CN102662325A - Improved adaptive learning tree power supply management method - Google Patents
Improved adaptive learning tree power supply management method Download PDFInfo
- Publication number
- CN102662325A CN102662325A CN2012101358382A CN201210135838A CN102662325A CN 102662325 A CN102662325 A CN 102662325A CN 2012101358382 A CN2012101358382 A CN 2012101358382A CN 201210135838 A CN201210135838 A CN 201210135838A CN 102662325 A CN102662325 A CN 102662325A
- Authority
- CN
- China
- Prior art keywords
- free time
- time length
- node
- value
- length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power supply management forecast method for a learning tree based on an idling time length, and relates to a network technology. An idling time length node is added on the basis of the conventional adaptive learning tree structure based on the probability; an idling time length value is used as a forecast basis, and an equipment entering mode at the idling time is controlled by using a corresponding low power consumption state; after the idling time, the idling time length forecast value is weighted and updated by adopting actual historical probability statistics of various power consumption states in a learning tree; and by adopting an N system method, the matching process for historical paths in the learning tree is avoided. According to the method, relatively high accuracy of the idling time length forecast value of the equipment is guaranteed, so that the equipment is relatively low in power consumption; and furthermore, the complexity of an adaptive learning tree forecasting and updating process is reduced.
Description
Technical field
The present invention relates to artificial intelligence field and built-in field, especially adopt the intelligent predicting method to carry out the built-in field of device power supply (DPS) management.
Background technology
In today of embedded technology high speed development, along with the diversification of mobile terminal function, power problems has caused the many attention of People more and more, and power management techniques has become the important indicator of weighing a mobile terminal performance.(Dynamic Power Management DPM) has obtained increasing research as can or closing to reach the technology of saving electric power by operating system opertaing device electric power starting to dynamic power management.Generally speaking, the DPM strategy is divided into 3 types: overtime strategy, predicting strategy and randomized policy.The basic thought of overtime strategy is to preestablish a series of timeout thresholds, in case the continuous idle time surpasses this threshold value, just switches to respective sleep mode, and threshold value can be fixed, also can be with the variation self-adaptation adjustment of system loading.In a single day predicting strategy predicts this free time and can remedy state and switch the power consumption penalty bring and just equipment is placed certain low power consumpting state.Randomized policy then be with DPM as the random optimization problem, through setting up decision model at random the behavior of equipment is described.
Adaptive learning tree (Adaptive Learning Tree; Be abbreviated as ALT) be a kind of predict model that early proposes, this tree is made up of decision node (representing with circle), predicted branches (dotting), historical branch (representing with solid line) and leaf node (representing with rectangle).Each decision node is represented the residing state of equipment in one period free time in the past, and predicted branches is used for connecting decision node and leaf node, and historical branch is used for connecting adjacent decision node, and leaf node is represented the degree of confidence (seeing accompanying drawing 1) of equipment state.ALT has mainly adopted free time cluster IPC principle (Idle Period Clustering).
Free time is defined as: get into idle condition to its time that exits from idle status and continued from system or equipment.Likewise, holding time then is its continuous in running order institute's duration.Therefore, the global behavior of system can be simulated with the time series of one group of working time and free time.When a free time, length was enough offset the caused power consumption of device shutdown, system can obtain Power Cutback by closing device.
Suppose
nBe the low power consumpting state number that system has, then system has altogether
n+ a kind of power supply status.Set (
corresponding working state of representing power supply status with
; All the other and the like); The system state rank is high more so; Its state power consumption is low more, and the power consumption of switching each other with duty is high more.To the free time of confirming
, its power consumption
is calculated as follows:
(1)
Wherein,
Be to switch to from idle condition
The time of state,
Be from
State switches to the time of idle condition,
With
Then be to switch power consumption levels accordingly,
The representative state
iUnder power consumption.Lose the hypothesis that lower state power consumption has higher switching power consumption simultaneously based on low more power consumption state,
Should more than or equal to
And when it is equal, obtain
Represented state
iAnd state
i+ 1 threshold limit value.Through like this; Can ask for each threshold time to adjacent power consumption state; Threshold value with
between the expression power consumption state
and
, then:
Thereby with the threshold value that obtains is boundary, and time coordinate can be divided into
n + 1 interval can be with a given free time and some intervals index value
Associate, confirm the optimal power state that equipment should get into this:
Therefore; One group free time sequence can be converted into
value sequence (
) of the best low power consumpting state of representing each free time, this process is called IPC.
