Empirical Models for Estimating the Dispersion Parameter of Robertson’s Platoon Dispersion Model
Bhaskar Paul, Indian Institute of Technology, KharagpurShow Abstract
Bhargab Maitra, Indian Institute of Technology, Kharagpur
Sudeshna Mitra, Indian Institute of Technology, Kharagpur
Modelling of vehicle progression is important for design of Signal coordination. In this regard, Robertson’s platoon dispersion model is the most widely used model. It requires calibration for its site specific application. The present work carry out the calibration of Roberson’s model for five arterials having variation of roadway width as four-lane, six lane and eight lane carriageway. Afterwards, best suited values of platoon dispersion factor are modelled empirically. An empirical model to relate the variation in α with traffic volume, vehicle mix, link length, and roadway width.The empirical models were formulated successfully to capture the variation in α over several arterials having roadway width as four lane, six lane and eight lane. The model can be used readily by professionals to estimate α to carry out the design of signal coordination plan considering the variation in spatiotemporal aspects of an interrupted traffic flow facility. Various design charts are built to aid the practitioners to estimate α while carrying the design of signal coordination plan using TRANSYT-7f.
Offset Optimization Between Signalized Intersections Taking into Account the Delay and Emission of Platoon: A Case Study in Beijing
Shenzhen Ding, Beijing Jiaotong UniversityShow Abstract
Xumei Chen, Beijing Jiaotong University
Lei Yu, Texas Southern University
Xu Wang, China Railway Siyuan Survey and Design Group CO., LTD
Offset optimization is an effective mean to ensure the smooth flow of urban arterial roads. The effective setting of offsets between intersections on arterial roads can greatly reduce the travel time of vehicles through intersections. However, the coordinated control system of urban arterial often does not achieve the desired effect. On the contrary, it is very likely to increase the traffic congestion on arterial roads, resulting in more delays of the platoon with more exhaust emissions, if the coordinated control system does not have the effective settings. Meantime, taking into account the increasing environmental pollution, the measures are needed to solve the conflict between environment and traffic management. Thus, this paper develops a bi-objective offset optimization model to reduce delays of the platoon on arterial roads while reducing the exhaust emissions. Further, the modified hierarchical method combining the branch and bound approach with introducing the relaxation coefficient is employed to solve the model. By introducing a relaxation coefficient, the modified hierarchical method overcomes the defect of the traditional one. Finally, Xi Dajie Road in Beijing is taken as an example. The results have shown that the bi-objective offset optimization model considering both the delays and emissions of platoon reduces delays by up to 20% and emissions by 7% compared with the existing timing plan. If compared with the offset optimization model considering the delays only, such model increases delays no more than 3% and reduces emissions by 6%.
Implementation of Platoon-Based Actuated Signal Control to Coordinated Intersections: A Case Study at Two Arterial Corridors in Greater Houston
Xing Wu, Lamar UniversityShow Abstract
Hao Yang, Toyota Info Technology Center
Bipul Mainali, Lamar University
Pratik Pokharel, Lamar University
This paper studies the implementation of the platoon-based actuated signal control system to arterial corridors in the Houston Metropolitan Area, where some intersections have coordinated signal control system. The proactive signal control system was previously developed based on available functions of the loop detectors and Econolite ASC/3 2100 Controller (widely used in Texas), and successfully tested at a separate intersection. The tested arterial corridors have several intersections closely spaced, so it is important to keep their signal control coordinated. However, the coordinated system was found not good in handling left-turn traffic from the major road and traffic from minor road, because such coordinated system was designed primarily for the through traffic on the major road. On the other hand, because of the limitation of detectors and controller, it is difficult to develop a coordinated platoon-based actuated control system for multi-intersections. For these reasons, we developed a model based on the functions of ASC/3 2100 Controller and loop detectors, so that the signal control system at an intersection can switched between the original coordinated control and the platoon-based control, according to the detected traffic volumes at each approach. On one testbed which have large left-turn traffic, the results based on the detector data before and after implementation show that this model works well to relieve the delay for both left-turn traffic and through traffic on the major road. On another testbed, the platoon-based control is activated only when the through traffic is low. Some improvements were also observed at some intersections.
