CN104484727A - Short-term load prediction method based on interconnected fuzzy neural network and vortex search - Google Patents
Short-term load prediction method based on interconnected fuzzy neural network and vortex search Download PDFInfo
- Publication number
- CN104484727A CN104484727A CN201510015222.5A CN201510015222A CN104484727A CN 104484727 A CN104484727 A CN 104484727A CN 201510015222 A CN201510015222 A CN 201510015222A CN 104484727 A CN104484727 A CN 104484727A
- Authority
- CN
- China
- Prior art keywords
- short
- neural network
- fuzzy neural
- interconnected
- term load
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 13
- 230000006870 function Effects 0.000 claims description 26
- 238000013277 forecasting method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 6
- 238000012804 iterative process Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 239000007787 solid Substances 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract 1
- 238000010845 search algorithm Methods 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 210000000746 body region Anatomy 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a short-term load prediction method based on an interconnected fuzzy neural network and vortex search. The method includes the steps of obtaining electrical loads of a plurality of history days; establishing a short-term load prediction model based on the interconnected fuzzy neural network through the electrical loads of the history days, wherein the model output is load prediction data of a day to be predicted; using the quadratic sum of the differences between the load prediction data of the day to be predicted and the load actual data of the day to be predicted as an error equation, using the error equation as a target function, optimizing the target function through the vortex search algorithm, and establishing a short-term load prediction model based on the interconnected fuzzy neural network and the vortex search after optimization is conducted; predicting the loads of the day to be predicted according to the short-term load prediction model. According to the method, the relevance between the load data of the history days is taken into consideration in the short-term electrical load prediction, the algorithm is simple, the running time is short, the accuracy of the short-term electrical load prediction is improved, the reliable foundation can be provided for the power grid dispatching control, and the solid guarantee is provided for the safe running of a power grid.
Description
Technical field
The present invention relates to power prediction technical field, particularly relate to a kind of short-term load forecasting method searched for based on Interconnected Fuzzy neural network and whirlpool.
Background technology
Fuzzy neural network is the system of a mixing, combines the semantic transparency of fuzzy system and the learning ability of neural network.In recent years, fuzzy neural network is more and more applied to the aspect such as system modelling and prediction, but the fuzzy neural network model that document nearly all at present proposes, all think that input variable is incoherent and independently, but short-term load forecasting is to predict the load of day to be predicted according to the load data of some history days, namely be associated between the historical load data for modeling, if the relevance between not considering for the load data of modeling, be difficult to the precision improving load prediction.Interconnected Fuzzy neural network is a kind of brand-new fuzzy neural network model, and it take into account the correlativity between input variable, thus can produce the fuzzy rule be associated and more effectively cover the input space be associated.Set up based on after the Short-term Load Forecasting Model of fuzzy neural network, also need to carry out to the parameter of model the advantage that optimizing could play Interconnected Fuzzy neural network better.A kind of optimizing algorithm obtains successful key and is, the method will average out in ability of searching optimum and local search ability, in the starting stage of optimizing search, information about search volume is little, therefore, in the starting stage, more need ability of searching optimum, when after algorithm search a to approximate optimal solution, the importance of local search ability rises, and so just can move closer to optimum solution.At present, common optimizing algorithm is mostly partial to ability of searching optimum or is partial to local search ability, seldom have and to average out between, and whirlpool searching algorithm can obtain good balance between global search and Local Search, and whirlpool searching algorithm is very simple, other common optimizing algorithms relatively, whirlpool searching algorithm does not need to arrange many extra parameters, just because whirlpool searching algorithm is simpler, the execution time of whirlpool algorithm is also relatively short, and to shorten working time be very important for short-term load forecasting, short-term load forecasting is very high to requirement of real-time, this just requires that the working time of prediction algorithm is short.Therefore, utilize the short-term load forecasting method based on Interconnected Fuzzy neural network and whirlpool search, short-term load forecasting precision can be improved.
Summary of the invention
Based on this, the invention provides a kind of short-term load forecasting method searched for based on Interconnected Fuzzy neural network and whirlpool;
Based on the short-term load forecasting method that Interconnected Fuzzy neural network and whirlpool are searched for, comprise the following steps:
Obtain the electric load of several history day;
The electric load of several history days described in utilization sets up the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network, and model exports the load prediction data for day to be predicted;
Using the quadratic sum of the difference of the load prediction data of the day to be predicted described in several and the load real data of day to be predicted as error equation;
Using described error equation as objective function, utilize whirlpool searching algorithm to carry out optimizing to described objective function, after optimizing terminates, namely establish the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network and whirlpool search;
According to the described Short-term Load Forecasting Model searched for based on Interconnected Fuzzy neural network and whirlpool, the load of day to be predicted is predicted.
