(cid:29)(cid:37)(cid:35)(cid:40)(cid:46)(cid:41)(cid:35)(cid:33)(cid:44)(cid:1)(cid:27)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:50)(cid:1)(cid:4)(cid:19)(cid:22)(cid:28)(cid:5)
`
`(cid:20)(cid:37)(cid:48)(cid:33)(cid:49)(cid:51)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:47)(cid:38)(cid:1)(cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:3)(cid:1)(cid:22)(cid:46)(cid:38)(cid:47)(cid:49)(cid:45)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)(cid:1)(cid:28)(cid:35)(cid:41)(cid:37)(cid:46)(cid:35)(cid:37)
`
`(cid:7)(cid:17)(cid:14)(cid:23)(cid:11)(cid:20)(cid:21)(cid:14)(cid:22)(cid:24)(cid:1)(cid:18)(cid:12)(cid:1)(cid:5)(cid:11)(cid:17)(cid:17)(cid:21)(cid:24)(cid:15)(cid:23)(cid:8)(cid:17)(cid:14)(cid:8)
`(cid:6)(cid:10)(cid:13)(cid:18)(cid:15)(cid:8)(cid:20)(cid:15)(cid:24)(cid:3)(cid:18)(cid:16)(cid:16)(cid:18)(cid:17)(cid:21)
`
`(cid:14)(cid:7)(cid:10)(cid:7)(cid:10)(cid:15)(cid:15)(cid:13)
`
`(cid:8)(cid:22)(cid:28)(cid:14)(cid:24)(cid:1)(cid:7)(cid:11)(cid:21)(cid:11)(cid:15)(cid:14)(cid:20)(cid:14)(cid:21)(cid:25)(cid:1)(cid:17)(cid:21)(cid:1)(cid:7)(cid:22)(cid:12)(cid:17)(cid:19)(cid:14)(cid:1)(cid:5)(cid:22)(cid:20)(cid:23)(cid:26)(cid:25)(cid:17)(cid:21)(cid:15)(cid:1)(cid:2)(cid:11)
`(cid:9)(cid:26)(cid:24)(cid:27)(cid:14)(cid:29)(cid:3)
`
`(cid:9)(cid:11)(cid:21)(cid:18)(cid:11)(cid:29)(cid:1)(cid:10)(cid:13)(cid:11)(cid:21)(cid:17)
`(cid:3)(cid:9)(cid:7)(cid:14)(cid:5)(cid:11)(cid:12)(cid:7)(cid:13)(cid:15)(cid:1)(cid:10)(cid:6)(cid:1)(cid:2)(cid:5)(cid:9)(cid:9)(cid:12)(cid:15)(cid:8)(cid:14)(cid:4)(cid:9)(cid:7)(cid:4)
`
`(cid:6)(cid:22)(cid:21)(cid:11)(cid:25)(cid:16)(cid:11)(cid:21)(cid:1)(cid:7)(cid:4)(cid:1)(cid:9)(cid:20)(cid:17)(cid:25)(cid:16)
`(cid:3)(cid:9)(cid:7)(cid:14)(cid:5)(cid:11)(cid:12)(cid:7)(cid:13)(cid:15)(cid:1)(cid:10)(cid:6)(cid:1)(cid:2)(cid:5)(cid:9)(cid:9)(cid:12)(cid:15)(cid:8)(cid:14)(cid:4)(cid:9)(cid:7)(cid:4)(cid:6)(cid:1)(cid:42)(cid:45)(cid:50)(cid:17)(cid:35)(cid:41)(cid:50)(cid:8)(cid:52)(cid:48)(cid:37)(cid:46)(cid:46)(cid:8)(cid:37)(cid:36)(cid:52)
`
`(cid:21)(cid:47)(cid:44)(cid:44)(cid:47)(cid:54)(cid:1)(cid:51)(cid:40)(cid:41)(cid:50)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:33)(cid:36)(cid:36)(cid:41)(cid:51)(cid:41)(cid:47)(cid:46)(cid:33)(cid:44)(cid:1)(cid:54)(cid:47)(cid:49)(cid:43)(cid:50)(cid:1)(cid:33)(cid:51)(cid:16) (cid:40)(cid:58)(cid:48)(cid:16)(cid:9)(cid:9)(cid:49)(cid:37)(cid:48)(cid:47)(cid:50)(cid:41)(cid:51)(cid:47)(cid:49)(cid:56)(cid:8)(cid:52)(cid:48)(cid:37)(cid:46)(cid:46)(cid:8)(cid:37)(cid:36)(cid:52)(cid:9)(cid:35)(cid:41)(cid:50)(cid:32)(cid:49)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:50)
`(cid:26)(cid:33)(cid:49)(cid:51)(cid:1)(cid:47)(cid:38)(cid:1)(cid:51)(cid:40)(cid:37) (cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:28)(cid:35)(cid:41)(cid:37)(cid:46)(cid:35)(cid:37)(cid:50)(cid:1)(cid:19)(cid:47)(cid:45)(cid:45)(cid:47)(cid:46)(cid:50)
`