Optimal Control of Isolated Oversaturated Intersections Revisited
Vinayak Bhosle, IIT MadrasShow Abstract
Bhargava Rama Chilukuri, Indian Institute of Technology, Madras
Safe manoeuvre of conflicting movements through intersections is achieved using traffic signals, whose parameters are determined based on the arrival rates, geometry, etc. However, the inherent assumption of the traditional methods is that the intersection operates at or under saturation. As the traffic demands grow, several intersections begin to operate at higher volume to capacity ratios leading to oversaturated conditions. Existing literature on analytical treatment of optimal control of oversaturated intersections is limited to only some specific cases, but they provide a greater insight into the optimal control problem and its variables. In this regard, this research will attempt to extend the current understanding of the optimal control of isolated intersections operating at two phase and three phase control that minimizes total delay. The study extends Gazis framework [1964, 1976] that used cumulative count curves to evaluate the system state and control performance. Results indicate that the performance of the proposed strategy is superior to the traditional methods. While approaches with smaller saturation flows incurred higher delay compared to the traditional approach, total control delay and the oversaturation duration have significantly reduced with the proposed strategy. The analytical results of this research are expected to enhance the current understanding of optimal control of isolated oversaturated intersections and open the doors to a simple set of algorithms for optimal control with minimal infrastructure.
A Peer-to-Peer Logic Environment to Validate Flashing Yellow Arrow Decision Support System
Hatem Abou-Senna, University of Central FloridaShow Abstract
Essam Radwan, University of Central Florida
Hesham Eldeeb, University of Central Florida
The flashing yellow arrow (FYA) signal display creates an opportunity to enhance the left-turn phase with a variable mode that can be changed on demand. This research develops an integrated general purpose data collection module that time stamps detector and phase state changes within a National Electrical Manufacturers Association (NEMA) actuated traffic signal controller to provide recommendations for the flashing yellow arrow left-turn mode on a cycle-by-cycle basis. 115 left turn approaches at 38 intersections with locations across the State of Florida were analyzed totaling 1370 hours of video data processed including off-peak and peak conditions. Video data extraction was an essential step in developing the gap thresholds for the permissive left-turn. Actual intersection field data was obtained through loop detector mapping to the controller in the lab in real-time mode using a peer-to-peer logic environment. A Custom communications software was developed to retrieve instantaneous channel input data, synchronize opposing thru green phase, analyze traffic information, provide the algorithm decision, and generate a real-time log recording the events to determine whether it would be optimal to switch the red arrow to a flashing yellow arrow. The algorithm determines the time interval between the successive arrivals of vehicles and computes the corresponding headway for each lane by cycle on a second-by-second basis. Peer-to-peer-logic is a necessary step to verify and validate new traffic concepts prior to field testing and offers the advantage of acquiring and analyzing real-time traffic data coupled with video feed with the benefit of a safe environment.
State of Adaptive Signal Systems in the United States
Katherine Brunk, Clemson UniversityShow Abstract
Sakib Khan, Clemson University
Mashrur Chowdhury, Clemson University
Adaptive Signal Control Systems (ASCS) is an advanced traffic signal technology that uses an algorithm to adjust traffic signals in real time, based on traffic flow demand. Using parameters such as phase sequence, cycle length, offset and split, each algorithm focuses on achieving specific measures of effectiveness, such as minimizing travel time, number of stops, and delay. While the technology was introduced many years ago, adoption of the technology has been slow in the United States. The reasons for this vary with some examples being cost of adoption, insufficient benefits, and insufficient manpower. This research includes a state survey with a follow-up survey to local contacts to assess the impacts of ASCS on safety and operations. While increasingly common abroad, conclusions from these United States-targeted surveys prove that most states have considered or studied ASCS, though many have not implemented the technology. Fourteen states indicated that they currently have ASCS active on at least one corridor. A follow-up survey was distributed to city and county contacts to identify corridor characteristics that will allow for the best operational and safety results, such as design speed, number of intersections, and corridor type. The dual approach to surveying two groups of transportation personnel within each state allowed the researchers to gather the opinions of those who have conducted operational studies of ASCS deployed in their jurisdiction. The responses will help to determine direction for future study, in order to provide recommendations for types of corridors that best fit the benefits of ASCS.
