Advances, Systems and Applications
From: Task grouping and optimized deep learning based VM sizing for hosting containers as a service
Number of Iteration | Deep-ConvLSTM_FPO with Population Size 5 | Deep-ConvLSTM_FPO with Population Size 10 | Deep-ConvLSTM_FPO with Population Size 15 | Deep-ConvLSTM_FPO with Population Size 20 |
---|---|---|---|---|
Resource Utilization | ||||
5 | 0.0654 | 0.0636 | 0.0588 | 0.0547 |
10 | 0.0733 | 0.0715 | 0.0677 | 0.0636 |
15 | 0.0714 | 0.0687 | 0.0636 | 0.0598 |
20 | 0.0721 | 0.0699 | 0.0647 | 0.0615 |
Response Time | ||||
5 | 540 | 538 | 534 | 531 |
10 | 449 | 446 | 443 | 440 |
15 | 442 | 440 | 439 | 436 |
20 | 427 | 422 | 419 | 416 |
Task Rejection Rate | ||||
5 | 0.2054 | 0.1979 | 0.1876 | 0.1757 |
10 | 0.2241 | 0.2168 | 0.2088 | 0.1977 |
15 | 0.2385 | 0.2258 | 0.2157 | 0.2076 |
20 | 0.2486 | 0.2368 | 0.2279 | 0.2168 |
Makespan | ||||
5 | 0.5656 | 0.5543 | 0.5368 | 0.5146 |
10 | 0.5866 | 0.5754 | 0.5543 | 0.5368 |
15 | 0.6077 | 0.5865 | 0.5754 | 0.5543 |
20 | 0.6357 | 0.6268 | 0.6157 | 0.6075 |