Modelling Electricity Consumption Forecasting Using the Markov Process and Hybrid Features Selection

Abstract

Given the problem of electrical energy storage, it is critical to predict the amount of load required in order to have a reliable and stable power distribution network. Predicting electricity consumption of subscribers and analyzing their consumption behavior under the influence of various factors and time variables is important. Given the large volume of subscriber consumption data and the effective factors, it is only possible to analyze the data using new information technology tools such as data mining. In this paper, feature selection, clustering and Markov process techniques are used to model and predict the power consumption data of subscribers. First, the selection of a subset of effective features is based on the combined PCA approach and the Firefly algorithm. Subscribers are then clustered based on the features selected by the K-means. Finally, subscriber behavior patterns are modeled to predict consumption using the Markov process on high-risk clusters. This study is simulated based on the data of electricity subscribers in Bushehr-Iran Power Distribution Company. The simulation results show the superiority of the proposed model over other similar algorithms such as LASSO-QRNN and HyFIS. The accuracy of power consumption prediction in the proposed method is about 1% compared to LASSO-QRNN and about 0.5% compared to HyFIS.

Model of Information System Communication in Aggressive Cyberspace: Reliability, Functional Safety, Economics

“…Based on the calculations, the results of which are visualized in Fig. 1, based on expressions (26) and (27) for RIS the dependencies {W , R} = f (t) are calculated, where W is the accumulated parameter of efficiency of operation of RIS, and R is the accompanying risk from its operation. The corresponding graphs are shown in Fig.…”

Modeling a session of subject-system interaction in a wireless communication infrastructure with a mixed resource

“…Suppose that the processing of each received input request in such a system is carried out by the service apparatus, for the operation of which a resource is allocated, the volume of which is characterized by a stochastic parameter with a certain distribution law [ 24 ]. Let resource management be characterized by the Markov process of "Death and Recovery" X ( t ) [ 24 , 25 ]. Accordingly, the resource of the queuing system summarizes the stable and unstable components.…”

A Power Evolution Game Model and Its Application Contained in Virtual Power Plants

“…Game theory has been widely used in various fields, and then gradually applied in the power systems [41]. In the early days, game theory was used to analyse the revenue distribution and sharing problem in power systems [42], the adaptive distribution of power transaction costs [43][44][45], the energy cost-saving problems in power systems [46], the planning and expansion of power transmission system in power systems [47][48][49] and preference analysis among different agents in power systems [50].…”