`(cid:27)(cid:37)(cid:35)(cid:47)(cid:45)(cid:45)(cid:37)(cid:46)(cid:36)(cid:37)(cid:36)(cid:1)(cid:19)(cid:41)(cid:51)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)
`(cid:28)(cid:33)(cid:46)(cid:42)(cid:33)(cid:56)(cid:1)(cid:30)(cid:36)(cid:33)(cid:46)(cid:41)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:23)(cid:47)(cid:46)(cid:33)(cid:51)(cid:40)(cid:33)(cid:46)(cid:1)(cid:24)(cid:8)(cid:1)(cid:28)(cid:45)(cid:41)(cid:51)(cid:40)(cid:6)(cid:1)(cid:2)(cid:26)(cid:47)(cid:54)(cid:37)(cid:49)(cid:1)(cid:24)(cid:33)(cid:46)(cid:33)(cid:39)(cid:37)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:41)(cid:46)(cid:1)(cid:24)(cid:47)(cid:34)(cid:41)(cid:44)(cid:37)(cid:1)(cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:41)(cid:46)(cid:39)(cid:1)(cid:4)(cid:33)(cid:1)(cid:28)(cid:52)(cid:49)(cid:53)(cid:37)(cid:56)(cid:5)(cid:2)(cid:6)(cid:1)(cid:8)(cid:1)(cid:18)(cid:52)(cid:39)(cid:52)(cid:50)(cid:51)(cid:1)(cid:10)(cid:15)(cid:15)(cid:13)(cid:8)
`
`(cid:30)(cid:46)(cid:41)(cid:53)(cid:37)(cid:49)(cid:50)(cid:41)(cid:51)(cid:56)(cid:1)(cid:47)(cid:38)(cid:1)(cid:26)(cid:37)(cid:46)(cid:46)(cid:50)(cid:56)(cid:44)(cid:53)(cid:33)(cid:46)(cid:41)(cid:33)(cid:1)(cid:20)(cid:37)(cid:48)(cid:33)(cid:49)(cid:51)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:47)(cid:38)(cid:1)(cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:22)(cid:46)(cid:38)(cid:47)(cid:49)(cid:45)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)(cid:1)(cid:28)(cid:35)(cid:41)(cid:37)(cid:46)(cid:35)(cid:37)(cid:1)(cid:29)(cid:37)(cid:35)(cid:40)(cid:46)(cid:41)(cid:35)(cid:33)(cid:44)(cid:1)(cid:27)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:1)(cid:25)(cid:47)(cid:8)(cid:1)(cid:24)(cid:28)(cid:7)(cid:19)(cid:22)(cid:28)(cid:7)(cid:15)(cid:14)(cid:7)(cid:11)(cid:13)(cid:8)
`
`(cid:57)(cid:41)(cid:50)(cid:1)(cid:48)(cid:33)(cid:48)(cid:37)(cid:49)(cid:1)(cid:41)(cid:50)(cid:1)(cid:48)(cid:47)(cid:50)(cid:51)(cid:37)(cid:36)(cid:1)(cid:33)(cid:51)(cid:1)(cid:28)(cid:35)(cid:40)(cid:47)(cid:44)(cid:33)(cid:49)(cid:44)(cid:56)(cid:19)(cid:47)(cid:45)(cid:45)(cid:47)(cid:46)(cid:50)(cid:8) (cid:40)(cid:58)(cid:48)(cid:16)(cid:9)(cid:9)(cid:49)(cid:37)(cid:48)(cid:47)(cid:50)(cid:41)(cid:51)(cid:47)(cid:49)(cid:56)(cid:8)(cid:52)(cid:48)(cid:37)(cid:46)(cid:46)(cid:8)(cid:37)(cid:36)(cid:52)(cid:9)(cid:35)(cid:41)(cid:50)(cid:32)(cid:49)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:50)(cid:9)(cid:10)(cid:13)(cid:12)
`(cid:21)(cid:47)(cid:49)(cid:1)(cid:45)(cid:47)(cid:49)(cid:37)(cid:1)(cid:41)(cid:46)(cid:38)(cid:47)(cid:49)(cid:45)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)(cid:6)(cid:1)(cid:48)(cid:44)(cid:37)(cid:33)(cid:50)(cid:37)(cid:1)(cid:35)(cid:47)(cid:46)(cid:51)(cid:33)(cid:35)(cid:51) (cid:44)(cid:41)(cid:34)(cid:49)(cid:33)(cid:49)(cid:56)(cid:49)(cid:37)(cid:48)(cid:47)(cid:50)(cid:41)(cid:51)(cid:47)(cid:49)(cid:56)(cid:17)(cid:48)(cid:47)(cid:34)(cid:47)(cid:55)(cid:8)(cid:52)(cid:48)(cid:37)(cid:46)(cid:46)(cid:8)(cid:37)(cid:36)(cid:52)(cid:8)
`
`Qualcomm Incorporated
`Exhibit 1013
`Page 1 of 14
`
`

