Page - X - in Short-Term Load Forecasting by Artificial Intelligent Technologies

pattern has been learned, there is a lack of systematic explanation onhow the accurate forecasting resultsareobtained;supportvectorregression(SVR)modelcouldacquiresuperiorperformanceonly withtheproperparametersdeterminationsearchalgorithms. Therefore, it isessential toconstructan inferencesystemtocollect thecharacteristic rules todetermine thedatapatterncategory. Secondly, it should assign an appropriate approach to implement forecasting for (1) ARIMA or exponential smoothing approaches, the only option is to adjust their differential or seasonal parameters; (2) ANN or SVR models, the forthcoming problem is how to determine the best parameter combination (e.g., numbers of hidden layer, units of each layer, learning rate; or hyper-parameters) to acquire superior forecasting performance. Particularly, for the focus of this discussion, inordertodeterminethebestparametercombination,aseriesofevolutionaryalgorithms should be employed to test which data pattern ismost familiar. Based on experimental findings, thoseevolutionaryalgorithms themselvesalsohavemerits anddrawbacks, for example,GAandIA are excellent for regular trenddatapatterns (real number) [2,3], SAexcelled forfluctuationornoise datapatterns(realnumber)[4],TAisgoodforregularcyclicdatapatterns(realnumber)[5],andACO isgoodfor integernumbersearching[6]. It is possible to build an intelligent support system to improve the efficiency of hybrid evolutionary algorithms/models or to improve them by theoretical innovative arrangements (chaotizationandcloudtheory) inall forecasting/prediction/classificationapplications. Firstly,filter the original data by thedatabasewith awell-defined characteristic set of rules for thedatapattern, such as linear, logarithmic, inverse, quadratic, cubic, compound, power, growth, exponential, etc., to recognize the appropriate data pattern (fluctuation, regular, or noise). The recognition decision rules should include two principles: (1) The change rate of two continuous data; and (2) the decreasingorincreasingtrendofthechangerate, i.e., thebehavioroftheapproachedcurve. Secondly, select adequate improvement tools (hybrid evolutionary algorithms, hybrid seasonal mechanism, chaotization of decision variables, cloud theory, and any combination of all tolls) to avoid being trappedinalocaloptimum, improvement toolscouldbeemployedintotheseoptimizationproblems toobtainan improved, satisfiedsolution. Thisdiscussionof theworkbytheauthorof thisprefacehighlightswork inanemergingareaof hybrid advanced techniques that has come to the forefront over the past decade. These collected articles in this text span a great deal more of cutting edge areas that are truly interdisciplinary innature. References 1. Fan,G.F.;Peng,L.L.;Hong,W.C.Short termloadforecastingbasedonphasespacereconstruction algorithmandbi-squarekernel regressionmodel.AppliedEnergy2018,224,13–33. 2. Hong, W.C. Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting.NeuralComputingandApplications2012,21,583–593. 3. Hong,W.C.; Dong, Y.; Zhang,W.Y.; Chen, L.Y.; Panigrahi, B.K. Cyclic electric load forecasting by seasonal SVRwith chaotic genetic algorithm. International Journal ofElectrical Power&Energy Systems2013,44,604–614. 4. Geng, J.;Huang,M.L.; Li,M.W.;Hong,W.C.Hybridizationof seasonal chaotic cloudsimulated annealingalgorithminaSVR-based loadforecastingmodel.Neurocomputing2015,151,1362–1373. 5. Hong, W.C.; Pai, P.F.; Yang, S.L.; Theng, R. Highway traffic forecasting by support vector regressionmodelwith tabu search algorithms. in Proc. the IEEE International JointConference on NeuralNetworks,2006,pp.1617–1621. x