Integrated Assignment and Signal Coordination for Improved Traffic Network Operations
Yuanchang Xie, University of Massachusetts, LowellShow Abstract
Nathan H. Gartner, University of Massachusetts, Lowell
Tugba Arsava, Wentworth Institute of Technology
Traffic signal optimization has often been conducted locally based on the approaching volumes and turning traffic counts at individual intersections without fully accounting for the underlying Origin and Destination (OD) information and driver route choice behavior. On the other hand, traffic assignment procedures do not consider the provision of progression opportunities obtained by optimal signal coordination strategies. Consequently, the interactive effects between signal coordination and traffic redistribution due to driver route choice behavior are not fully considered. Employing such myopic approaches, solving congestion problems by optimizing signal timing at one intersection may simply shift it to another location, leading to suboptimal planning and operation decisions. This research proposes an integrated traffic assignment and signal coordination scheme by introducing a progression adjustment function which is tailored to the traffic flow characteristics on each link. This new approach is able to simultaneously optimize traffic assignment and all the relevant signal control parameters such as cycle length, green splits and offsets. A case study on a simple network demonstrates that the proposed approach has the potential to significantly improve traffic network operations.
Monte Carlo Tree Search Solution for Intersection Signal Optimization: MCTS-IO
HongSheng QI, Zhejiang UniversityShow Abstract
Channelized section spillover (CSS) happens when demand increases to such a degree that vehicles are blocked at upstream section and not able to enter channelized section. The evolution of CSS is dynamic in nature not only due to the interactions between traffic flow of different movements, but also lies in the fact that existing CSS influences the queuing process in channelized section and contributes to the formation of new CSS at the next signal cycle. Such dynamic interactions have not been modeled explicitly and leaves room for signal optimization. A Monte Carlo Tree Search-based model is proposed to solve intersection optimization problem (named MCTS-IO) with CSS dynamic evolution explicitly modeled. The model works in a rolling horizon way. At each decision point, MCTS-IO simulates the intersection by selecting a sequence of phases, and progressively updates the relative preferences of the phases. After all simulations are performed, the phase with the best policy PI is selected. Both PI and decision space can be customized which ensures the algorithm flexibility . The method is tested against Synchro results under three designed scenarios. It is demonstrated that the proposed MCTS-IO model is always able to find a solution that is better than Synchro.
Stop-Bar and Advance Detection Design for Left Turn Operation
Enas AMIN, University of IdahoShow Abstract
Paul Olson, P.R.Olson Associates Ltd.
Ali Hajbabaie, Washington State University
Michael Lowry, University of Idaho
To date, there are no clear guidelines on selecting detector location, size, and signal timing parameters for left-turn operations at signalized intersection. This paper attempts to fill this gap through testing alternative detector designs and signal timing parameters for protected-permitted left-turn phasing. First, a survey was conducted to document state-of-the-art practices in the United States for left-turn signalized intersection operations and to identify the most common detector design and signal timing parameters used for left-turn operations. Second, a VISSIM software-in-the-loop microscopic simulation model was used to model the intersection operations under different detector configurations (stop-bar detection and queue/advance detection), signal timing parameters, left-turn volumes, and opposing through volumes. The operational effect of each of these parameters on green time utilization, left-turn delay, and intersection delay was analyzed and modeled. In this paper, a comparison between the operational efficiency of stop-bar detection and queue detection is presented. Also, as part of the analysis, the operational benefits of protected-permitted left-turn operations under different left-turn demand levels and opposing through volumes was documented and quantified.
A Two-Way Arterial Signal Coordination Model Considering Side-Street Turning Traffic
Wei Huang, Hong Kong UniversityShow Abstract
Can Chen, Tongji University
Xueqi Che, Tongji University
Keping Li, Tongji University
In most arterial traffic progression models, the turning traffic from side streets is usually neglected. In practice, an effective progression model should explicitly consider the turning flow and the effect of queue clearance time, hence the turning traffic can not be ignored especially when the spacing between intersections is short. In this paper, a novel two-way bandwidth maximization model is proposed, which explicitly considers the left-turn traffic joining the arterial via side streets. The basic framework of the proposed model is a modified MULTIBAND model that changes the locations and continuities of the progression lines. The queueing process is elaborated in the modified model, considering the side-street phase sequence. Moreover, the side-street phase sequence is optimized simultaneously by adding the green bands for left turning flow to the bandwidth maximization problem. For the lead left-turn phase on side streets, the minimum bandwidth constraints are established based on a simple linear delay model for the corresponding left-turn flow from side streets. To evaluate the efficiency of the proposed model, an arterial with long and short spacing intersections is used. Through three test scenarios with low, medium and high turning traffic onto the arterial, the key model properties are demonstrated and numerical results confirm that the proposed model can efficiently reduce the overall network average delay and number of stops per vehicle.