Compared with general technology, the short-term load forecasting method that the present invention is based on Interconnected Fuzzy neural network and whirlpool search considers relevance between history daily load data in short-term electric load prediction, algorithm is comparatively simple, working time is shorter, improve the precision of short-term electric load prediction, can control to provide reliable basis for dispatching of power netwoks, the safe operation for electrical network provides solid guarantee.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the short-term load forecasting method that the present invention is based on Interconnected Fuzzy neural network and whirlpool search.
Embodiment
For further setting forth the technological means that the present invention takes and the effect obtained, below in conjunction with accompanying drawing and preferred embodiment, to technical scheme of the present invention, carrying out clear and intactly describing
Refer to Fig. 1, for the present invention is based on the schematic flow sheet of the short-term load forecasting method of Interconnected Fuzzy neural network and whirlpool search, the present invention is based on the short-term load forecasting method of Interconnected Fuzzy neural network and whirlpool search, comprising the following steps:
S101 obtains the electric load of several history day;
First, the electric load of several history days is obtained;
The electric load of several history days described in S102 utilizes sets up the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network, and model exports the load prediction data for day to be predicted;
As one of them embodiment, the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is a kind of three-decker;
The ground floor of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is input layer, and input variable is the part in the electric load of described several history days;
The input variable composition of vector X of the input layer described in note;
X＝[X(k)|k＝1,2,…,n]
Wherein, n is the input variable number of described input layer;
The second layer of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is fuzzy rule layer, described fuzzy rule layer utilizes multivariate Gaussian fuzzy membership functions to realize the former piece of fuzzy rule, described multivariate Gaussian fuzzy membership functions can be formed and rotate super ellipsoids body region, utilize the rotation super ellipsoids body region that formed can the input space that is associated of more effective covering, thus the required fuzzy rule quantity reduced;
Described multivariate Gaussian fuzzy membership function is defined as:
φ
i(X)＝exp(-d
i 2(X))
d
i 2(X)＝(X-M
i)
TΣ
i -1(X-M
i)
Wherein, φ
i(X) be i-th multivariate Gaussian fuzzy membership function, M
iand Σ
iaverage value vector and the covariance matrix of i-th fuzzy membership functions respectively;
Described covariance matrix Σ
ia matrix that is symmetrical and positive definite, therefore Σ
iinverse matrix Σ
i -1also be a matrix that is symmetrical and positive definite, thus can by Σ
i -1be decomposed into the product of two triangular matrixes, thus avoid time-consuming matrix inversion to calculate;
Σ
i -1＝Γ
i TΓ
i
Wherein, Γ
iit is a lower triangle square formation;
The third layer of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is output layer, the sum of products of the weight coefficient of the fuzzy rule that described output layer produces using described fuzzy rule layer and corresponding fuzzy rule is as output, and the weight coefficient of described fuzzy rule is as the consequent of described fuzzy rule;
The weight coefficient composition of vector W of the fuzzy rule described in note;
W＝[W(k)|k＝1,2,…,n]
T
Described fuzzy membership functions composition of vector Φ;
Φ＝[φ
i|i＝1,2,…,r]
Wherein, r is the number of described fuzzy membership functions;
The output of described output layer is also the output of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network, is designated as y;
S103 is using the quadratic sum of the difference of the load prediction data of the day to be predicted described in several and the load real data of day to be predicted as error equation;
As one of them embodiment, in the electric load of several described history days, choose N group data;
{(X
1,y
1 *),(X
2,y
2 *),…,(X
k,y
k *),…,(X
N,y
N *)}
Wherein, X
kfor the kth group input data of the input layer of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network, y
k *for corresponding X
kthe desired output of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network;
Error equation described in foundation;
Wherein, E is the output of described error equation, y
kfor corresponding X
kthe output of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network;
Described error equation as objective function, utilizes whirlpool searching algorithm to carry out optimizing to described objective function by S104, after optimizing terminates, namely establishes the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network and whirlpool search;