ALT strategy hypothesis equipment has under idle condition
N(total status number does to plant low power consumpting state
N+ a kind, comprise a kind of normal operating conditions), then based on IPC (Idle Period Clustering) principle with each section idle condition time span of equipment corresponding to an integer numerical value
Represent, and each
Value corresponding again the optimal operational condition of equipment.For
N+ a kind of state can be used state set
Represent all states, for length do like this
mA string historical free time path sequence, just can use
Represent, wherein
,
Represent recent free time
Value is then according to this historical series
Predict that next contingent free time is corresponding
Value.So ALT utilizes historical free time path sequence to predict the process of the length of free time next time.
ALT has following advantage: the one, and this tree root is border free time historical record and setting up factually, on macroscopic view, the equipment behaviour in service is had preferably and holds; The 2nd, ALT can upgrade automatically; Reasonable changing condition (Eui-Young Chung, Benini, the L. that has reflected that equipment uses; De Micheli G. Dynamic power management using adaptive learning tree; Computer-Aided Design, 1999,7 (11): 274-279.).For the predicting strategy research of adopting ALT, mainly contain at present based on the prediction of device physical status historical record with based on free time length forecast method.
Predict that about using existent method is to carry out predicted state according to probability to select based on the device physical status historical record; Then accurately whether upgrade the respective path probability according to predicting (He Kejia. based on the adaptive learning predicting strategy of probability; Computer engineering; 2010,36 (10): 215-220.).This method has been kept one and has been upgraded actual free time situation that prediction window writes down historical equipment under the given path; Select to occur in the window maximum records as predicting the outcome next time; Abandon the oldest record during renewal; Obviously, a kind of increase of state probability will inevitably cause the reduction of other several kinds of state probabilities.
Aspect free time length Forecasting Methodology; Existing document proposes to predict free time length and upgrade the predicted time (Qi Longning on this path based on the time expectation value; Hu Chen, Zhang Zhe etc. based on the DPM predicting strategy of time expectation table, Circuits and Systems journal; 2007,2 (12): 89-93.).This method is in low power consumpting state to equipment at every turn
iThe time energy consumption and free time
tRelationship description (Sandy Irani; Sandeep Shukla; Rajesh Gupta. Competitive Analysis of Dynamic Power Management Strategies for Systems with Multiple Power Saving States. Proceedings of the 2002 Design; Automation and Test in Europe Conference and Exhibition; 2002,2:1530-1591.), suppose that the free time distribution has probability density function
, the energy consumption expectation the when equipment of obtaining is in state i is shown in formula (1):
(4)
Wherein
Be that equipment is in state
iThe time power consumption,
Be that equipment is from state
iSwitch to the power consumption penalty of normal operating conditions,
It is the free time expectation.Thereby draw with free time expectation value as basis for forecasting, can obtain minimum power consumption penalty in theory.In the renewal process; This strategy takes the exponential average method that
value is carried out the weighting renewal, to carry out prediction next time.The computing formula of exponential average forecast updating algorithm is following:
(5)
Wherein
aBe a constant between 0 to 1, the expression with last time actual value degree of closeness,
aBig more, the expression predicted value is more near the actual value of last time.
There is corresponding defects in above-mentioned two kinds of methods: there is higher power consumption in the former, and the prediction free time length update method that the latter uses can cause and the deviation of reality is bigger, also causes it to have higher power consumption.
Summary of the invention
The present invention is directed to the high power consumption of prior art, defective that predicated error is bigger, propose a kind of improvement adaptive learning tree power management Forecasting Methodology, the method that can obtain more low-power consumption loss is provided for the portable terminal peripheral power supply management.