An Experimental Study on Max-Pressure Traffic Controller Based on Travel Times
Pedro Mercader, T-SMART Lab, Technion-Israel Institute of TechnologyShow Abstract
Wasim Uwayid, T-SMART Lab, Technion-Israel Institute of Technology
Jack Haddad, No Organization
The traffic control of an arbitrary network of signalized intersections is considered. This work presents a new version of the max-pressure controller, also known as back-pressure. The most remarkable features of the max-pressure algorithm for traffic signal control are scalability, stability, and distribution. The modified version presented in this paper improves the practical applicability of the max-pressure controller by considering as input travel times instead of queue lengths. The two main practical advantages of this new version are: (i) travel times are easier to estimate than queue lengths, and (ii) max-pressure controller based on travel times has an inherent capacity-aware property, i.e., it takes into account the finite capacity of each link. Travel time tends to diverge when the queue length is close to its capacity. It should be noted that previous max-pressure algorithms rely exclusively on queue length measurements, which may be difficult to accomplish in practice. Moreover, these previous algorithms generally assume queues with unbounded capacity. This is problematic because a point queue model is not able to reproduce spillbacks, which are a crucial issue that a traffic signal controller should avoid. After presenting the modified version of the max-pressure controller, it is compared with existing control policies in a microscopic traffic simulator. Moreover, results of a real implementation of the developed algorithm to a signalized intersection, located at an urban arterial in Jerusalem, are shown. To the best of the authors' knowledge, this is the first real implementation of a max-pressure controller at a signalized intersection.
Area-Wide Urban Traffic Optimal Splits Control Under NEMA Standards with Model Predictive Control
Qichao Wang, Virginia Polytechnic Institute and State UniversityShow Abstract
Montasir Abbas, Virginia Polytechnic Institute and State University
The splits are one of the three important types of the control parameters in a modern traffic controller. Few studies have been done on coordinated optimal splits control under the National Electrical Manufacturing Association Standards (NEMA Standards). We proposed a virtual phase-link concept and used this concept to model the urban traffic control under the NEMA Standards. We framed the coordinated optimal splits control problem as a linear quadratic programming problem and implemented the optimal feedback control with model predictive control. The outputs of the solution are the timing plans that can be used in NEMA controllers. We conducted microscopic simulation studies to compare timing plans generated from the proposed method with the ones generated from a state-of-the-practice signal timing software. It was found that the proposed method significantly outperformed the benchmarking method under semi-actuated control settings. The evaluation of the optimization algorithm shows that the optimization process can be performed in a real-time manner, indicating that the proposed method can be implemented for large-scale urban traffic optimal splits control.
Real-Time Dynamic Traffic Control Based on Traffic State Estimation
Afzal Ahmed, NED University of Engineering and TechnologyShow Abstract
Syed Ahsan Ali Naqvi, Hong Kong Polytechnic University
Dong Ngoduy, University of Canterbury
The accurate depiction of the existing traffic state on a road network is essential in reducing congestion and delays at signalized intersections. The existing literature in the optimization of signal timings either utilizes prediction of traffic state from traffic flow models or limited real-time measurements available from sensors. Prediction of traffic state based on historic data cannot represent the dynamics of change in traffic demand or network capacity. Similarly, data obtained from limited point sensors in a network provides estimates which contain errors. A reliable estimate of existing traffic state is, therefore, necessary to obtain signal timings which are based on the existing condition of traffic on the network. This research proposes a framework which utilizes estimates of traffic flows and travel times based on real-time estimated traffic state for obtaining optimal signal timings. The prediction of traffic state from the Cell Transmission Model (CTM) and measurements from traffic sensors are combined in the recursive algorithm of Extended Kalman Filter (EKF) to obtain a reliable estimate of existing traffic state. The estimate of traffic state obtained from the CTM-EKF model is utilized in the optimization of signal timings using Genetic Algorithm (GA) in the proposed CTM-EKF-GA framework. The proposed framework is applied to a synthetic signalized intersection and the results are compared with a model-based optimal solution and simulated reality. The optimal delay estimated by CTM-EKF-GA framework is only 0.6% higher than the perfect solution, whereas the delay estimated by CTM-GA model is 12.9% higher than the perfect solution.
