 | 8 | 7.5 | 264 | 0.45 | 58971 | 271 | 99.99 | 0.46 |
| 8 | 9 | 8.5 | 7 | 0.01 | 58978 | 7 | 100 | 0.01 |
| TOTAL | - | - | 58978 | 100 | - | - | - | - |
4 Análisis Gráfico
4.1 Histogramas de Cantidad
par(mar = c(8, 7, 5, 2))
barplot(TDF_Enteros$ni,
names.arg = TDF_Enteros$MC,
main = "",
xlab = "",
ylab = "",
col = "#EEC900",
ylim = c(0, max(TDF_Enteros$ni) * 1.2),
space = 0,
las = 2,
cex.names = 0.7)
mtext("Cantidad", side = 2, line = 4.5, cex = 1, font = 1)
mtext("GHI (kWh/m²)", side = 1, line = 4)
mtext("Gráfica N°1: Distribución de Cantidad de Plantas Solares por GHI",
side = 3,
line = 2,
adj = 0.5,
cex = 0.9,
font = 2)
par(mar = c(8, 7, 5, 2))
barplot(TDF_Enteros$ni,
main="",
xlab = "",
ylab = "",
names.arg = TDF_Enteros$MC,
col = "#EEC900",
space = 0,
cex.names = 0.7,
las = 2,
ylim = c(0, 58978))
mtext("Cantidad", side = 2, line = 4.5, cex = 1, font = 1)
mtext("GHI (kWh/m²)", side = 1, line = 4)
mtext("Gráfica N°2: Distribución de Cantidad de Plantas Solares por GHI",
side = 3,
line = 2,
adj = 0.5,
cex = 0.9,
font = 2)
4.2 Histogramas Porcentuales
par(mar = c(8, 5, 5, 2))
bp3 <- barplot(TDF_Enteros$hi,
main = "",
xlab = "",
ylab = "Porcentaje (%)",
col = "#EEC900",
space = 0,
names.arg = TDF_Enteros$MC,
cex.names = 0.7,
las = 2,
ylim = c(0, max(TDF_Enteros$hi) * 1.2))
mtext("GHI (kWh/m²)", side = 1, line = 4)
mtext("Gráfica N°3: Distribución Porcentual de las Plantas Solares por GHI",
side = 3,
line = 2,
adj = 0.5,
cex = 0.9,
font = 2)
text(x = bp3,
y = TDF_Enteros$hi,
labels = paste0(round(TDF_Enteros$hi, 2), "%"),
pos = 3, cex = 0.6, col = "black")
par(mar = c(8, 5, 5, 2))
bp4 <- barplot(TDF_Enteros$hi,
main = "",
xlab = "",
ylab = "Porcentaje (%)",
col = "#EEC900",
space = 0,
names.arg = TDF_Enteros$MC,
las = 2,
cex.names = 0.7,
ylim = c(0, 100))
mtext("GHI (kWh/m²)", side = 1, line = 4)
mtext("Gráfica N°4: Distribución Porcentual de las Plantas Solares por GHI",
side = 3,
line = 2,
adj = 0.5,
cex = 0.9,
font = 2)
text(x = bp4,
y = TDF_Enteros$hi,
labels = paste0(round(TDF_Enteros$hi, 2), "%"),
pos = 3, cex = 0.6, col = "black")
4.3 Diagrama de Cajas (Boxplot)
par(mar = c(5, 5, 4, 2))
boxplot(Variable,
horizontal = TRUE,
col = "#EEC900",
xlab = "GHI (kWh/m²)",
cex.main = 0.9,
main = "Gráfica N°5: Distribución de GHI en las Plantas Solares")
4.4 Ojivas
par(mar = c(5, 5, 7, 10), xpd = TRUE)
# Coordenadas
x_asc <- TDF_Enteros$Ls
x_desc <- TDF_Enteros$Li
y_asc <- TDF_Enteros$Ni_asc
y_desc <- TDF_Enteros$Ni_desc
# 1. Dibujar la Ascendente
plot(x_asc, y_asc,
type = "b",
main = "",
xlab = "GHI (kWh/m²)",
ylab = "Frecuencia acumulada",
col = "black",
pch = 19,
xlim = c(min(TDF_Enteros$Li), max(x_asc)),
ylim = c(0, sum(TDF_Enteros$ni)),
bty = "l"
)
# 2. Agregar la Descendente
lines(x_desc, y_desc, col = "#CD8500", type = "b", pch = 19)
grid()
mtext("Gráfica N°6: Ojivas Ascendentes y Descendentes de la\nDistribución de GHI en las Plantas Solares",
side = 3,
line = 3,
adj = 0.5,
cex = 0.9,
font = 2)
legend("left",