The present invention increases free time length node as basis for forecasting in based on the learn trees of probability, adopt the probability statistics of historical free time that it is upgraded, adopt "
NSystem " several index values of preserving historical path sequence.Concrete technical scheme is following:
In based on the learn trees structure of probability, increase a leaf node of representing free time length node on each decision node of the bottom, leaf node is the brotgher of node with the state probability node that is connected based on decision node in the learn trees structure of probability;
According to free time length and corresponding power consumption state probability, the last time of in learn trees, preserving predicted free time length, call formula:
Calculate this prediction free time length value, learn trees is upgraded according to this prediction free time length value.Wherein, The probability that on behalf of the corresponding power consumption state of actual free time length,
in learn trees, preserve;
is actual free time length;
for predicting the free time length value last time,
is this prediction free time length value; When free time occurred, opertaing device got into low power consumpting state; The device free time finishes, and opertaing device gets into the use request of mode of operation with the response user.
With each historical path sequence corresponding one unique "
NSystem " (whole historical path sequence are for (being assumed to be under the length of setting
L), the length of the power consumption state that obtains does
LAll combinations; In the implementation procedure, historical path sequence is what close on most in the past
LThe length that the residing actual power loss state of equipment is formed successively in individual free time does
LSequence), as to have 2 kinds of low power consumpting state length be that 3 historical path sequence 210 can convert " three-shift " number into
=2*3*3+1*3=21.
The effect of this index value is to save complicated route matching process; Each index value has just been represented a historical path sequence, has all preserved the state probability and the prediction free time length value of corresponding historical path sequence in the structure during program realizes under each index value.With the relation of prediction free time length be exactly, obtained historical path sequence corresponding index value, just can directly get access to the prediction free time length value under this index value.
The present invention uses historical outline statistics to upgrade free time length, can be more accurate to following free time length prediction, thus the low power consumpting state of better controlling free time equipment should getting into when arriving is realized more Power Cutback; In the learn trees renewal process, adopt "
NSystem " form, make each historical path to represent, thereby avoided the complicacy of process with a shaping numerical value, promoted the efficient that realizes.
Description of drawings
Fig. 1 is original adaptive learning Tree-structure Model;
Fig. 2 is based on probability adaptation learn trees structural model;
Fig. 3 is the model of utilization structure of the present invention;
Fig. 4 is a schematic flow sheet of the present invention.
Embodiment
Below in conjunction with accompanying drawing enforcement of the present invention is specified.
Fig. 1 is original adaptive learning Tree-structure Model.
Set up the learn trees structural model according to free time equipment state of living in, equipment state degree of confidence.
Learn trees is made up of decision node (representing with circle), predicted branches (dotting), historical branch (representing with solid line) and leaf node (representing with rectangle).Decision node representes to pass by equipment state of living in one period free time, and leaf node is represented the degree of confidence of equipment state, and predicted branches connects decision node and leaf node, and historical branch connects adjacent decision node.
Fig. 2 is based on probability adaptation learn trees structural model.
This tree is made up of decision node (representing with circle), predicted branches (dotting), historical branch (representing with solid line) and leaf node (representing with rectangle).Decision node representes to pass by equipment state of living in one period free time, and leaf node is represented the equipment state probability, and predicted branches is used for connecting decision node and leaf node, and historical branch is used for connecting adjacent decision node.
Fig. 3 is the learn trees structural model that the present invention sets up.
Increase a leaf node of representing free time length node on each decision node of learn trees of the present invention bottom in based on the learn trees structure of probability, the state probability node that leaf node is connected with decision node is the brotgher of node.This leaf node comprises state probability node and prediction free time length node.
Learn trees structure of the present invention comprises decision node (representing with circle), predicted branches (dotting), historical branch (representing with solid line) and leaf node (representing with rectangle) equally; Except that the structure that keeps based on the probability adaptation learn trees, the free time length of leaf node (with field
expression) expression prediction next time is set also.In based on the learn trees structure of probability, increase a leaf node of representing free time length node on each decision node of the bottom, leaf node is the brotgher of node with the state probability node that is connected based on decision node in the learn trees structure of probability.As shown in the figure, rectangle leaf node that decision node e is connected part (comprise state probability node 1/5,1/5,3/5 and
) representative carries out certain state in the pilot process, decision node
mThe rectangle leaf node that connected part (comprise state probability node 1/3,1/3,1/3 and
) the expression original state.