`

`(cid:8)(cid:22)(cid:28)(cid:14)(cid:24)(cid:1)(cid:7)(cid:11)(cid:21)(cid:11)(cid:15)(cid:14)(cid:20)(cid:14)(cid:21)(cid:25)(cid:1)(cid:17)(cid:21)(cid:1)(cid:7)(cid:22)(cid:12)(cid:17)(cid:19)(cid:14)(cid:1)(cid:5)(cid:22)(cid:20)(cid:23)(cid:26)(cid:25)(cid:17)(cid:21)(cid:15)(cid:1)(cid:2)(cid:11)(cid:1)(cid:9)(cid:26)(cid:24)(cid:27)(cid:14)(cid:29)(cid:3)
`
`(cid:2)(cid:9)(cid:21)(cid:22)(cid:20)(cid:8)(cid:10)(cid:22)
`(cid:27)(cid:33)(cid:48)(cid:41)(cid:36)(cid:1)(cid:33)(cid:36)(cid:53)(cid:33)(cid:46)(cid:35)(cid:37)(cid:50)(cid:1)(cid:41)(cid:46)(cid:1)(cid:51)(cid:37)(cid:35)(cid:40)(cid:46)(cid:47)(cid:44)(cid:47)(cid:39)(cid:56)(cid:1)(cid:40)(cid:33)(cid:53)(cid:37)(cid:1)(cid:49)(cid:37)(cid:50)(cid:52)(cid:44)(cid:51)(cid:37)(cid:36)(cid:1)(cid:41)(cid:46)(cid:1)(cid:44)(cid:33)(cid:48)(cid:51)(cid:47)(cid:48)(cid:1)(cid:4)(cid:45)(cid:47)(cid:34)(cid:41)(cid:44)(cid:37)(cid:5)(cid:1)(cid:35)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:50)(cid:1)(cid:54)(cid:41)(cid:51)(cid:40)(cid:1)(cid:48)(cid:37)(cid:49)(cid:38)(cid:47)(cid:49)(cid:45)(cid:33)(cid:46)(cid:35)(cid:37)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:38)(cid:37)(cid:33)(cid:51)(cid:52)(cid:49)(cid:37)(cid:50)
`(cid:35)(cid:47)(cid:45)(cid:48)(cid:33)(cid:49)(cid:33)(cid:34)(cid:44)(cid:37)(cid:1)(cid:51)(cid:47)(cid:1)(cid:36)(cid:37)(cid:50)(cid:43)(cid:51)(cid:47)(cid:48)(cid:1)(cid:4)(cid:50)(cid:51)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)(cid:33)(cid:49)(cid:56)(cid:5)(cid:1)(cid:45)(cid:33)(cid:35)(cid:40)(cid:41)(cid:46)(cid:37)(cid:50)(cid:8)(cid:1)(cid:18)(cid:36)(cid:53)(cid:33)(cid:46)(cid:35)(cid:37)(cid:50)(cid:1)(cid:41)(cid:46)(cid:1)(cid:49)(cid:37)(cid:35)(cid:40)(cid:33)(cid:49)(cid:39)(cid:37)(cid:33)(cid:34)(cid:44)(cid:37)(cid:1)(cid:34)(cid:33)(cid:58)(cid:37)(cid:49)(cid:56)(cid:1)(cid:51)(cid:37)(cid:35)(cid:40)(cid:46)(cid:47)(cid:44)(cid:47)(cid:39)(cid:56)(cid:1)(cid:40)(cid:33)(cid:53)(cid:37)(cid:1)(cid:38)(cid:33)(cid:41)(cid:44)(cid:37)(cid:36)(cid:1)(cid:51)(cid:47)
`(cid:43)(cid:37)(cid:37)(cid:48)(cid:1)(cid:48)(cid:33)(cid:35)(cid:37)(cid:6)(cid:1)(cid:36)(cid:37)(cid:35)(cid:49)(cid:37)(cid:33)(cid:50)(cid:41)(cid:46)(cid:39)(cid:1)(cid:51)(cid:40)(cid:37)(cid:1)(cid:52)(cid:50)(cid:37)(cid:38)(cid:52)(cid:44)(cid:46)(cid:37)(cid:50)(cid:50)(cid:1)(cid:47)(cid:38)(cid:1)(cid:45)(cid:47)(cid:34)(cid:41)(cid:44)(cid:37)(cid:1)(cid:35)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:50)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:48)(cid:47)(cid:49)(cid:51)(cid:33)(cid:34)(cid:44)(cid:37)(cid:1)(cid:54)(cid:41)(cid:49)(cid:37)(cid:44)(cid:37)(cid:50)(cid:50)(cid:1)(cid:36)(cid:37)(cid:53)(cid:41)(cid:35)(cid:37)(cid:50)(cid:8)(cid:1)(cid:28)(cid:37)(cid:53)(cid:37)(cid:49)(cid:33)(cid:44)(cid:1)(cid:45)(cid:37)(cid:51)(cid:40)(cid:47)(cid:36)(cid:50)(cid:1)(cid:47)(cid:38)
`(cid:48)(cid:47)(cid:54)(cid:37)(cid:49)(cid:1)(cid:45)(cid:33)(cid:46)(cid:33)(cid:39)(cid:37)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:35)(cid:33)(cid:46)(cid:1)(cid:34)(cid:37)(cid:1)(cid:52)(cid:50)(cid:37)(cid:36)(cid:1)(cid:51)(cid:47)(cid:1)(cid:48)(cid:49)(cid:47)(cid:44)(cid:47)(cid:46)(cid:39)(cid:1)(cid:51)(cid:40)(cid:37)(cid:1)(cid:34)(cid:33)(cid:58)(cid:37)(cid:49)(cid:56)(cid:1)(cid:44)(cid:41)(cid:38)(cid:37)(cid:1)(cid:47)(cid:38)(cid:1)(cid:33)(cid:1)(cid:45)(cid:47)(cid:34)(cid:41)(cid:44)(cid:37)(cid:1)(cid:35)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:8)(cid:1)(cid:31)(cid:37)(cid:1)(cid:48)(cid:49)(cid:47)(cid:53)(cid:41)(cid:36)(cid:37)(cid:1)(cid:33)(cid:1)(cid:36)(cid:37)(cid:51)(cid:33)(cid:41)(cid:44)(cid:37)(cid:36)