Impact of Phase Sequence on Cycle Length Resonance
Christopher Day, Iowa State UniversityShow Abstract
A M Tahsin Emtenan, Iowa State University
The concept of resonant cycle length, that there are certain cycle lengths that may provide excellent progression due to corridor geometry and other factors, has some currency as a potential strategy for cycle length selection. Past studies have identified resonant cycles under certain conditions and demonstrated benefits from use of the strategy as a means of selecting cycle length. The present study revisits the concept in application to flow-based models of traffic signal performance, highlighting the impact of phase sequence optimization. The phenomenon of cycle length resonance is explored for corridors with equal and randomly-generated spacing between intersections, and finally for a field-calibrated corridor. Under each scenario, the performance of different cycle lengths is explored under two optimization strategies: optimization of only offsets; and optimization of both offsets and phase sequence. It is found that phase sequence has a substantial impact on the performance of coordination. Optimized phase sequences were found to yield 8–14% improvement in performance compared to use of the default sequence. For corridors where a resonant cycle length is evident, when phase sequences can also be adjusted, the poorer performance of non-resonant cycle lengths can be mitigated by optimizing phase sequence. While use of a resonant cycle length is likely to yield good performance for some corridors under appropriate conditions, the use of a phase sequence optimization strategy is likely to have a strong impact on most corridors, and can be more impactful than selection of a resonant cycle length.
A Decentralized Network Level Adaptive Signal Control Algorithm by Deep Reinforcement Learning
Yaobang Gong, University of Central FloridaShow Abstract
Mohamed Abdel-Aty, University of Central Florida
Qing Cai, University of Central Florida
Md. Sharikur Rahman, University of Central Florida
Adaptive traffic signal control systems are deployed to accommodate real-time traffic conditions. Yet needs and behaviors of the individual vehicles might be overseen by their model-based decision making and aggregated input traffic data. Recently, several pioneering studies employed deep reinforcement learning to come up with model-free control algorithms based on information regarding individual vehicles. However, those studies are limited to isolated intersections and their effectiveness were only evaluated in ideal simulated traffic conditions by hypothetical benchmark signal control algorithms. To fill the gap, this study proposes a decentralized network level adaptive signal control algorithm using one of the famous deep reinforcement learning techniques, double dueling deep Q network. The algorithm was evaluated by the real-world coordinated actuated signals in a simulated suburban traffic corridor in Seminole County, Florida. The evaluation results showed that the algorithm outperforms the benchmark signal control system. It is able to reduce 10.27% of travel time and 46.46% of total delay.
Queue-Based Guidance for Signalization Consideration at Two- and Three-Legged Intersections
Shannon Warchol, North Carolina State UniversityShow Abstract
Nagui Rouphail, North Carolina State University
Christopher Vaughan, Institute for Transportation Research and Education
Brendan Kearns, North Carolina State University
This research collected and analyzed gap acceptance in North Carolina to develop a data-driven method for determining the need for considering additional signalization analysis at intersections with fewer than four legs. This method can be used for movements that merge with or cross two lanes of oncoming traffic. It is intended to provide guidance and support to traffic engineers in their decision-making process. Charts are provided to determine the expected 95th percentile queue lengths for left turn, right turn, and U-Turn movements crossing or merging with two lanes of conflicting traffic. This situation is typically present along four lane roadways where a one-way primary movement opposes either a minor road right turn movement or a left turn movement, or in the case of a median U-Turn opening. Adjustment factors to the conflicting flowrate were developed to account for the presence of upstream signalized intersections. This method less frequently recommends further signal consideration when compared to the MUTCD peak hour warrant, but is similar to the delay-based level of service D/E threshold for two-way stop-controlled intersections in HCM6 Chapter 19.
Impacts of Changing from Permissive/Protected Left Turn to Protected Only Phasing: A Case Study in the City of Tucson, Arizona
Xiaofeng Li, University of ArizonaShow Abstract
Alexander Weber, Kimley-Horn and Associates, Inc.
Adrian Cottam, University of Arizona
Yao-Jan Wu, University of Arizona
Recent research has focused on the safety or mobility impacts of signal timing. Several studies have compared the choice between a protected-only left turn (PO) and a protected-permissive left turn (PPLT). However, few have compared both the safety and mobility impacts, and their tradeoffs. This study proposed data-driven methods to conduct a pilot study at an intersection in Tucson, Arizona. This study evaluated the impacts on vehicular mobility and multi-modal safety when changing from a PPLT to a PO. First, the daily and annual delay for the through and left-turn movements for the intersection was evaluated using a calibrated delay model and year-long 15-min traffic sensor data. Then, real-world near misses between cyclists, pedestrians, and vehicles were manually collected and analyzed using 48-hour of videos. Last, both mobility and safety measures were converted into an annual cost to determine the tradeoff between the before (PPLT) and the after (PO) situations. The results of this study demonstrated the feasibility of the proposed methods, providing practitioners with different options to effectively and efficiently evaluate left-turn phasing strategies.