As one of them embodiment, utilizing before whirlpool searching algorithm carries out optimizing to described objective function, the parameter of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network determined required for first will pointing out;
A fuzzy membership functions had described in r, input dimension is the parameter vector to be determined of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network of n is α;
α＝[W(1),W(2),…,W(r),m
1 1,…,m
1 n,…,m
r 1,…,m
r n,ρ
1 11,ρ
1 21,ρ
1 22,…,ρ
i j1,…,ρ
i jj,…,ρ
r nn]
Wherein, m
i j(i=1 ..., r; J=1 ..., n) be the average vector M of described i-th fuzzy membership functions
ia jth element, ρ
i jc(i=1 ..., r; J=1 ..., n; C=1 ..., j) be described lower triangular matrix Γ
iin be positioned at jth row c arrange element;
If described parameter vector α has p element;
When the dimension of search volume is two dimension, utilize whirlpool searching algorithm to carry out track that optimizing search obtains is similar to the whirlpool that agitated liquid is formed, therefore this algorithm called after whirlpool is searched for, described error equation contains described parameter vector α to be determined, using described error equation as objective function, whirlpool searching algorithm described in utilization carries out optimizing, after searching process terminates, described parameter vector α to be determined can be determined, and then the Short-term Load Forecasting Model can set up based on Interconnected Fuzzy neural network and whirlpool search, the step that whirlpool searching algorithm described in utilization carries out optimizing comprises the following steps:
First initialization is carried out;
Described initialization comprises the following steps;
Initialization search center μ
0
Wherein, ul and ll is p dimensional vector, ul and ll represents the upper bound and the lower bound that p ties up optimizing space respectively;
Initialization search radius r
0;
Wherein max (ul) represents the maximal value of ul, and min (ll) represents the minimum value of ll;
Heart μ in the search
0the random generator of Gaussian distributed is utilized to produce one group of initial solution C at random
0(s);
Note t=0, t are the number of times of iterative loop, and initialization procedure terminates;
Error equation described in each initial solution being substituted into, the value of the described error equation obtained is designated as f (s), makes the minimum initial solution of the value of described error equation be designated as s
best, the minimum value of described error equation is designated as f (s
best);
Setting maximum iteration time is maxitr, enters iterative loop;
Described iterative loop comprises the following steps:
The random generator of Gaussian distributed is utilized to produce the candidate solution C of the t time iterative process at random
t(s);
From C
tthe solution s ' making the value of described error equation minimum is selected in (s), and with the search center μ of s ' as the t time iterative process
t;
If f (s ') <f (s
best), then make s
best=s ', makes f (s
best)=f (s ');
If f (s ') >=f (s
best), then keep s
bestvalue constant;
Make μ
t+1=s
best;
Note incomplete gamma function be γ (s, a);
Note function gamma (s, inverse function a) be gammaincinv (s, a);
Utilize function gammaincinv (s, search radius a) described in reduction;
r
t＝r
0·(1/s)·gammaincinv(s，a
t)
Wherein, t represents the t time described iterative loop, r
trepresent the search radius in the iterative loop described in the t time, s can value be 0.1;
Make iterations t increase by 1, iteration cycle process terminate;
Gammaincinv (s, a) balance that the good nature that function has makes whirlpool search can realize between global search and Local Search, the optimizing ability of thus described whirlpool searching algorithm is stronger, and the required parameter arranged of described whirlpool searching algorithm is less, and the operation time of thus described whirlpool searching algorithm is shorter;
Repeat described iteration cycle process, until reach described maximum iteration time;
After reaching described maximum iteration time, described searching process terminates, and described parameter vector α to be determined is determined, thus finally establishes the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network and whirlpool search;
S105, according to the described Short-term Load Forecasting Model searched for based on Interconnected Fuzzy neural network and whirlpool, predicts the load of day to be predicted;
The Short-term Load Forecasting Model searched for based on Interconnected Fuzzy neural network and whirlpool described in the input of the Power system load data of some history days being set up, exports the predicted load being day to be predicted;
Compared with general technology, the Short-term Load Forecasting Model that the present invention is based on Interconnected Fuzzy neural network and whirlpool search considers relevance between history daily load data in short-term electric load prediction, algorithm is comparatively simple, working time is shorter, improve the precision of short-term electric load prediction, can control to provide reliable basis for dispatching of power netwoks, the safe operation for electrical network provides solid guarantee.
The above embodiment only have expressed several embodiment of the present invention; it describes comparatively concrete and detailed; but therefore can not be interpreted as the restriction to the scope of the claims of the present invention; it should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise; some distortion and improvement can also be made; these all belong to protection scope of the present invention, and therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (4)
1., based on the short-term load forecasting method that Interconnected Fuzzy neural network and whirlpool are searched for, it is characterized in that, comprise the following steps:
Obtain the electric load of several history day;
The electric load of several history days described in utilization sets up the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network, and model exports the load prediction data for day to be predicted;
Using the quadratic sum of the difference of the load prediction data of the day to be predicted described in several and the load real data of day to be predicted as error equation;
Using described error equation as objective function, utilize whirlpool searching algorithm to carry out optimizing to described objective function, after optimizing terminates, namely establish the Short-term Load Forecasting Model based on Interconnected Fuzzy neural network and whirlpool search;
According to the described Short-term Load Forecasting Model searched for based on Interconnected Fuzzy neural network and whirlpool, the load of day to be predicted is predicted.
2. the short-term load forecasting method searched for based on Interconnected Fuzzy neural network and whirlpool according to claim 1, it is characterized in that, the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is a kind of three-decker;
The ground floor of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is input layer, and input variable is the part in the electric load of described several history days;
The second layer of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is fuzzy rule layer, and described fuzzy rule layer utilizes multivariate Gaussian fuzzy membership functions to realize the former piece of fuzzy rule;
The third layer of the structure of the described Short-term Load Forecasting Model based on Interconnected Fuzzy neural network is output layer, the sum of products of the weight coefficient of the fuzzy rule that described output layer produces using described fuzzy rule layer and corresponding fuzzy rule is as output, and the weight coefficient of described fuzzy rule is as the consequent of described fuzzy rule.
3. the short-term load forecasting method searched for based on Interconnected Fuzzy neural network and whirlpool according to claim 1, it is characterized in that, the described whirlpool searching algorithm that utilizes carries out optimizing to described objective function, comprises the following steps:
First initialization is carried out;
Described initialization comprises the following steps;
Initialization search center μ
0with search radius r
0, heart μ in the search
0neighbouring random generation one group of initial solution C
0(s), note t=0, t are the number of times of iterative loop, and described initialization procedure terminates;
Error equation described in each initial solution being substituted into, the value of the described error equation obtained is designated as f (s), makes the minimum initial solution of the value of described error equation be designated as s
best, the minimum value of described error equation is designated as f (s
best);
Setting maximum iteration time, enters iterative loop;
Described iterative loop comprises the following steps:
Produce the candidate solution C of the t time iterative process
t(s);
From C
tthe solution s ' making the value of described error equation minimum is selected in (s), and with the search center μ of s ' the t time iterative process the most
t;
If f (s ') <f (s
best), then make s
best=s ', makes f (s
best)=f (s ');
If f (s ') >=f (s
best), then keep s
bestvalue constant;
Make μ
t+1=s
best;
Reduce search radius, and the search radius after order reduction is r
t+1;
Make iterations t increase by 1, iteration cycle process terminate;
Repeat described iteration cycle process, until reach described maximum iteration time.
4. the short-term load forecasting method searched for based on Interconnected Fuzzy neural network and whirlpool according to claim 3, it is characterized in that, described reduction search radius utilizes the inverse function of incomplete gamma function to carry out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510015222.5A CN104484727A (en) | 2015-01-12 | 2015-01-12 | Short-term load prediction method based on interconnected fuzzy neural network and vortex search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510015222.5A CN104484727A (en) | 2015-01-12 | 2015-01-12 | Short-term load prediction method based on interconnected fuzzy neural network and vortex search |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104484727A true CN104484727A (en) | 2015-04-01 |
Family
ID=52759268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510015222.5A Pending CN104484727A (en) | 2015-01-12 | 2015-01-12 | Short-term load prediction method based on interconnected fuzzy neural network and vortex search |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104484727A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108842A (en) * | 2017-12-22 | 2018-06-01 | 国网能源研究院有限公司 | A kind of anti-benefit deviation neural net prediction method and device based on cost association |