`(cid:33)(cid:46)(cid:33)(cid:44)(cid:56)(cid:50)(cid:41)(cid:50)(cid:1)(cid:47)(cid:38)(cid:1)(cid:48)(cid:47)(cid:54)(cid:37)(cid:49)(cid:1)(cid:35)(cid:47)(cid:46)(cid:50)(cid:52)(cid:45)(cid:48)(cid:51)(cid:41)(cid:47)(cid:46)(cid:1)(cid:51)(cid:56)(cid:48)(cid:41)(cid:35)(cid:33)(cid:44)(cid:44)(cid:56)(cid:1)(cid:37)(cid:46)(cid:35)(cid:47)(cid:52)(cid:46)(cid:51)(cid:37)(cid:49)(cid:37)(cid:36)(cid:1)(cid:41)(cid:46)(cid:1)(cid:33)(cid:1)(cid:46)(cid:37)(cid:51)(cid:54)(cid:47)(cid:49)(cid:43)(cid:37)(cid:36)(cid:1)(cid:44)(cid:33)(cid:48)(cid:51)(cid:47)(cid:48)(cid:1)(cid:35)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:51)(cid:40)(cid:37)(cid:1)(cid:48)(cid:47)(cid:54)(cid:37)(cid:49)
`(cid:45)(cid:33)(cid:46)(cid:33)(cid:39)(cid:37)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:45)(cid:37)(cid:51)(cid:40)(cid:47)(cid:36)(cid:50)(cid:1)(cid:35)(cid:52)(cid:49)(cid:49)(cid:37)(cid:46)(cid:51)(cid:44)(cid:56)(cid:1)(cid:52)(cid:50)(cid:37)(cid:36)(cid:8)(cid:1)(cid:31)(cid:37)(cid:1)(cid:33)(cid:44)(cid:50)(cid:47)(cid:1)(cid:47)(cid:52)(cid:51)(cid:44)(cid:41)(cid:46)(cid:37)(cid:1)(cid:50)(cid:47)(cid:45)(cid:37)(cid:1)(cid:46)(cid:47)(cid:53)(cid:37)(cid:44)(cid:1)(cid:48)(cid:49)(cid:47)(cid:48)(cid:47)(cid:50)(cid:37)(cid:36)(cid:1)(cid:48)(cid:47)(cid:54)(cid:37)(cid:49)(cid:1)(cid:45)(cid:33)(cid:46)(cid:33)(cid:39)(cid:37)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:45)(cid:37)(cid:51)(cid:40)(cid:47)(cid:36)(cid:50)(cid:8)
`
`(cid:4)(cid:14)(cid:21)(cid:10)(cid:14)(cid:19)(cid:15)(cid:14)(cid:17)(cid:11)(cid:21)
`(cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:28)(cid:35)(cid:41)(cid:37)(cid:46)(cid:35)(cid:37)(cid:50)
`
`(cid:3)(cid:18)(cid:16)(cid:16)(cid:11)(cid:17)(cid:22)(cid:21)
`(cid:30)(cid:46)(cid:41)(cid:53)(cid:37)(cid:49)(cid:50)(cid:41)(cid:51)(cid:56)(cid:1)(cid:47)(cid:38)(cid:1)(cid:26)(cid:37)(cid:46)(cid:46)(cid:50)(cid:56)(cid:44)(cid:53)(cid:33)(cid:46)(cid:41)(cid:33)(cid:1)(cid:20)(cid:37)(cid:48)(cid:33)(cid:49)(cid:51)(cid:45)(cid:37)(cid:46)(cid:51)(cid:1)(cid:47)(cid:38)(cid:1)(cid:19)(cid:47)(cid:45)(cid:48)(cid:52)(cid:51)(cid:37)(cid:49)(cid:1)(cid:33)(cid:46)(cid:36)(cid:1)(cid:22)(cid:46)(cid:38)(cid:47)(cid:49)(cid:45)(cid:33)(cid:51)(cid:41)(cid:47)(cid:46)(cid:1)(cid:28)(cid:35)(cid:41)(cid:37)(cid:46)(cid:35)(cid:37)(cid:1)(cid:29)(cid:37)(cid:35)(cid:40)(cid:46)(cid:41)(cid:35)(cid:33)(cid:44)(cid:1)(cid:27)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:1)(cid:25)(cid:47)(cid:8)(cid:1)(cid:24)(cid:28)(cid:7)
`(cid:19)(cid:22)(cid:28)(cid:7)(cid:15)(cid:14)(cid:7)(cid:11)(cid:13)(cid:8)
`
`(cid:57)(cid:41)(cid:50)(cid:1)(cid:51)(cid:37)(cid:35)(cid:40)(cid:46)(cid:41)(cid:35)(cid:33)(cid:44)(cid:1)(cid:49)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:1)(cid:41)(cid:50)(cid:1)(cid:33)(cid:53)(cid:33)(cid:41)(cid:44)(cid:33)(cid:34)(cid:44)(cid:37)(cid:1)(cid:33)(cid:51)(cid:1)(cid:28)(cid:35)(cid:40)(cid:47)(cid:44)(cid:33)(cid:49)(cid:44)(cid:56)(cid:19)(cid:47)(cid:45)(cid:45)(cid:47)(cid:46)(cid:50)(cid:16) (cid:40)(cid:58)(cid:48)(cid:16)(cid:9)(cid:9)(cid:49)(cid:37)(cid:48)(cid:47)(cid:50)(cid:41)(cid:51)(cid:47)(cid:49)(cid:56)(cid:8)(cid:52)(cid:48)(cid:37)(cid:46)(cid:46)(cid:8)(cid:37)(cid:36)(cid:52)(cid:9)(cid:35)(cid:41)(cid:50)(cid:32)(cid:49)(cid:37)(cid:48)(cid:47)(cid:49)(cid:51)(cid:50)(cid:9)(cid:10)(cid:13)(cid:12)
`
`Page 2 of 14
`
`