Fig. 4 is a schematic flow sheet of the present invention.Specifically comprise the steps:
Initialization; In learn trees, obtain next time the free time length value according to the historical path that provides; Free time arrives, and opertaing device gets into corresponding low power consumpting state; Free time finishes, according to this actual free time length value with learn trees in historical probability statistics renewal learn trees in the predicted value of respective paths, and opertaing device entering mode of operation; Repeat above step, when equipment turn-offs, finish whole flow process.
(1) initialization study tree tree structure
Set up the historical series index, set historical path sequence length, (whole historical path sequence are for (being assumed to be under the length of setting for structure variablees such as the predicted state probability of the whole historical path sequence of initialization and predicted time length information
L), the length of the power consumption state that obtains according to the IPC principle does
LAll combinations; In the implementation procedure, historical path sequence is what close on most in the past
LThe length that the residing actual power loss state of equipment is formed successively in individual free time does
LSequence).
(2) confirm free time length according to historical series
When equipment is in running order; Obtain to predict the length value of free time according to the historical path sequence corresponding index value in the learn trees next time: promptly the save value of
field in the learn trees (it is complete 0 that initial historical path sequence is chosen as, as length be 3 historical path sequence is
).
(3) when free time occurs, opertaing device gets into low power consumpting state
According to the free time length predicted value of obtaining; Through relatively being divided into a low power consumpting state that adopts the equipment that the IPC principle obtains with equilibration time; Thereby when free time arrived, the device power supply (DPS) management function opertaing device that provides through calling system got into this state model (as calling SetDevicePower () function under the WinCE system).
(4) learn trees upgrades
The actual free time end of equipment, the historical path sequence of calculating preseting length "
NSystem " index value (be similar to binary computing method, as to have 2 kinds of low power consumpting state length is that 3 historical path sequence 210 can convert " three-shift " number into
=2*3*3+1*3=21); (the probability denominator of all state probability nodes adds 1 to upgrade the predicted state probability node of preserving in the learn trees structure under this index value; The state probability node molecule that equipment actual power loss state is corresponding adds 1); Upgrade prediction free time length according to new predicted state probability; Method is following: adopt actual free time length multiply by probability that the corresponding power consumption state of actual free time length preserves in learn trees add prediction free time length multiply by 1 deduct actual free time length correspondence the power consumption state probable value of in learn trees, preserving, promptly call formula:
Calculate this prediction free time length value, learn trees is upgraded.Wherein, The probability that on behalf of the corresponding power consumption state of actual free time length,
in learn trees, preserve;
is actual free time length;
for predicting the free time length value last time,
is this prediction free time length value.
"
NSystem " effect of index value is in the realization of specific procedure, can save complicated route matching process; and each index value has just been represented a historical path sequence, has all preserved the state probability of corresponding historical path sequence during program realizes in each index value structure down and has predicted the free time length value.With the relation of prediction free time length be exactly, obtained historical path sequence corresponding index value, just can directly get access to the prediction free time length value under this index value.
(5) opertaing device gets into mode of operation
The device free time finishes, and the device power supply (DPS) management function opertaing device that provides through calling system gets into the use request (as WinCE system under call SetDevicePower () function) of mode of operation with the response user.
(6) repeat the 2nd to the 5th step and get into off state up to equipment.
Below illustrate:
Length is obeyed under the situation of even distribution occasion probability the inventive method is tested at one's leisure.Concrete parameter is provided with as follows: the power consumption of each state is respectively
;
;
; Switch power consumption and be respectively
;
;
; Historical series length is set to 3; Moving window length is set to 10, is 0.5 based on the exponential average coefficient a value in the expectation value strategy; Estimate the performance of dynamic power management Forecasting Methodology, the main usually contention of using, promptly Forecasting Methodology produces the ratio of power consumption and the desirable power consumption of off-line, and contention is low more, shows that the effect of Power Cutback is remarkable more.Adopt above parameter to be provided with and existingly compare test, to obtain true objective appraisal based on time expectation value strategy to the present invention.
