1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
|
library("tidyverse")
options(dplyr.summarise.inform = FALSE)
library("class")
library("rpart")
library("rpart.plot")
library("viridis")
library("MLmetrics")
## Simulation Parameters:
## simkey {baseline,extended,hint,hintandextended}
## wireless {lora,nbiot}
## wakeupfor {60s,180s}
## seed [1,200]
## node on[0,12]
## isSender {0,1}
## dataSize {1MB}
## Metrics:
## energy [0,+inf)
## nDataRcv [0,+inf)
nseed=200
nwakeupfor=2
nwireless=2
nsimkey=4
nsimulations=nseed*nwakeupfor*nwireless*nsimkey # Must be 3200
## Load data
data=suppressMessages(read_csv("../CCGRID2022.csv"))%>%distinct() # Note that in the data experiment wireless=="lora",seed==1,wakeupfor==60,simkey=="baseline" is present 2 times in the CSV file
data_seed=data%>%group_by(simkey,wireless,wakeupfor,seed)%>%summarize(energy=sum(energy),coverage=sum(nDataRcv))%>%
mutate(efficiency=energy/coverage)%>%
ungroup()
F1_Score2=function(truth, pred){
result=sapply(c("baseline","extended","hint","hintandextended"),function(c){
cur_truth=truth[truth==c]
cur_pred=pred[truth==c]
col=paste0("f1_",c)
score=F1_Score(cur_truth,cur_pred)
if(is.nan(score)){score=0}
list(tibble(!!col:=score))
})
do.call("cbind",result)
}
build_models=function(ignore_hint=TRUE){
## Prepare data for traning
set.seed(1) # Reproducibility
wireless_map=c("lora"=1,"nbiot"=2)
data_ml=data_seed%>%select(-efficiency,-seed)%>%mutate(wireless=wireless_map[data_seed$wireless])
if(ignore_hint){
data_ml=data_ml%>%filter(simkey!="hint")
}
train_set=data_ml%>%sample_frac(0.8) # 80% of the data
test_set=data_ml%>%suppressMessages(anti_join(train_set)) # 20% of the data
## KNN predict function
knn_fn=function(inputs){
as.vector(knn(train=train_set%>%select(-simkey),test=inputs%>%select(-simkey),cl=train_set$simkey,k=10))
}
## Decision tree
tree=rpart(
simkey ~ wireless + wakeupfor + energy + coverage,
data=train_set,
method="class",
minsplit=60,
minbucket=1)
## Tree predict function
tree_fn=function(inputs){
as.vector(predict(tree,newdata=inputs%>%select(-simkey),type="class"))
}
## Build models
models=list(predict_knn=knn_fn,predict_tree=tree_fn)
## Computer performances
perfs=sapply(seq(1,20),function(i){
## Prepare data for traning
set.seed(1) # Reproducibility
wireless_map=c("lora"=1,"nbiot"=2)
data_ml=data_seed%>%select(-efficiency,-seed)%>%mutate(wireless=wireless_map[data_seed$wireless])
if(ignore_hint){
data_ml=data_ml%>%filter(simkey!="hint")
}
train_set=data_ml%>%sample_frac(0.8) # 80% of the data
test_set=data_ml%>%suppressMessages(anti_join(train_set)) # 20% of the data
## KNN
knn_predictions=as.vector(knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=10))
## Decision tree
tree=rpart(
simkey ~ wireless + wakeupfor + energy + coverage,
data=train_set,
method="class",
minsplit=60,
minbucket=1)
tree_predictions=as.vector(predict(tree,newdata=test_set%>%select(-simkey),type="class"))
## Prefs
f1_knn=F1_Score2(test_set$simkey,knn_predictions)
f1_tree=F1_Score2(test_set$simkey,tree_predictions)
accuracy_knn=sum(test_set$simkey==knn_predictions)/length(test_set$simkey)
accuracy_tree=sum(test_set$simkey==tree_predictions)/length(test_set$simkey)
list(cbind(tibble(model=c("knn","tree")),rbind(f1_knn,f1_tree),tibble(accuracy=c(accuracy_knn,accuracy_tree))))
})
perfs=do.call("rbind",perfs)%>%mutate_if(is.numeric, ~round(.,digits=2))
perfs=perfs%>%group_by(model)%>%summarize(
f1_baseline=mean(f1_baseline),
f1_hint=mean(f1_hint),
f1_extended=mean(f1_extended),
f1_hintandextended=mean(f1_hintandextended),
accuracy=mean(accuracy))
write.csv(perfs,paste0("figures/f1_scores_offline_ignoreHINT",ignore_hint,".csv"),quote=FALSE,row.names=FALSE)
## Return models
models
}
generate_inputs=function(ignore_hint=FALSE) {
## Prepare data for traning
set.seed(1) # Reproducibility
wireless_map=c("lora"=1,"nbiot"=2)
data_ml=data_seed%>%select(-efficiency,-seed)%>%mutate(wireless=wireless_map[data_seed$wireless])
if(ignore_hint){
data_ml=data_ml%>%filter(simkey!="hint")
}
train_set=data_ml%>%sample_frac(0.8) # 80% of the data