`

`Power Management in Mobile Computing (A Survey)
`
`MS-CIS-98-26
`
`Sanjay Udani and Jonathan Smith
`
`University of P ennsylvania
`School of Engineering and Applied Science
`Computer and Information Science Department
`
`Philadelphia, PA 19104-6389
`
`1998
`
`Page 3 of 14
`
`

`

`Power Management in Mobile Computing*
`
`Jonathan Smith
`Sanjay Udani
`Distributed Systems Laboratory
`Department of Computer Information Science
`University of Pennsylvania
`{ udani, jms} @dsl. cis. upenn. edu
`
`August 1996
`
`Abstract
`Rapid advances in technology have resulted in laptop {mobile) computers with performance and
`features comparable to desktop (stationary) machines. Advances in rechargeable battery technology
`have failed to keep pace, decreasing the usefulness of mobile computers and portable wireless devices.
`Several methods of power management can be used to prolong the battery life of a mobile computer.
`We provide a detailed analysis of power consumption typically encountered in a networked laptop com(cid:173)
`puter and the power management methods currently used. We also outline some novel proposed power
`management methods.
`
`1
`
`Introduction
`
`Laptop computers have often served as portable word processors or game machines. Such machines were
`generally two or more generations behind desktop computers in terms of processing power, features and
`performance. Limitations in display and miniaturization technology prevented laptops from being able to
`compete with desktops as "real" (i.e. full featured) computers.
`Recent advances in technology have dramatically improved laptop performance and it is increasingly
`common to see software development being done on a laptop. Laptops with a 133 MHz Pentium processor,
`1.2 Gigabyte hard disk, modular 6x CD ROM drive and 12.1 inch SVGA display are available in mid-1996,
`albeit at a price premium over comparable desktops. A survey in Computerworld [7] predicts that the
`number of workers using portable computers will expand from about one in five today to about one in three
`by the year 2000, and that 80% of portable users will use their portables as their primary machines, up
`from the current 303. This optimistic view is heavily dependent on laptops being able to overcome some
`key drawbacks. In addition to a price premium, laptops have another significant disadvantage compared to
`desktops-
`limited battery life.
`
`1.1 B ackground
`The major components of a typical laptop are the microprocessor (CPU), liquid crystal display (LCD),
`hard disk, system memory (DRAM), keyboard/mouse, CD ROM drive, floppy drive, I/O subsystem, audio
`subsystem and in the case of a mobile computer, a wireless network card. There are other components, but
`these are significant consumers of power. The CPU /motherboard of a laptop poses several design problems
`not found in a desktop. In addition to the power it consumes, there are also extreme thermal dissipation
`and space concerns. Because of these issues, laptop CPU's are still typically several months behind desktop
`CPU's in terms of processing power.
`The display is another major power consumer and again poses problems not found in a desktop machine.
`Unlike the Cathode Ray Tube (CRT) monitors used in all desktops, there are two major types of displays
`
`"This work was supported by the Hewlett-Packard Research Grants Program, the AT&T Foundation, NSF #CDA-92-14924,
`and DARPA #MDA972-95-1-0013.
`
`1
`
`Page 4 of 14
`
`