Concrete contention comparing result is seen table one.The contention that method 1 expression the present invention can reach in the table; Prior art is adopted in method 2 expressions; Based on the contention that time expectation value method can reach, data can be found out from table, and the power consumption of two kinds of methods is higher than the desirable power consumption 20.9% and 23.69% of off-line respectively; The effect of Power Cutback of the present invention is lower than based on 2.79 percentage points of expectation value strategies, has better reached the saving of power consumption.
Table 1 evenly divides to plant predicts the contention contrast
| Method | 1 | |
|
1.21 | 1.2314 | |
|
1.2127 | 1.2394 | |
|
1.2105 | 1.2409 | |
Experiment number 4 | 1.2065 | 1.2365 | |
Experiment number 5 | 1.2055 | 1.2365 | |
Mean value | 1.209 | 1.2369 |
Claims (4)
1. one kind is improved adaptive learning tree power management Forecasting Methodology; It is characterized in that: in based on the learn trees structure of probability, increase a leaf node of representing free time length node on each decision node of the bottom, the state probability node that leaf node is connected with decision node is the brotgher of node; Set up the historical series index; Set historical path sequence length; Confirm actual free time length according to historical series; Predicted free time length
probability
, the last time of in learn trees, preserving according to actual free time length
and corresponding power consumption state thereof; Call formula:
calculate this prediction free time length value, learn trees is upgraded; When free time occurred, opertaing device got into low power consumpting state; The device free time finishes; Opertaing device gets into the use request of mode of operation with the response user; Wherein, The probability that on behalf of the corresponding power consumption state of actual free time length,
in learn trees, preserve;
is actual free time length;
for predicting the free time length value last time,
is this prediction free time length value.
2. method according to claim 1 is characterized in that, said learn trees is upgraded is specially: the historical path sequence of calculating preseting length "
NSystem " index value, upgrade the predicted state probability node of preserving in the study tree construction under this index value, upgrade this prediction free time length according to new predicted state probability.
3. method according to claim 2 is characterized in that, calculate "
NSystem " index value specifically comprises, history free time discrete value sequence is regarded as "
N" the system number, obtain the decision node index value under the current sequence through addition and multiplying.
4. method according to claim 2 is characterized in that, each index value is represented a historical path sequence, and whole historical path sequence are the length of setting
LThe length of the power consumption state that obtains according to the IPC principle down, does
LAll combinations, when equipment is in running order, obtain the prediction length value of free time according to the historical path sequence corresponding index value in the learn trees.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210135838.2A CN102662325B (en) | 2012-05-04 | 2012-05-04 | Improved adaptive learning tree power supply management method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210135838.2A CN102662325B (en) | 2012-05-04 | 2012-05-04 | Improved adaptive learning tree power supply management method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102662325A true CN102662325A (en) | 2012-09-12 |
CN102662325B CN102662325B (en) | 2014-10-15 |
Family
ID=46771831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210135838.2A Active CN102662325B (en) | 2012-05-04 | 2012-05-04 | Improved adaptive learning tree power supply management method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102662325B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
WO2017084385A1 (en) * | 2015-11-16 | 2017-05-26 | 广州广电运通金融电子股份有限公司 | Self-service equipment energy saving control method and device |
CN114048197A (en) * | 2022-01-13 | 2022-02-15 | 浙江大华技术股份有限公司 | Tree structure data processing method, electronic equipment and computer readable storage device |
CN116610204A (en) * | 2023-07-19 | 2023-08-18 | 碳丝路文化传播(成都)有限公司 | Power management method, system, electronic equipment and medium for electric equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1696847A (en) * | 2005-06-14 | 2005-11-16 | 上海理工大学 | Power supply management method for electronic apparatus |
US20080091308A1 (en) * | 2006-07-27 | 2008-04-17 | Jeremy Henson | Devices, Systems, and Methods for Adaptive RF Sensing in Arc Fault Detection |