test_set=data_ml%>%anti_join(train_set) # 20% of the data
## KNN training
knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=10)
## KNN analysis
knn_cont_table=table(knn_predictions,test_set$simkey)
knn_accuracy=round((sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))*100)
knn_prop_table=round(prop.table(knn_cont_table),digits=2)
## Decision tree
tree=rpart(
simkey ~ wireless + wakeupfor + energy + coverage,
data=train_set,
method="class",
minsplit=60,
minbucket=1)
tree_predictions=predict(tree,newdata=test_set%>%select(-simkey),type="class")
tree_cont_table=table(tree_predictions,test_set$simkey)
tree_accuracy=(sum(diag(tree_cont_table)/sum(rowSums(tree_cont_table))))
tree_prop_table=round(prop.table(tree_cont_table),digits=2)
## Elbow plot
elbow_data=lapply(seq(1,10),function(kvalue){
knn_predictions=knn(train=train_set%>%select(-simkey),test=test_set%>%select(-simkey),cl=train_set$simkey,k=kvalue)
## KNN analysis
knn_cont_table=table(knn_predictions,test_set$simkey)
knn_accuracy=(sum(diag(knn_cont_table)/sum(rowSums(knn_cont_table))))
knn_prop_table=round(prop.table(knn_cont_table),digits=2)
tibble(k=kvalue,accuracy=knn_accuracy)
})
elbow_data=do.call("rbind",elbow_data)
ggplot(data=elbow_data,aes(k,accuracy))+geom_point()+geom_line()+ggtitle(paste("K-elbow for with NoHint to",as.character(ignore_hint)))+ylim(c(0,1))
ggsave(paste0("figures/knn_elbow_NoHintIs",as.character(ignore_hint),".pdf"))
## Prints
print(paste0("Accuracy: KNN=",knn_accuracy,"% CART=",tree_accuracy,"%"))
pdf(paste0("figures/tree_",as.character(ignore_hint),".pdf"))
tree_plot=rpart.plot(tree,box.palette=as.list(viridis::viridis(4,begin=0.48)),tweak=1.111)
silent_call=dev.off()
## Notes: KNN accuracy jump to 76% and CART to 80% accuracy without the hint policy
## Generate simulation inputs
inputs=tibble(
wakeupfor = c(60,180,60,180),
wireless = c("lora", "lora", "nbiot", "nbiot"))
constraints=apply(inputs,1,function(row){
wi=row["wireless"]
wa=as.numeric(row["wakeupfor"])
## First extract energy/coverage boundaries
min_energy=min((data_seed%>%filter(wireless==wi,wakeupfor==wa))$energy)
max_energy=max((data_seed%>%filter(wireless==wi,wakeupfor==wa))$energy)
min_coverage=min((data_seed%>%filter(wireless==wi,wakeupfor==wa))$coverage)
max_coverage=max((data_seed%>%filter(wireless==wi,wakeupfor==wa))$coverage)
## Generate random points (10 per scenarios)
n=100
current_inputs=tibble(
wireless=rep(wi,n),
wakeupfor=rep(wa,n),
energy_constraint=runif(n,min_energy,max_energy),
coverage_constraint=round(runif(n,min_coverage,max_coverage)))
predictions_knn=knn(train=train_set%>%select(-simkey),test=current_inputs%>%
rename(energy=energy_constraint,coverage=coverage_constraint)%>%
mutate(wireless=wireless_map[wireless]),cl=train_set$simkey,k=10)
predictions_tree=predict(tree,newdata=current_inputs%>%
rename(energy=energy_constraint,coverage=coverage_constraint)%>%
mutate(wireless=wireless_map[wireless]),type="class")
knn_final=tibble(cbind(current_inputs,tibble(simkey=predictions_knn,model="knn")))
tree_final=tibble(cbind(current_inputs,tibble(simkey=predictions_tree,model="tree")))
rbind(knn_final,tree_final)
})
inputs=do.call("rbind",constraints)%>%distinct()
## Dimension Energy/Coverage
ggplot(data_seed%>%mutate(wakeupfor=as.character(wakeupfor)),
aes(coverage,energy,color=simkey))+geom_point()+
geom_point(data=inputs%>%mutate(wakeupfor=as.character(wakeupfor)),aes(coverage_constraint,energy_constraint),size=3,pch=5)+
ggtitle("Dimension Energy/Coverage")+xlab("Coverage")+ylab("Sum of nodes energy consumption (J)")+
facet_wrap(~wakeupfor+wireless,scale="free")
ggsave(paste0("figures/random_inputs_NoHintIs",as.character(ignore_hint),".pdf"),width=15)
write.csv(inputs,paste0("inputs/inputs_NoHintIs",as.character(ignore_hint),".csv"),row.names=FALSE, quote=FALSE)
}
## Build models and generate performance metrics
build_models(ignore_hint=FALSE)
build_models(ignore_hint=TRUE)
## Generate inputs
generate_inputs(ignore_hint=FALSE)
generate_inputs(ignore_hint=TRUE)
|
