Environmentally friendly approach to energy consumption implies planning the resources' amount which could be delivered and utilized by the end user. For the resource provider this means being able to get remote data from a huge number of users, with further data analysis being performed to predict future consumption. The main objective of this work was a comparison of classical regression analysis methods with neural network analysis for solving a household energy consumption prediction problem. Research was based on an array of energy consumption data collected from 47 households situated in the Rostov region (Russia) over a period of 730 days. We investigated the forecasting models based on statistical regressing of 1-st, 2-d and 3-d order and a recurrent neural network (the best result we achieved had been given by a neural network with one hidden layer of 10 neurons). Forecasting time-frame was 20% of the data-set (nearly three months) and 80% we used for training. For our data the best result was achieved by a neural network where the ratio error of the forecast practically didn't exceed 5% (mean ratio error was 0.22 and standard deviation of 3.7). For the regression models these terms were 0.37 and 6.24 for the 1-st order, 3.31 and 6.45 for the 2-d order, 0.29 and 6.7 for the 3-d order model respectively. As a result of this work we determined, that rather simple recurrent neural network provides a better result in terms of energy consumption prediction in comparison with classical regression analysis methods, though more complex networks, such as LSTM, need a wider data array to learn.

Keywords: energy resources, metering device, housing and communal services, energy consumption forecasting, data analysis, regression, time series, recurrent neural network, machine learning, “smart city”

This article describes an estimation of developed data exchange protocol robustness. Protocol is used in wireless connectivity. This protocol was made for delivering data from a meter to GSM-concentrator. This system is a part of hardware-software complex for energy resources and water metering. To solve this problem an imitation model was developed, which consider various collisions on the line. The purpose of modeling is to estimate probability of failure while transmitting daily data from meters to GSM-concentrator. The model was made of N random number generators, the period of time is divided into time slots. These generators give random slots which is a modeling of random transmissions. During modeling we consider a simultaneous transmission of two generators as a failure. Then the model was modified to address the possible “semi-collision”, when two generators use slots which are close to each other. The results of modified model show that probability of failure using developed protocol is negligible.

Keywords: еnergy resource, meter, complex, radio channel, probability, collision, failure, imitation model

The article presents the results of research and development of a method for testing hypotheses about the form of the probability density function of the random variable in the face of considerable uncertainty a priori. The results obtained, contrary to the traditional skepticism in regard to the processing of data samples, the volume of the order of ten values ​​indicate the potential to improve the reliability of their classification.

Keywords: processing of statistical data, small sample size, the numerical method, the simulation supplement statistical experiment, random process.

In the article a number of approaches to a flapping wing pilotless vehicle control system synthesis are analyzed. Referred type of pilotless vehicles is possessed of a number of advantages compared to the traditional schemes, but requires a special approach to control system creation because of strong nonlinearity and multicoupling of a controlling object mathematical model. As a result of a control system synthesis approaches analysis a synergetic approach was marked out as the most adequate for the mentioned above type of controlling objects. An idea of prognostics application for the goal of reaching of adaptive control is also set forth. In this case parameters of an object of control and parameters of ambient both are to be forecasted whereby an adaptive behavior of an object of control is expected to be achieved.

Keywords: control system, pilotless vehicle, control theory, “barrier of dimensionality”, synergetic approach, adaptation, prognostic.