`

`used in laptops - passive dual scan (STN - Super Twisted Nematic) and active matrix (TFT - Thin Film
`Tuansistor). The dual scan display is cheaper and easier to manufacture but has poorer picture quality,
`especially when displaying fast-moving images. The active matrix display produces excellent picture quality
`but at a higher cost and greater power consumption. Active matrix displays are also more difficult to
`manufacture and very often have several defective pixels in them. Table 1 shows some of the differences
`between typical desktop and laptop displays1 .
`
`Display
`type
`Desktop
`Laptop
`
`Display size
`(diagonal inches)
`17''
`11.3"
`
`Weight Power Consumed Resolution Number
`(lbs)
`(Watts)
`(pixels)
`of colors
`47.4
`190 (max)
`1280x1024 unlimited
`2.7
`1.1
`800x600
`262,144
`
`Table 1: Comparison of typical laptop and desktop displays.
`
`In addition to reducing the physical size (i.e. form factor), laptop drive design also requires increased
`tolerance for mechanical shocks and the ability to spin up faster than desktop drives. The latter is necessary
`because laptop drives get spun down more often in order to reduce power consumption (this is explained in
`more detail in Section 4.1). Table 2 shows the contrast between typical2 desktop and laptop drives. The
`differences in power consumption are very significant, as we will see later in this paper.
`
`Type
`
`Desktop
`Laptop
`
`Capacity
`(MBytes)
`2113
`810
`
`Size
`(inches3)
`15.0
`8.3
`
`Weight Power (R/W) Power (Idle) Shock Tolerance
`(lbs)
`(Watts)
`(Watts)
`(Gs)
`1.0
`7.0
`3.2
`2
`0.4
`2.1
`1.0
`100
`
`Table 2: Comparison of laptop and desktop hard drives
`
`All of the subsystems of the laptop share a single battery as their primary source of power when not
`plugged into a wall outlet. There is usually an additional small battery for the real time clock and for
`memory backup, but this is not relevant to our discussion.
`A mobile computer (for the purposes of this paper, we define a mobile computer as a laptop computer
`with wireless networking capabilities) has severe limits on its electrical power usage, and a frequent complaint
`about mobile computers is the short lifespan of the battery [11]. Battery life is rarely more than 2-3 hours for a
`heavily-used laptop. Additional features, such as larger color displays, larger and faster hard disks, powerful
`processors, more memory and CD-ROM drives are becoming common, and result in increased electrical
`power demands. Unfortunately, laptop batteries are not advancing as rapidly as the other subsystems (for a
`comparison, see Figure 1). Each new feature, unless managed properly, will only further reduce battery life
`and inhibit untethered operation.
`
`1.2 Overview
`In the next section we discuss laptop batteries and show why batteries are unlikely to improve significantly in
`the forseeable future. Section 3 examines relative power consumption of the major subsystems of a laptop.
`In Section 4 we survey currently applied power management techniques for each of the subsystems, and
`discuss some of the problems associated with them. Section 5 outlines several new power management ideas.
`
`1The monitor is a Nanao FlexScan T2-17TS and the laptop display is Fujitsu's FLC29SVC6S Active Matrix LCD
`2Tbe desktop drive is a Seagate Medalist Pro 2.1 and the laptop drive is a Seagate Marathon 810
`
`2
`
`Page 5 of 14
`
`

`

`2 The Problem with Batteries
`
`A battery's performance can be characterized by the total amount of energy it can store (i.e. power x
`duration) and the physical dimensions (weight and size) of the battery. The total energy available from a
`battery is a design issue and is fixed at design time, along with its weight and size. The only value available
`for manipulation by the user is duration, or battery life. Short battery life plagues mobile computer users
`to whom the stark contrast between exponential and non-exponential technology improvement rates are
`particularly evident.
`
`16x
`
`,.,
`
`1b
`
`,.,
`
`0
`:;;
`
`ax
`
`6x
`
`4x
`
`2X
`
`IX
`
`/
`I!
`I _/~
`~ ,'
`<I:
`, , /
`,' it'
`_/'.,;~
`
`,
`,'
`
`.... ···
`~ .··
`~~ ....
`/
`~ ....
`'
`---- ~<)/
`___ .-·'
`_/
`----
`.·····
`,,'' ... -·············
`
`,--
`
`Battary (Energy Stored)
`
`6
`
`Time (Years)
`
`"' >-s
`I!! .. c..
`~ c G>
`
`-0
`
`E
`0
`
`E
`G>
`>
`~
`.5
`
`Figure 1: Approximate performance/capacity growth of major laptop components
`
`Figure 1 shows the approximate time it takes for the some of the major subsystems of a laptop to double
`in performance or capacity [2, 19]. In general, an unmanaged performance or capacity increase also indicates
`some increase in power consumption. Based on current research, the growth rate of battery power output
`through the year 2000 is expected to be no more than 20% [19].
`Advancements in power storage technology are slow in comparison to the other subsystems of a mobile
`computer. At present there is a shift from Nickel Cadmium (NiCd) and Nickel Metal Hydride (NiMH)
`batteries to Lithium Ion (Li-ion), which has a significantly better gravimetric energy density (energy per
`unit of weight) and longer recharge cycle life, as shown in Table 3. Li-ion batteries took many years to
`develop and have some disadvantages compared to NiCd batteries-they can require an additional 2-3 hours
`to reach their maximum charge compared to NiCd batteries, and require much stricter voltage regulation
`when charging [11]. Significant advances in battery technology take many years and are unable to keep pace
`with the growth of laptop power consumption.
`An important issue in mobile computing is battery weight. One impractical solution to the limited
`battery life problem would be to carry multiple spare batteries and simply replace them as necessary. There
`are also laptops that allow a user to install two batteries in the laptop, extending the laptop's usage but
`at the expense of additional weight and the loss of a modular bay. The most recent advances in laptop
`batteries are in the form of better "fuel gauging" of the battery, to give a more precise measure of the charge
`level and to estimate the time left before a recharge is needed. For example, Intel-Duracell's Smart Battery
`Specifications [15] propose a common information mechanism for laptop rechargeable batteries. Although
`this is a useful measure, it does not extend battery life from the user's point of view.
`Another issue that bas been brought up with laptop batteries is that of safety. The current generation of
`
`3
`
`Page 6 of 14
`
`