CN101754437A (en) * | 2008-12-19 | 2010-06-23 | 英特尔公司 | Handling sensors in a context aware platform |
CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
JP2012034444A (en) * | 2010-07-28 | 2012-02-16 | Toshiba Corp | Power supply-demand planning device and method thereof |
-
2012
- 2012-05-04 CN CN201210135838.2A patent/CN102662325B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1696847A (en) * | 2005-06-14 | 2005-11-16 | 上海理工大学 | Power supply management method for electronic apparatus |
US20080091308A1 (en) * | 2006-07-27 | 2008-04-17 | Jeremy Henson | Devices, Systems, and Methods for Adaptive RF Sensing in Arc Fault Detection |
CN101754437A (en) * | 2008-12-19 | 2010-06-23 | 英特尔公司 | Handling sensors in a context aware platform |
JP2012034444A (en) * | 2010-07-28 | 2012-02-16 | Toshiba Corp | Power supply-demand planning device and method thereof |
CN102436630A (en) * | 2010-07-28 | 2012-05-02 | 株式会社东芝 | Power supply-demand planning device and method thereof |
CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103853918A (en) * | 2014-02-21 | 2014-06-11 | 南京邮电大学 | Cloud computing server dispatching method based on idle time prediction |
CN103853918B (en) * | 2014-02-21 | 2017-01-04 | 南京邮电大学 | A kind of cloud computing server dispatching method based on free time prediction |
WO2017084385A1 (en) * | 2015-11-16 | 2017-05-26 | 广州广电运通金融电子股份有限公司 | Self-service equipment energy saving control method and device |
US10394302B2 (en) | 2015-11-16 | 2019-08-27 | Grg Banking Equipment Co., Ltd. | Self-service equipment energy saving control method and device |
CN114048197A (en) * | 2022-01-13 | 2022-02-15 | 浙江大华技术股份有限公司 | Tree structure data processing method, electronic equipment and computer readable storage device |
CN116610204A (en) * | 2023-07-19 | 2023-08-18 | 碳丝路文化传播(成都)有限公司 | Power management method, system, electronic equipment and medium for electric equipment |
CN116610204B (en) * | 2023-07-19 | 2023-11-14 | 碳丝路文化传播(成都)有限公司 | Power management method, system, electronic equipment and medium for electric equipment |
Also Published As
Publication number | Publication date |
---|---|
CN102662325B (en) | 2014-10-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sedghi et al. | Distribution network expansion considering distributed generation and storage units using modified PSO algorithm | |
CN107516170B (en) | Difference self-healing control method based on equipment failure probability and power grid operation risk | |
CN110930016A (en) | Cascade reservoir random optimization scheduling method based on deep Q learning | |
CN107578288B (en) | Non-invasive load decomposition method considering user power consumption mode difference | |
CN104009494B (en) | A kind of environmental economy power generation dispatching method | |
CN102662325B (en) | Improved adaptive learning tree power supply management method | |
CN102715061B (en) | Method and device for energy-saving irrigation | |
CN110490429A (en) | Based on SSA algorithm intelligent building micro-capacitance sensor household loads fast dispatch method | |
CN112734135B (en) | Power load prediction method, intelligent terminal and computer readable storage medium | |
CN102395146A (en) | Multiple-target monitoring oriented method for sensing topology construction in wireless sensor network | |
CN116974768A (en) | Calculation power scheduling method based on deep learning | |
CN112836911A (en) | Method and device for determining cell energy-saving parameter, electronic equipment and storage medium | |
CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
CN115689069A (en) | Power grid dispatching control method and system based on artificial intelligence | |
Dang et al. | A unified stochastic model for energy management in solar-powered embedded systems | |
CN110380407B (en) | Power distribution network operation optimization method considering agricultural electric irrigation and drainage loads | |
CN116739187A (en) | Reservoir optimal scheduling decision method, device, computer equipment and storage medium | |
Zhang et al. | Structure-aware stochastic load management in smart grids | |
CN109359671B (en) | Classification intelligent extraction method for hydropower station reservoir dispatching rules | |
CN113783179B (en) | Power grid load prediction and optimization method | |
Xia et al. | One-day-ahead load forecast using an adaptive approach | |
CN112584386A (en) | 5G C-RAN resource prediction and allocation method and system | |
Chen et al. | Short-term power load model based on combined optimization of cuckoo algorithm and lightGBM | |
CN114650190B (en) | Energy-saving method, system, terminal equipment and storage medium for data center network | |
CN114742285B (en) | Construction method and application of resident power consumption mode prediction model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |