光伏太阳能功率预测基于BP神经网络

most of the researches on PV power generation forecasting methods have problems such as long time for model training and propose an optimization. Using the BP(backpropagation) neural network, this learning algorithm is mainly applicable to multi-input, multi-output networks. It can rely on ready-made data and input and output without knowing the mathematical relationship between the mapping relationship in which input and output. The mapping relationship is learned and stored. In addition, BP neural networks have great advantages in dealing with non-linear problems and have strong generalization ability.

clear 
clc
warning off 
nntwarn off

global p     % Training input of data
global t     % Training output of data
global R     % The number of input node
global S2    % The number of output node
global S1    % The number of hidden layers node
global S     % Encoding length
S1=7;


day=[
24.28050041	79.18664551	118.7556229	0.498066664
24.27223969	79.11182404	107.4616165	0.453699917
24.32404137	79.12751007	113.1695709	0.483233273
24.28742981	79.02813721	119.4852142	0.522066772
24.29614639	78.63471985	124.2647552	0.548966765
24.44758797	77.61372375	123.2032242	0.555933356
24.5573349	75.72170258	133.1891327	0.597466707
24.71410561	75.81557465	151.4627838	0.67566663
24.79006767	73.11479187	169.4704132	0.749633372
24.90089226	72.61096191	176.5809174	0.782366931
25.03055954	71.96666718	161.6261444	0.697733402
25.05233383	70.77360535	134.8908539	0.600666761
25.07719231	71.31375122	136.8597565	0.641833305
25.19164848	70.52310944	149.4885712	0.729600012
25.29346275	69.68406677	160.9412384	0.81126672
25.44688034	68.67297363	168.1025848	0.882033348
25.60445404	65.91831207	185.1776276	0.970600069
25.74345016	64.28778076	212.1323547	1.094433427
25.86354637	63.09873199	226.2109528	1.161266565
26.0164547	63.28351974	237.5073547	1.208199978
26.09581757	60.10884094	239.8231812	1.193166733
26.22686195	58.52819061	250.0517273	1.229533315
26.39403152	56.94085312	257.771759	1.269633651
26.42829514	55.34542465	250.2635498	1.233933449
26.49137497	54.0851593	234.5327148	1.120566726
26.54426193	54.70727921	223.725235	1.053766608
26.50731087	53.55802155	215.5336304	1.01933372
26.42572403	52.25370789	212.4824524	0.556166649
26.43495941	52.74851227	210.2404633	1.031600118
26.44470978	53.16724396	228.1355286	1.151333332
26.57367516	54.28215408	266.3484192	1.397633553
26.65934563	52.6730957	328.9782715	1.674700022
26.80798531	51.54441071	377.1354675	1.886999965
26.97813797	50.69446945	411.3053589	2.02246666
27.07191086	51.11526489	394.967041	1.902066946
27.11913872	51.00314713	378.4665222	1.81556654
27.0648098	49.77826691	329.460144	1.595699906
26.8507061	50.18064499	280.3239441	1.349666595
26.78201103	50.40595245	230.4190521	1.123233438
26.7053833	50.91542816	195.2900696	0.946866691
26.47287369	50.59962845	184.5733795	0.901999712
26.42066765	51.92476273	182.5689392	0.942266643
26.31132507	51.17784882	186.7106934	1.005866766
26.26443672	51.77466965	191.8409729	1.056366682
26.33745766	51.60219193	206.1300964	1.162166715
26.35835075	51.94431686	217.2509308	1.210532904
26.32790756	51.76330566	219.2840881	1.198300123
26.3177166	51.44794083	215.0214691	1.153099895
26.38223457	51.89785767	218.2433319	1.181799889
26.37432671	51.58493805	240.7233124	1.29396677
26.38178635	51.38508987	245.8151703	1.339000106
26.39197159	50.84028625	222.4656067	1.207066774
26.45825195	51.78571701	202.6178894	1.097766876
26.44766617	51.99055862	203.1655121	1.11193347
26.43800354	51.35631943	216.8106995	1.173566461
26.52618027	51.7565