| Symbol |
Description |
|
|
Training dataset |
|
|
Feature vector of sample
|
|
|
Class label of sample
|
|
|
Number of attack categories |
|
|
Teacher network |
|
|
Student network |
|
|
Parameters of teacher/student networks |
|
|
Knowledge distillation loss |
|
|
Cross-entropy loss |
|
|
Kullback–Leibler divergence |
|
|
Temperature parameter for distillation |
|
|
Loss balancing coefficient |
|
|
Quantization bit-width |
|
|
Threat level at time
|
|
|
Exponential smoothing parameter |
|
|
Window size for threat estimation |
|
|
Energy consumption of IDS module |
|
|
Energy per multiply–accumulate operation |
|
|
Memory access energy per neuron |
|
|
Carbon intensity at node , time
|
|
|
Renewable energy fraction |
|
|
Scheduling decision variable |
|
|
Energy requirement of job
|
|
|
Maximum power capacity of node
|
|
|
Deadline of job
|
|
|
Security priority weight |
|
|
Total number of participating nodes |
|
|
Number of node groups |
|
|
Local objective function |
|
|
Global objective function |
| Acronym |
Definition |
| IDS |
Intrusion Detection System |
| EEIDM |
Energy-Efficient Intrusion Detection Module |
| LCE |
Lightweight Cryptographic Engine |
| HFLC |
Hierarchical Federated Learning Coordinator |
| CASE |
Carbon-Aware Scheduling Engine |
| KD |
Knowledge Distillation |
| FL |
Federated Learning |
| ASCON |
Authenticated Encryption Standard |
| ECDH |
Elliptic Curve Diffie-Hellman |
| AUC |
Area Under ROC Curve |
| ROC |
Receiver Operating Characteristic |