Figure 4 - uploaded by Sven Tomforde
Content may be subject to copyright.
Source publication
In recent years, autonomic and organic computing have become areas of active research in the informatics community. Both initiatives aim at handling the growing complexity in technical systems by focusing on adaptation and self-optimisation capabilities. A promising application for organic concepts is the control of road traffic signals in urban ar...
Similar publications
In this paper, a Fog-Radio Access Network (F-RAN) architecture is considered in which Ultra-Reliable and Low-Latency communications (URLLC) traffic is served by the Edge Nodes (ENs) of a cellular network, while enhanced Mobile BroadBand (eMBB) communications are handled centrally at a cloud processor as in a Cloud-RAN system. This solution guarante...
Citations
... Using a broad range of real-time traffic data, a variety of methods to control traffic light signals have been proposed. For example, rule-based reinforcement learning ATLC is presented in [148], where the traffic lights of neighboring intersections coordinate locally; the work is extended by including an additional hierarchical observer/controller component at the regional level in order to better optimize the ATLC operation [149]. Moreover, multi-agent based algorithms have been applied to traffic light systems [150]- [156]; for instance multiple fuzzy logic controllers, interconnected using IEEE 802.15.4 technology are employed to dynamically order phases and calculate green time while factoring turns [150]. ...
... [173] [177]. [146] Optimize sequence and length of traffic lights Improve delay and throughput Single [147] Optimize signal phase and time Reduce time and space complexity Single [148] Simulation based Improve delay and throughput Multiple [149] Centralized/decentralized Improve delay reducing fuel consumption [150] Optimize signal phase and green time duration Improve delay and throughput [151] Optimize signal phase and green time duration Minimize average vehicle waiting time Single [152] adjust green time duration Reduce average vehicle waiting time [153] Optimize signal phase and green time duration Improve average travel time Single or multiple [154] Optimize signal phase and green time duration Improve delay and throughput Multiple [155] Coordinated traffic signal control Reduce total number of stopped vehicles Single [156] Reduce computational complexity Improve delay and throughput Multiple [157] Optimize signal phase and green time duration Improve delay and throughput ...
Traffic management and on-road safety have been a concern for the transportation authorities and the engineering communities for many years. Most of the implemented technologies for intelligent highways focus on safety measures and increased driver awareness, and expect a centralized management for the vehicular traffic flow. Leveraging recent advances in wireless communication, researchers have proposed solutions based on vehicle-to-vehicle (V2V) and vehicle-to-Infrastructure (V2I) communication in order to detect traffic jams and better disseminate data from on-road and on-vehicle sensors. Moreover, the development of connected autonomous vehicles (CAV) have motivated a paradigm shift in how traffic will be managed. Overall, these major technological advances have motivated the notion of dynamic traffic management (DTM), where smart road reconfiguration capabilities, e.g., dynamic lane reversal, adaptive traffic light timing, etc. will be exploited in real-time to improve traffic flow and adapt to unexpected incidents. This chapter discusses what the challenges in realizing DTM are and covers how CAV has revolutionized traffic management. Moreover, we highlight the issues for handling human-driven vehicles while roads are transitioning to CAV only traffic. Particularly, we articulate a new vision for inter-vehicle communication and assessment of road conditions, and promote a novel system for traffic management. Vehicle to on-road sensors as well as inter-vehicle connectivity will be enabled through the use of handheld devices such as smartphones. This not only enables real-time data sharing but also expedites the adoption of DTM without awaiting the dominant presence of autonomous vehicle on the road. ...
... Layer 2 is responsible for optimizing the LCS via an evolutionary algorithm (EA). Since the TLC needs to receive an answer in real time this more complex task is carried out in its own layer and independent from Layer 1 [6]. ...
... Thomsen et al. [3] have suggested a distributed collaborative incident validation approach to detect exceptional behavior in an organic system. The organic system in this case is a traffic network consisting of traffic lights, lanes and intersections based upon the work of Prothmann et al. [6]. Fig. 1 shows the underlying system that DCIV aims to improve. ...
... The organic traffic controller[6] which DCIV aims to improve. EA: Evolutionary Algorithm, LCS: Learning Classifier Model, SuOC: System under observation and control. ...
Adaptive traffic control systems are an important building block of optimal traffic flow. Principles from organic computing such as self-organization may be beneficial for these systems. To further improve the performance of a self-organized system a collaborative incident validation approach was suggested. This paper analyzes the impact of this additional system on the self-* properties of the overall system and concludes that an improvement can in fact be expected for certain self-* properties.
... Lastly, a comparative analysis around the question of which system is better suited for the use in an average city environment will be conducted. It is important to mention that SOTL and PSM have been loosely connected to the idea of OC in previous works ( [5,6] for SOTL and [7] for PSM). There they are correctly identified as OC-near or emergent systems and are usually used as an example giving an outlook on decentralized traffic control. ...
