RESUMEN
Electric truck platooning offers a promising solution to extend the range of electric vehicles during long-haul operations. However, optimizing the platoon speed to ensure efficient energy utilization remains a critical challenge. The existing research on implementing data-driven solutions for truck platooning remains limited and implementing first principles solution is still a challenge. However, recognizing the resemblance of truck platoon data to a time series serves as a compelling motivation to explore suitable analytical techniques to address the problem. This paper presents a novel deep learning approach using a sequence-to-sequence encoder-decoder model to obtain the speed profile to be followed by an autonomous electric truck platoon considering various constraints such as the available state of charge (SOC) in the batteries along with other vehicles and road conditions while ensuring that the platoon is string stable. To ensure that the framework is suitable for long-haul highway operation, the model has been trained using various known highway drive cycles. Encoder-decoder models were trained and hyperparameter tuning was performed for the same. Finally, the most suitable model has been chosen for the application. For testing the entire framework, drive cycle/speed prediction corresponding to different desired SOC profiles has been presented. A case study showing the relevance of the proposed framework in predicting the drive cycle on various routes and its impact on taking critical policy decisions during the planning of electric truck platoons has also been presented. This study would help to efficiently plan the feasible routes for electric trucks considering multiple constraints such as battery capacity, expected discharge rate, charging infrastructure availability, route length/travel time, and other on-road operating conditions while also maintaining stability.
RESUMEN
Background: India has rapidly scaled up its programme for antiretroviral therapy(ART). There is high potential for the emergence of HIV drug resistance (HIVDR),with an increasing number of patients on ART. It is not feasible to perform testingfor HIVDR using laboratory genotyping, owing to economic constraints. This studypiloted World Health Organization (WHO) early-warning indicators (EWIs) forHIVDR, and quality-of-care indicators (QCIs), in four ART clinics in Pune city.Methods: A retrospective study was conducted in 2015, among four ART clinicsin Pune city, India. The data on four standardized EWIs (EWI 1: On-time pill pickup, EWI 2: Retention of patients in ART care at 12 months after initiation, EWI 3:Pharmacy stock-out, EWI 4: Pharmacy dispensing practices) and three QCIs(QCI 1: Regularity in CD4 testing in patients taking ART, QCI 2: Percentage ofpatients initiating ART within 30 days of medical eligibility, QCI 3: Percentage ofpatients initiating ART within 30 days of initiation of anti-tuberculosis therapy) wereabstracted into WHO Excel HIV data abstractor tools, from the patient recordsfrom April 2013 to March 2014.Results: All four ART clinics met the EWI 4 target (100%) for ART dispensingpractices. The target for EWIs on-time pill-pick (EWI 1 >90%) and pharmacy stockouts (EWI 3: no stock-outs, 100%) were achieved in one clinic. None of the clinicsmet the EWI 2 target for retention in care at 12 months (>90%) and the overallretention was 76% (95% confidence interval: 73% to 79%). The targets for QCI 1and QCI 2 (>90% each) were achieved in one and two clinics respectively. Noneof the clinics achieved the target for QCI 3 (>90%).Conclusion: ART dispensing practices (EWI 4) were excellent in all clinics. Effortsare required to strengthen retention in care and timely pill pick-up and ensurecontinuity of clinic-level drug supply among the programme clinics in Pune city.The clinics should focus on regularity in testing CD4 count and timely initiation ofART