`

`Battery Characteristic
`Gravimetric Energy Density
`(Watt-hours/kg)
`Volumetric Energy Density
`(Watt-hours/liter)
`Recharge Life (Cycles)
`Memory Effect
`
`II Li-ion NiMH NiCd 11
`110
`65
`55
`
`260
`
`240
`
`210
`
`1200
`No
`
`1000
`Yes
`
`1000
`Yes
`
`Table 3: Some characteristics of common laptop batteries.
`
`Li-ion batteries have had mixed reviews in terms of safety. A laptop that is recharged/used in an insufficiently
`ventilated area may cause the battery to burn out. Dropping the laptop may cause a short-circuit that could
`start a fire in the laptop [23]. This is not mere speculation - for example, Apple Computer had to recall their
`Powerbook 5300 laptops [l] because the batteries ignited under certain conditions. Battery manufacturers
`claim otherwise - documents from them show that the batteries in laptops can survive significant abuse
`(short-circuit, puncturing, heat etc.) without any danger of fire or explosion [3]. These contradictory claims
`make it hard to decide on the safety of Li-ion batteries. It is not clear whether some of the problems are
`caused by bad design, or misuse by the user.
`We believe that these problems will increase as mobile computer use becomes more prevalent and batteries
`continue to increase in energy density. Again, the indications are that we must learn to use the available
`power more efficiently. Thus, unless there is a major advance in power management, the mobility of mobile
`computers is going to be severely restricted by short battery life.
`
`3 T he Balance Of Power
`
`1991-92
`
`386/25MHz
`8MBRAM
`85MBHD
`Backlit Di$p.
`
`---
`
`--- ---
`
`1993-94
`
`486125
`8MBRAM
`105MBHD
`Passive Color
`
`DISPLAY
`
`--- ---
`
`--
`
`..............
`..............
`
`...............
`
`CPU
`
`1995-96
`
`Penlium/90
`16MBRAM
`nOMBHD
`AcliveC<>lor
`
`70
`
`... 60
`;
`0
`CL so
`E
`
`* > (/) 40
`
`'ii
`~
`0 30
`0) s c 20
`
`CD
`
`CD
`~
`CD
`CL
`
`10
`
`HARD DRIVE
`
`1991
`
`1992
`
`1993
`
`1994
`
`1 995 Year
`
`Figure 2: Percentage of total power consumed by major components in a typical laptop computer.
`
`4
`
`Page 7 of 14
`
`

`

`Figure 2 shows the change over the past few years in the fraction of total power consumed by the major
`subsystems of a laptop computer. The x-axis represents recent years, and the data is for typical laptop3
`computers for that year. The specifications for a laptop we consider typical for that year are included in the
`bubbles above the graph lines. The values in the graph are mostly experimental values from [9, 16, 18] and
`measurements by the authors, although some estimations have been made for 1992. The jump in the power
`consumed by displays (1993 to 1994) is due to the move from grayscale to color displays. It should be noted
`that although the percentage of total power used by the display for the newest computer has decreased, the
`actual power used has increased due to the use of active matrix technology.
`The reduction in microprocessor power consumption is a result of advanced microprocessors with built-in
`power management and also the move to lower voltage designs. A more detailed explanation is provided in
`Section 4.3. Hard disks are consuming an increasing fraction of total system power as manufacturers focus
`on increasing capacity rather than reducing power consumption. The rest of the components of a typical
`laptop - keyboard, floppy drive etc. - typically consume less than 153 of the total power and are not shown
`on the chart. CD ROMs can use a significant amount of power, but are not included in the chart since they
`are used infrequently.
`
`Figure 3: Power consumption by each subsystem of a mobile computer.
`
`Figure 3 gives measured values of the power consumed by the major system components of a Toshiba
`410 CDT mobile computer (Pentium 90 with 8 MBytes of EDO RAM and AT&T WaveLAN PC Card).
`While this figure is based on actual measurements, the results are based on estimates of typical usage. The
`measured instantaneous power with the system idle (display on, HD spinning, WaveLAN receiving) was 14
`Watts which is small compared to a mains-powered appliance (e.g., a light bulb uses 60 Watts) but large for
`a system that is powered by a battery.
`The conclusion is that even though the Features/Dollar (and in some cases Features/Power Consumed)
`ratios have increased significantly, the overall power consumption of a laptop has also increased. One solution
`to this problem would be to decrease the capacity and/or performance of the individual components. For
`example, we could offer a 80286 laptop with 1 MB RAM, small grayscale display and a 10 MB disk that
`would offer superior battery life, but this machine might not load a current operating system, nor be useful
`in day-to-day laptop-based tasks. In fact, machines similar to this already exist as palmtop computers or
`Personal Digital Assistants (PDA) and have their own niche. Since reducing the features available on a
`computer is not economically feasible we are forced to intelligently manage system power use.
`
`3The computers measured were the Zenith MasterSport SLe (1991), Compaq LTE 386 (1993), Compaq 486 (1994) and
`Toshiba 410 CDT (1995-96)
`
`5
`
`Page 8 of 14
`
`