Since traffic light control plays a major role in urban mobility, it is important to be on the lookout for new methods to improve car congestion. This paper will take a look at two such methods, SOTL and a phase-synchronization approach to traffic control, through the lens of Organic Computing Systems. This contains the attempt at identifying self-organization,-configuration,-integration,-management and-improvement in both systems, and implementing them in case of their absence. A closer look will be taken at how the degree of self-organization SOTL, PSM and their modified versions experience can be measured. Finally, a comparison will take place, that will try to assess the application of both traffic control methods in modern city environments.
... Future plans include integrating the concept of adaptive-lane reversal in the Organic Traffic-Control (OTC) system-a self-adaptive and self-organised urban-traffic-management system that controls the green duration of traffic lights [20], establishes progressive signal systems [16] ("green waves") and guides road users through the network using variable message signs [21]. Possible challenges include devising a full decentralised extension of flow-lane reversal as well as using the OTC's ability to adapt its control strategy for the improvements of such an extension. ...
Every year, traffic congestion costs the global economy billions of dollars in lost productivity, particularly in urban areas. Traffic congestion is a complex problem, as traffic conditions may change at any time. Tidal-flow lanes can be utilised as a feasible traffic-congestion-mitigation strategy to balance the fluctuating traffic demands throughout the day. This paper proposes an adaptive-lane-reversal approach for tidal-flow lanes, to decrease the impact of traffic congestion in urban areas. In order to evaluate the adaptive approach under various traffic conditions, several algorithms and parameter sets are examined, using various network models and traffic demands. As a result, the total travel time of the vehicles in the various networks was decreased by up to 81%.
... erefore, intelligent traffic light control systems based on traffic volume [1] and traffic density [2] appear to provide real-time control of traffic lights in order to meet the traffic needs of vehicles at the intersection. Other research on traffic light timing optimization includes studies on travel time [3] and intelligent traffic based on lane [4]. ...
The purpose of this research is to find a traffic light timing optimization scheme. During the research, an intersection between Xi’an Mingguang road and the Fourth FengCheng road was chosen to analyze the crossing time distribution of pedestrians who were separated from west-to-the-right-turn vehicles during which the method of breaking off both ends of pedestrian green light signals was used. The VISSIM software was used for traffic simulation, aimed at improving traffic volume and right-turning vehicle average speed for less vehicle queuing delays, less human-vehicle conflicts, and better security for pedestrians without excessive interruption on their street crossing efficiency. The optimal scheme is obtained and the result shows that (1) the number of passing vehicles remains unchanged, with the queuing delay reduced by 5.78% and crosswalk passing speed increased by 19.01% compared with the original one. (2) As the scheme effect is positively correlated with the increase of right turn vehicle numbers, the scheme could be adopted for urban traffic management based on the local situation, which is not only in peak traffic hours but also in the flat peak time to ensure vehicle efficiency and pedestrian safety in the light of “vehicle yielding to pedestrians” regulation. (3) The scheme could also be adopted in cities with no “vehicle yielding to pedestrians” policy for both people-vehicle separation and pedestrian safety when crossing streets.
... Cao et al. (2000) incorporated Learning Classifier System (LCS) and TCP/IP (Transmission Control Protocol/Internet Protocol) based communication server into a distributed learning control strategy to increase the speed of control. Prothmann et al. (2009) managed the complexity by using an organic approach to NTSC and proved the feasibility of the proposed approach. Lu et al. (2011) proposed a multi-agent NTSC by using Swarm Intelligence and Neuro-Fuzzy RL to combine the better attributes of both with improving the learning speed and performance. ...
Improvement of traffic signal control (TSC) efficiency has been found to lead to improved urban transportation and enhanced quality of life. Recently, the use of reinforcement learning (RL) in various areas of TSC has gained significant traction; thus, we conducted a systematic literature review as a systematic, comprehensive, and reproducible review to dissect all the existing research that applied RL in the network-level TSC domain, called as RL in NTSC or RL-NTSC for brevity. The review only targeted the network-level articles that tested the proposed methods in networks with two or more intersections. This review covers 160 peer-reviewed articles from 30 countries published from 1994 to March 2020. The goal of this study is to provide the research community with statistical and conceptual knowledge, summarize existence evidence, characterize RL applications in NTSC domains, explore all applied methods and major first events in the defined scope, and identify areas for further research based on the explored research problems in current research. We analyzed the extracted data from the included articles in the following seven categories: (1) publication and authors’ data, (2) method identification and analysis, (3) environment attributes and traffic simulation, (4) application domains of RL-NTSC, (5) major first events of RL-NTSC and authors’ key statements, (6) code availability, and (7) evaluation. This paper provides a comprehensive view of the past 26 years of research on applying RL to NTSC. It also reveals the role of advancing deep learning methods in the revival of the research area, the rise of using non-commercial microscopic traffic simulators, a lack of interaction between traffic and transportation engineering practitioners and researchers, and a lack of proposal and creation of testbeds which can likely bring different communities together around common goals.