| CN109617097A (en) * | 2018-12-26 | 2019-04-12 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision administering method based on fuzzy neural network algorithm |
| CN114021445A (en) * | 2021-10-29 | 2022-02-08 | 天津大学 | Ocean vortex mixed non-local prediction method based on random forest model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093285A (en) * | 2013-01-22 | 2013-05-08 | 清华大学 | Short-term load forecast method based on artificial neural network |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
-
2015
- 2015-01-12 CN CN201510015222.5A patent/CN104484727A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093285A (en) * | 2013-01-22 | 2013-05-08 | 清华大学 | Short-term load forecast method based on artificial neural network |
| CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
Non-Patent Citations (5)
| Title |
|---|
| A. BADRI ET AL: "Application of Artificial Neural Networks and Fuzzy logic Methods for Short Term Load Forecasting", 《ENERGY PROCEDIA》 * |
| BERAT DOGAN ET AL: "A new metaheuristic for numerical function optimization:Vortex Search algorithm", 《INFORMATION SCIENCES》 * |
| 于海燕: "基于模糊神经网络的电力负荷短期预测", 《电网技术》 * |
| 崔志坤: "基于模糊神经网络的短期电力负荷预测的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 赵宇红 等: "混合模糊神经网络在短期负荷预测中的应用", 《电力系统及其自动化学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108842A (en) * | 2017-12-22 | 2018-06-01 | 国网能源研究院有限公司 | A kind of anti-benefit deviation neural net prediction method and device based on cost association |
| CN108108842B (en) * | 2017-12-22 | 2022-04-05 | 国网能源研究院有限公司 | Cost association-based benefit deviation resistant neural network prediction method and device |
| CN109617097A (en) * | 2018-12-26 | 2019-04-12 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision administering method based on fuzzy neural network algorithm |
| CN109617097B (en) * | 2018-12-26 | 2022-06-21 | 贵州电网有限责任公司 | Three-phase load unbalance self-decision-making treatment method based on fuzzy neural network algorithm |
| CN114021445A (en) * | 2021-10-29 | 2022-02-08 | 天津大学 | Ocean vortex mixed non-local prediction method based on random forest model |
| CN114021445B (en) * | 2021-10-29 | 2023-07-28 | 天津大学 | Ocean vortex mixing non-locality prediction method based on random forest model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Arya et al. | Cascade‐IλDμN controller design for AGC of thermal and hydro‐thermal power systems integrated with renewable energy sources | |
| Zhao et al. | Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting | |
| Cai et al. | A hybrid CPSO–SQP method for economic dispatch considering the valve-point effects | |
| CN102270309B (en) | Short-term electric load prediction method based on ensemble learning | |
| Zhang et al. | A distributed approach for wind power probabilistic forecasting considering spatio-temporal correlation without direct access to off-site information | |
| Behera et al. | Solar photovoltaic power forecasting using optimized modified extreme learning machine technique | |
| Hassan et al. | Operational framework for recent advances in backtracking search optimisation algorithm: A systematic review and performance evaluation | |
| Zhang et al. | Robust optimization for dynamic economic dispatch under wind power uncertainty with different levels of uncertainty budget | |
| Raju et al. | Load frequency control of a multi‐area system incorporating distributed generation resources, gate controlled series capacitor along with high‐voltage direct current link using hybrid ALO‐pattern search optimised fractional order controller | |
| CN105023070A (en) | Output power prediction method of photovoltaic system | |
| CN103489038A (en) | Photovoltaic ultra-short-term power prediction method based on LM-BP neural network | |
| CN107844849A (en) | A kind of new energy output short term prediction method returned based on experience wavelet transformation with improving Gaussian process | |
| Alaee et al. | Stochastic transmission expansion planning incorporating reliability solved using SFLA meta-heuristic optimization technique | |
| Zheng et al. | Short‐term wind power prediction in microgrids using a hybrid approach integrating genetic algorithm, particle swarm optimization, and adaptive neuro‐fuzzy inference systems | |
| Bagheri et al. | A novel wind power forecasting based feature selection and hybrid forecast engine bundled with honey bee mating optimization | |
| Li et al. | A hybrid deep interval prediction model for wind speed forecasting | |
| Afshar | A cellular automata approach for the hydro-power operation of multi-reservoir systems | |
| Teferra et al. | Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization | |
| CN102831475A (en) | Sine normalization method for power forecast model of wind power plant | |
| Zhang et al. | Deep reinforcement learning for load shedding against short-term voltage instability in large power systems | |
| CN104484727A (en) | Short-term load prediction method based on interconnected fuzzy neural network and vortex search | |
| Kamal K et al. | Optimal scheduling of cascaded hydrothermal systems using a new improved particle swarm optimization technique | |
| Sahu et al. | Resilient frequency stability of a PV/wind penetrated complex power system with CSA tuned robust Type-2 fuzzy cascade PIF Controller | |
| Rajiv et al. | Gaussian process metamodels for floating offshore wind turbine platforms | |
| Vohra et al. | End-to-end learning with multiple modalities for system-optimised renewables nowcasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150401 |