AVTOBUSLARDA YO‘LOVCHI OQIMINI PROGNOZLASH ASOSIDA HARAKAT INTERVALINI OPTIMALLASHTIRISH

J.A.Axunov

Farg‘ona davlat texnika universiteti


Abstract

Annotatsiya. Mazkur maqolada avtobuslarda yo‘lovchi oqimini prognozlash asosida harakat intervalini optimallashtirish masalasi kompleks tarzda ko‘rib chiqiladi. Zamonaviy shahar transport tizimlarida qat’iy belgilangan harakat jadvali ko‘pincha yo‘lovchi oqimining o‘zgaruvchan xususiyatlarini hisobga olmaydi, natijada yo‘lovchilarning kutish vaqti ortadi hamda transport vositalaridan foydalanish samaradorligi pasayadi [6], [7]. Shu sababli maqolada yo‘lovchi oqimiga moslashuvchan holda dinamik harakat intervalini aniqlash yondashuvi taklif etiladi.

Tadqiqotda yo‘lovchi oqimi vaqt qatori sifatida qaralib, uning prognozi uchun statistik va sun’iy intellektga asoslangan yondashuvlar qo‘llanildi. Xususan, ARIMA modeli vaqt qatoridagi chiziqli bog‘lanishlarni aniqlashda, Bi-LSTM neyron tarmog‘i esa nolinear va murakkab o‘zgarishlarni hisobga olishda qo‘llanildi [2], [3], [4], [5]. Prognoz natijalari asosida avtobuslar harakat intervalini optimallashtirish uchun ko‘p maqsadli matematik model ishlab chiqildi.

Mazkur modelda asosiy mezonlar sifatida yo‘lovchilar kutish vaqti va transport vositalarining ekspluatatsion xarajatlari minimallashtiriladi. Shuningdek, optimallashtirish jarayonida zamonaviy yondashuvlar, jumladan, ko‘p maqsadli optimallashtirish usullari qo‘llanildi [1]. Tahlil natijalari shuni ko‘rsatadiki, dinamik intervalni qo‘llash orqali yo‘lovchilar kutish vaqti kamayadi, transport tizimining samaradorligi esa sezilarli darajada oshadi.

Natijalar shuni ko‘rsatadiki, yo‘lovchi oqimini prognozlash asosida harakat intervalini optimallashtirish jamoat transporti tizimining samaradorligini oshirish, ekspluatatsion xarajatlarni kamaytirish va xizmat ko‘rsatish sifatini yaxshilashda muhim ilmiy va amaliy ahamiyatga ega.

Kalit so‘zlar. yo‘lovchi oqimi, harakat intervali, prognozlash, ARIMA, Bi-LSTM, optimallashtirish, jamoat transporti.

Abstract. This paper comprehensively examines the problem of optimizing bus headways based on passenger flow prediction. In modern urban transport systems, fixed timetables often fail to account for the dynamic nature of passenger demand, resulting in increased passenger waiting times and reduced operational efficiency of public transport systems [6], [7]. Therefore, this study proposes an approach for determining dynamic headways that adapt to passenger flow variations.

In this research, passenger flow is considered as a time series, and both statistical and artificial intelligence-based approaches are applied for its prediction. In particular, the ARIMA model is used to identify linear relationships in time series data, while the Bi-LSTM neural network is employed to capture nonlinear and complex patterns [2], [3], [4], [5]. Based on the prediction results, a multi-objective mathematical model for optimizing bus headways is developed.

In the proposed model, the main criteria are the minimization of passenger waiting time and operational costs of transport vehicles. Furthermore, modern optimization techniques, including multi-objective optimization methods, are applied in the solution process [1]. The analysis results show that the implementation of dynamic headways significantly reduces passenger waiting time and improves the overall efficiency of the transport system.

The results indicate that optimizing bus headways based on passenger flow prediction has significant scientific and practical importance in improving the efficiency of public transport systems, reducing operational costs, and enhancing service quality.

Keywords. passenger flow, headway, forecasting, ARIMA, Bi-LSTM, optimization, public transport.


References

1. Cheng G., He Y. Enhancing passenger comfort and operator efficiency through multi-objective bus timetable optimization. Electronic Research Archive, 2024, 32(1), 565–583. DOI: 10.3934/era.2024028

2. Pei Y., Ran S., Wang W., Dong C. Bus Passenger Flow Prediction Model Based on WPD, Attention Mechanism, and Bi-LSTM. Sustainability, 2023, 15(20), 14889. DOI: 10.3390/su152014889

3. Ye R. Research on Bus Passenger Flow Dynamic Prediction and Route Optimization Strategy Based on Spatiotemporal Clustering and ARIMA Model. World Journal of Innovation and Modern Technology, 2025, 8(4). DOI: 10.53469/wjimt.2025.08(04).02

4. Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, 9(8), 1735–1780.

5. Box G.E.P., Jenkins G.M., Reinsel G.C., Ljung G.M. Time Series Analysis: Forecasting and Control. Wiley, 2015.

6. Vuchic V.R. Urban Transit Systems and Technology. Wiley, 2007.

7. Ceder A. Public Transit Planning and Operation: Modeling, Practice and Behavior. CRC Press, 2016.

Most read articles by the same author(s)