Estimating Peak-Hour Traffic Profiles for the Selection of Appropriate Day-of-Year Signal Timing Plans
Nikola Mitrovic, Florida Atlantic UniversityShow Abstract
Aleksandar Stevanovic, Florida Atlantic University
Multiple Day-of-Year (DOY) signal timing plans are developed to deal with day-to-day traffic fluctuations during a particular peak-hour. Once the operating intervals of these plans are scheduled, they stay valid for next several months or even years. A signal timing plan deployed in this way is rigid regarding any day-to-day changes in the peak-hour traffic and might not be the best option for the prevailing traffic. In this paper, we select an appropriate DOY signal timing plan for the next peak-hour based on estimated traffic profile of that peak-hour. We first applied k-means clustering to a historical data set to identify the dominant profiles and develop optimal signal timing plans for the extracted demand profiles. We then utilized recent traffic information to predict the profile of next peak-hour traffic and select the signal timing plan relevant for the estimated profile. For predictions of an upcoming peak-hour traffic profile, we tested multiple methods in the context of: (i) within-an-hour prediction where all traffic information available 15-30 minute before the start of peak-hour are utilized, and (ii)next-day prediction where traffic information from previous (but not of the investigated) days are considered. The results of the analysis, based on three-year of volume data along a five-mile corridor in Fort-Lauderdale, show that the adequate signal plan can be selected for ~65% and ~75\% of the days in a year in the context of next-day and within-an-hour prediction, respectively. The results merit the further development of this idea and its integration in a decision-support system.
Concurrent Progression of Through and Turning Movements for Arterials Experiencing Heavy Turning Flows and Bay-Length Constraints
Yen-Hsiang Chen, University of Maryland, College ParkShow Abstract
Yao Cheng, University of Maryland, College Park
Gang-Len Chang, University of Maryland, College Park
Contending with congestion on major urban arterials by providing progression bands has long been a priority task for the traffic community. However, on an arterial experiencing heavy left-turn volumes at major intersections, the left-turn queue may spill back rapidly and further degrade the effectiveness of the through progression band if the left-turn volume and the limited bay length have not been accounted for in the optimization of signal coordination plan. Such negative impact from left-turn queues also justifies the need to take into account the concurrent progression of through and left-turn flows on major arterials. To address these two issues, this paper presents a three-staged signal optimization model that can circumvent or minimize the impact of left-turn spillback to the through movements and concurrently minimize the delay of left-turn flows. The proposed model firstly obtains an initial maximized bandwidth from an existing state-of-the-art method and then maximizes the portion of through bandwidth not impeded by the left-turn overflows. The delay of left-turn flows at each intersection will be also minimized under the obtained effective through bandwidth. The results from the numerical analyses have confirmed the benefits and need of including the left-turn volume and its bay length in the design of dual progression for through and left-turn movements. The simulation experiments further show a reduction on the average delay and the number of stops, respectively by 6.4% and 5.5%, for vehicles traversing an arterial segment of six intersections, compared to the state-of-the-art model, MULTIBAND.
An Adaptive Signal Control Method Using Cell Transmission Model and Mixed Integer Linear Programming
Hao Liu, University of Texas, AustinShow Abstract
Amber Chen, University of Texas
Randy Machemehl, University of Texas, Austin
Adaptive signal control is a favorable way to reduce the congestion and improve the mobility of urban traffic networks. This paper proposes an adaptive signal control algorithm to optimize the signal timing for the incoming cycle at an isolated intersection. Traffic volume prediction and signal optimization are two crucial components of adaptive control methods. A CTM-based model predicts the traffic volumes for the target intersection by counting the current vehicle numbers in the upstream cells. This model does not make assumptions about the arrival process and the correlation of the flows between consecutive cycles. Through this method, the accuracy of the volume prediction is ensured even under a rapidly varying traffic conditions. In addition, the signal optimization problem is modeled as a mixed integer linear program (MILP) based on the Barron-Jensen/Frankowska (B-J/F) solution to the Lighthill-Whitham-Richards (LWR) model. The sequence and the splits of phases can be optimized at the same time according to the current traffic condition. Finally, this paper compares the new method to the critical lane flow ratio method which is a commonly used strategy. The total delay per vehicle resulting from the new method is reduced under degrees of traffic congestion ranging from low to high.