legend = c("Ascendente", "Descendente"),
col = c("black", "#CD8500"),
lty = 1,
pch = 1,
cex = 0.6,
inset = c(0.05, 0.05),
bty = "n")
5 Indicadores Estadísticos
## INDICADORES DE TENDENCIA CENTRAL
# Media aritmética
media <- round(mean(Variable), 2)
# Mediana
mediana <- round(median(Variable), 2)
# Moda
max_frecuencia <- max(TDF_Enteros$ni)
moda_vals <- TDF_Enteros$MC[TDF_Enteros$ni == max_frecuencia]
moda_txt <- paste(round(moda_vals, 2), collapse = ", ")
## INDICADORES DE DISPERSIÓN
# Varianza
varianza <- var(Variable)
# Desviación Estándar
sd_val <- sd(Variable)
# Coeficiente de Variación
cv <- round((sd_val / abs(media)) * 100, 2)
## INDICADORES DE FORMA
# Coeficiente de Asimetría
asimetria <- skewness(Variable, type = 2)
# Curtosis
curtosis <- kurtosis(Variable)
# Outliers
Q1 <- quantile(Variable, 0.25)
Q3 <- quantile(Variable, 0.75)
IQR_val <- Q3 - Q1
lim_inf <- Q1 - 1.5 * IQR_val
lim_sup <- Q3 + 1.5 * IQR_val
outliers_data <- Variable[Variable < lim_inf | Variable > lim_sup]
num_outliers <- length(outliers_data)
if(num_outliers > 0){
rango_outliers <- paste0(num_outliers, " [", round(min(outliers_data), 2), "; ", round(max(outliers_data), 2), "]")
} else {
rango_outliers <- "0 [Sin Outliers]"
}
tabla_indicadores <- data.frame(
"Variable" = c("GHI (kWh/m²)"),
"Rango_MinMax" = paste0("[", round(min(Variable), 2), "; ", round(max(Variable), 2), "]"),
"X" = c(media),
"Me" = c(mediana),
"Mo" = c(moda_txt),
"V" = c(varianza),
"Sd" = c(sd_val),
"Cv" = c(cv),
"As" = c(asimetria),
"K" = c(curtosis),
"Outliers" = rango_outliers)
# Generar Tabla GT
tabla_conclusiones_gt <- tabla_indicadores %>%
gt() %>%
tab_header(title = md("**Tabla N°3 de Conclusiones de GHI de las Plantas Solares**")) %>%
tab_source_note(source_note = "Autor: Martin Sarmiento") %>%
cols_label(
Variable = "Variable",
Rango_MinMax = "Rango",
X = "Media (X)",
Me = "Mediana (Me)",
Mo = "Moda (Mo)",
V = "Varianza (V)",
Sd = "Desv. Est. (Sd)",
Cv = "C.V. (%)",
As = "Asimetría (As)",
K = "Curtosis (K)",
Outliers = "Outliers [Intervalo]"
) %>%
tab_options(
heading.title.font.size = px(16),
column_labels.background.color = "#F0F0F0"
)
tabla_conclusiones_gt| Tabla N°3 de Conclusiones de GHI de las Plantas Solares | ||||||||||
| Variable | Rango | Media (X) | Mediana (Me) | Moda (Mo) | Varianza (V) | Desv. Est. (Sd) | C.V. (%) | Asimetría (As) | Curtosis (K) | Outliers [Intervalo] |
|---|---|---|---|---|---|---|---|---|---|---|
| GHI (kWh/m²) | [0; 8.05] | 4.55 | 4.47 | 4.5 | 0.737728 | 0.8589109 | 18.88 | 0.4615969 | -0.408403 | 112 [0; 8.05] |
| Autor: Martin Sarmiento | ||||||||||
6 Conclusiones
La variable “GHI” fluctúa entre 0 y 8.05 kWh/m² y sus valores se encuentran alrededor de 4.47 kWh/m², con una desviación estándar de 0.8589109 , siendo una variable homogénea, cuyos valores se concentran en la parte media alta de la variable con la agregación de valores atípicos de 112 outliers; por todo lo anterior, el comportamiento de la variable es regular.