| 000 | 02869cam a2200337 a 4500 | ||
|---|---|---|---|
| 003 | EG-GiCUC | ||
| 005 | 20250223032657.0 | ||
| 008 | 210123s2020 ua dh f m 000 0 eng d | ||
| 040 |
_aEG-GiCUC _beng _cEG-GiCUC |
||
| 041 | 0 | _aeng | |
| 049 | _aDeposite | ||
| 097 | _aM.Sc | ||
| 099 | _aCai01.13.08.M.Sc.2020.Ne.S | ||
| 100 | 0 | _aNeveen Mohamed Hussien Mostafa Hassan | |
| 245 | 1 | 0 |
_aStates and power consumption estimation for nilm / _cNeveen Mohamed Hussien Mostafa Hassan ; Supervised Mohsen A. Rashwan , Ahmed Mohamed Hesham Mohamed Riad |
| 246 | 1 | 5 | _aتحديد الحالات والقوة المستهلكة لمراقبة الحمل غير التدخلية |
| 260 |
_aCairo : _bNeveen Mohamed Hussien Mostafa Hassan , _c2020 |
||
| 300 |
_a75 P. : _bcharts , facimiles ; _c30cm |
||
| 502 | _aThesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Electronics and Communication | ||
| 520 | _aNon-intrusive load monitoring is a technique which targets controlling the energy consumption in order to provide power saving. Non-intrusive load monitoring specifically aims to separate household power consumption using feature identification signature. We analyze each device signature based on its active power load curve. For an electrical home appliances network which consists of a known set of devices, Hidden Markov Model is used for system modeling. Then our proposed method is introduced to enhance determining and defining all states for each appliance. Weclassify each device into a set of states according to the power consumption (not only the ON and OFF states) in the form of different power levels. AMPds dataset (the Almanac of minutely power dataset) is used in training and testing for six selected home devices in a certain household and is also compared to GREEND dataset showing the advantage of the variable observed power readings with those of constant power readings. Each device has different number of states.The proposed mechanism is then used to minimize these states after learning the behavior of each state into OFF and ON states only. In order to test our algorithm and processing capability, we increase the number of the home appliances where and we use devices that have similar power consumption and power load identification signature. We show that the proposed method provides high accuracy results on the system level, the device level, state inference, power and state sequence estimation | ||
| 530 | _aIssued also as CD | ||
| 653 | 4 | _aHidden Markov Model | |
| 653 | 4 | _aLoad dis-aggregation | |
| 653 | 4 | _aNon-Intrusive Load Monitoring (NILM) | |
| 700 | 0 |
_aAhmed Mohamed Hesham Mohamed Riad , _eSupervisor |
|
| 700 | 0 |
_aMohsen A. Rashwan , _eSupervisor |
|
| 856 | _uhttp://172.23.153.220/th.pdf | ||
| 905 |
_aNazla _eRevisor |
||
| 905 |
_aShimaa _eCataloger |
||
| 942 |
_2ddc _cTH |
||
| 999 |
_c79635 _d79635 |
||