Author: A.N. Gavrilov
Abstract
Forecasting the turnover of seaports is an integral part of port management. Since port construction is capital-intensive and the demand for port capacity directly depends on forecasts of cargo turnover, improved accuracy of forecasts can significantly reduce investment volumes in the construction/reconstruction of port facilities, as well as operating costs. The present article proposes a probabilistic approach to forecasting port cargo turnover, which can significantly reduce the length of the uncertainty interval of cargo turnover, calculated as the sum of the cargo turnover of independent segments specified at intervals. This approach can be successfully applied if the cargo turnover segments are considered as
independent normally or uniformly distributed random variables. It has been found that, for both cases, the result of adding segments can be approximated by a normally distributed random variable, and an interval of values can be calculated for it. The method reduces the interval of cargo turnover uncertainty in comparison with the classical approach.
Keywords: ports, forecasting methods, cargo turnover, segmentation, probability, interval estimation, uncertainty interval, mathematical expectation, variance, normal distribution, uniform distribution, Irwin — Hall distribution.
References
1. Svetunkov I.S., Svetunkov S.G. Metody sotsialno-ekonomicheskogo prognozirovaniya. T. 1. Teoriya i metodologiya [Social and economic forecasting methods. Vol. 1. Theory and Methodology]. M: Urite, 2015, 351 p.
2. Alefeld G., Hercberger U. Vvedenie v intervalnye vychisleniya. [Introduction to interval computing]. М.: Mir, 1987, 356 p.
3. Holding "Forum" postroit v Tamani odin iz krupneyshikh v Rossii konteinernykh terminalov [Forum Holding will build one of the largest container terminals in Russia in Taman]. https://www.tks.ru/logistics/2015/06/22/0001 (accessed on 10.09.2020).
4. Eshhe odin konteinerny terminal na Kamchatke [Another container terminal in Kamchatka] https://seanews.ru/2019/05/06/ru-eshhe-odinkontejnernyj-terminal-na-kamchatke (accessed on 10.09.2020).
5. Feller V. Vvedenie v teoriyu veroyatnostei i yeyo prilozheniya. Tom 1. 2-е izd. [Introduction to probability theory and its applications. Volume 1, 2nd Edition] — М.: Mir, 1964, 511 p.
6. Bryc W. The Normal Distribution: Characterizations with Applications. — Springer-Verlag, 1995, p. 139.
7. Rebro I.V. et al. Prikladnaya matematicheskaya statistika dlya tehnicheskih specialnostey uchebnoe posobie. [Applied Mathematical Statistics for Technical Specialties: A Study Guide]. Volgograd: IUNYA VolgGTU, 2011, 149 p.
8. Johnson N L., Kotz S., Balakrishnan N. Continuous Univariate Distributions, Vol. 2, 2nd Edition. Wiley, 1995.
9. Montgomery D.C., Runger G.C. Applied Statistics and Probability for Engineers (6th ed.). Wiley, 2014, p. 241.
10. Zharinov I.O., Zharinov O.O. Teoreticheskaya ocenka funkciy plotnosti veroyatnosti raspredeleniya koordinat cveta v sistemah bortovoi indikacii. [Theoretical estimate of the probability density function of color coordinates distribution in on-board display systems]. Programmnaya inzheneriya [Software engineering], 2015, Vol. 3, pp. 35 — 43. http://window.edu.ru/resource/584/80584/files/pi2015n3.pdf (accessed on 10.09.2020).
About author:
A.N. Gavrilov - Maritime State University named after Admiral G.I. Nevelskoy, Vladivostok, e-mail: gavrilov@msun.ru
Issue: 62/63 (2021)
For citation: A.N. Gavrilov. Method of reducing uncertainty intervals in forecasting cargo turnover in sea ports. Research Bulletin by Russian Maritime Register of Shipping. 2021, No. 62/63, pp. 42-49.
UDC 656.615+338.12.017+519.2
Fr: 8:30 – 16:15 (msk)