Table 5 Energy consumptionan alysis with comparative context.

From: A unified low-carbon cybersecurity framework integrating energy-efficient intrusion detection, lightweight cryptography, and carbon-aware scheduling for edge–cloud architectures

Configuration

Inference (mJ)

Power (W)

Training (kWh)

Comm. (mJ/round)

Total (kWh/day)

Reduction versus baseline (%)

Cloud deployment

 Teacher (Full)

12.45

285.3

8.72

N/A

6.85

–

 FedAvg baseline

12.45

285.3

9.15

856.2

7.23

–

 Edge deployment (Raspberry Pi 4)

 Teacher (Full)

89.67

5.8

N/A

N/A

0.139

–

 Student (32-bit)

28.34

3.2

N/A

N/A

0.077

44.6

 Student (16-bit)

14.23

2.4

N/A

N/A

0.058

58.3

 Student (8-bit)

7.89

1.8

N/A

N/A

0.043

69.1

 Student (4-bit)

4.56

1.4

N/A

N/A

0.034

75.5

 GreenShield

8.12

1.9

N/A

234.5

0.045

67.6

Hierarchical FL deployment

 FedAvg (Full)

12.45

285.3

9.15

856.2

7.23

–

 FedProx

12.67

287.1

9.34

867.4

7.38

–

 GreenShield

8.12

92.4

3.21

234.5

2.36

67.4

 p valuevsFedAvg

   

0.012

  
Back to article page