... MARL is also used in [49] to tackle the complexity emerging in MAS domains. Especially the "Extended Classifier System" (XCS) variant by Wilson [50] (including its variants from the OC domain such as [51][52][53][54]), which has been widely used for implementing self-adaptation with runtime learning capabilities. For instance, XCS can be seen as an integral part of OC systems that are said to exhibit self-learning properties. ...
Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system’s operational limits are not violated. On the grid level, distribution management systems (DMS) seek to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by setpoint specification of batteries, photovoltaic generators, or flexible loads. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing “organic” HEMS and DMS which possess multiple self-x capabilities, collectively referred to as self-management. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this concept paper, the vision of ODiS is presented in detail based on a thorough review of the state of the art.
... MARL is also used in [45] to tackle the complexity emerging in MAS domains. Especially the "Extended Classifier System" (XCS) variant by Wilson [46] (including its variants from the OC domain such as [47,48,49,50]) has been widely used for implementing self-adaptation with runtime learning capabilities. For instance, XCS can be seen as an integral part of OC systems that are said to exhibit self-learning properties. ...
Due to the decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the basic critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system's operational limits are not violated. On the grid level, distribution management systems (DMS) try to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by using batteries, photovoltaic generators, or flexible loads optimally. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing "organic" HEMS and DMS which possess multiple self-* capabilities. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this article, the vision of ODiS is presented in detail based on a thorough review of the state of the art.
... Once the simulation model has been adjusted, the robot can use it to quickly come up with a new gait that still works despite the failure. Prothmann et al. (2009) describe an observer-controller architecture for an adaptive traffic light system. On the lowest layer, a reactive traffic light controller is employed. ...
... (Cao et al., 2000) incorporated Learning Classifier System (LCS) and TCP/IP (Transmission Control Protocol/Internet Protocol) based communication server into a distributed learning control strategy to increase the speed of control. (Prothmann et al., 2009) managed the complexity by using an organic approach to NTSC and proved the feasibility of the proposed approach. (W. ...
... Liu et al., 2018; Zhou et al., 2019; M. Xu et al., 2020; Shi and F. Chen, 2018; J. Lee et al., 2020; T. Tan et al., 2019; Horsuwan and Aswakul, 2019; Chu et al., 2019; Wei et al., 2019a; N. Xu et al., 2019; Rizzo et al., 2019b; Zheng et al., 2019a; Gong et al., 2019; D. Kim and Jeong, 2020; Yang et al., 2019; Ni and Cassidy, 2019; Ge et al., 2019; Shabestray and Abdulhai, 2019; Kitagawa et al., 2019; Van der Pol and Oliehoek, 2016; Rizzo et al., 2019a; P. Chen et al., 2019; Chu et al., 2016a; Vinitsky et al., 2018; Reda et al., 2019; Huang et al., 2019 Model-based methods Khamis and Gomaa, 2014; Kuyer et al., 2008; M. Wiering et al., 2004; Houli et al., 2010; Khamis et al., 2012; M. A. Wiering, 2000; Khamis and Gomaa, 2012; Da Silva et al., 2006 RL and GT Qu et al., 2020; L.-H.Xu et al., 2013; X. Zhao et al., 2009;Daeichian and Haghani, 2018;El-Tantawy et al., 2013;El-Tantawy and Abdulhai, 2010;Xinhai and Lunhui, 2009 ADP Fagan andMeier, 2014; T. Li et al., 2008b;Yin et al., 2015;Dai et al., 2010; Reda et al., 2019 Code, Simulation, and Evaluation Code is availableWei et al., 2018;Zhou et al., 2019;Genders and Razavi, 2020;Chu et al., 2019;Wei et al., 2019a;Zheng et al., 2019a;Wei et al., 2019b;Brys et al., 2014;Vinitsky et al., 2018 No Simulation W. Xu et al., 2015Reda et al., 2019;Dowling et al., 2004;El-Tantawy and Abdulhai, 2010;Davarynejad et al., 2010;Xinhai and Lunhui, 2009 No Evaluation/Self-comparison W.Xu et al., 2015;Reda et al., 2019;Dowling et al., 2004;El-Tantawy and Abdulhai, 2010;Davarynejad et al., 2010;Xinhai and Lunhui, 2009;Dusparic and Cahill, 2009b; X.-Y. Liu et al., 2018;Prothmann et al., 2009 ...