`

`4 Current Work in Power Management
`
`Currently, power management in laptops is performed in a variety of ways, including custom BIOS
`implementations, unique device configurations for specific operating systems, and various interpretations of
`the Advanced Power Management standard [15] (APM - a joint proposal from Intel and Microsoft). The
`APM BIOS is a layer of software that supports power management in computers with "power manageable"
`hardware. The APM specification defines the hardware independent software interface between system
`hardware and an operating system power management policy driver. Unfortunately, most manufacturers
`incorporate only a small subset of the APM features, and few operating systems actually use the features.
`Most laptops have simple power management schemes that allow the CPU to be run in "fast" or "slow"
`mode to conserve power (described in more detail in Section 4.3). In addition, the display can be blanked
`after being idle for a set amount of time, and the hard drive can be powered down when idle for several
`minutes. The user commonly has the option to set each of the parameters individually. The remainder
`of this section examines each major subsystem of a laptop and discusses the details of currently available
`management schemes.
`
`4 .1 Hard Disk Power Management
`The hard disk is one of the three big consumers in a laptop's power budget as can be seen in Figures 2
`and 3. Depending on its state, the disk can use up between one and three Watts-approximately 25% of
`total system power. Although the Power /MByte ratio has fallen rapidly in the past few years, the actual
`power consumed by a typical drive has remained approximately constant. Since some of the other laptop
`components have reduced their power consumption, the net effect (Figure 2) is that a laptop hard drive is
`taking an increasing percentage of total system power. Drive manufacturers driven by consumer demands
`have focused their efforts on increasing drive capacity, rather than decreasing overall power consumption.
`
`3.5
`
`3.0
`
`2.5
`
`1.0
`
`0.5
`
`CD Powerup - Electronics activated, platters off
`@ $pinup - Platters start spinning
`
`Idle - Platters spinning
`
`@
`© Seek - Actual data transfer
`© Spindown - Platters spirning down
`© Powerdown - Drive oil
`
`©
`
`©
`
`©
`
`Time (Seconds)
`
`Figure 4: Dynamic power consumption for a typical laptop-optimized hard disk.
`
`6
`
`Page 9 of 14
`
`

`

`Figure 4 is derived from Li, et. al's [16] measurements and illustrates the dynamic power consumption of
`a typical laptop-optimized hard drive (a Maxtor MXL-105 III). The total energy consumed is equal to the
`entire shaded area under the curve (i.e. Energy= Watts*Seconds). The largest power drain occurs during
`spin up, shown as area 2 in the figure. Spinning up a disk requires overcoming the mechanical inertia of the
`stationary platters of a disk. Once the platters are spinning, the power required to keep them spinning is
`much lower, as shown in area 3 of the figure. Disks optimized for laptops have a shorter spin up time than
`disks intended for ordinary PC's, to allow for frequent spin-downs to conserve energy. Of course, spinning(cid:173)
`down and spinning-up a disk too frequently can result in higher overall power consumption since the energy
`required to spin up a disk is much higher than that needed to keep the disk spinning. In theory, the best
`power conservation happens when a disk is spun down if the energy it would spend being idle (i.e. area 3)
`is equivalent to or greater than the additional cost of spinning it back up (the area in 2). As we will see,
`this isn't always feasible in practice.
`Research has been done on reducing the overall amount of energy used by a hard drive. This has ranged
`from simple algorithms that spin down the drive when it is idle for more than a set length of time (currently
`the most common method), to adaptive spin down techniques where the drive examines past access patterns
`to determine a dynamic spin down strategy.
`The fixed length spin down policy has one big advantage: it is very simple to implement. If the spinning
`disk is not accessed for idle_time minutes, the assumption is that there will be no disk accesses in the near
`future and the disk is spun down. It spins up again when there is a read/write request. This is the only
`widely available disk management method at present. Since the user fixes the value of idle_time and rarely
`readjusts it, the savings are very limited. Setting idle_time too low results in the user waiting for the drive
`to spin up too often. Too high a value of idle_time results in minimal