| 1. |
- Helali Moghadam, Mahshid, et al.
(författare)
-
Adaptive Runtime Response Time Control in PLC-based Real-Time Systems using Reinforcement Learning
- 2018
-
Ingår i: ACM/IEEE 13th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2018, , co-located with International Conference on Software Engineering, ICSE 2018; Gothenburg; Sweden; 28 May 2018 through 29 May 2018; Code 138312. - New York, NY, USA : ACM. ; , s. 217-223
-
Konferensbidrag (refereegranskat)abstract
- Timing requirements such as constraints on response time are key characteristics of real-time systems and violations of these requirements might cause a total failure, particularly in hard real-time systems. Runtime monitoring of the system properties is of great importance to detect and mitigate such failures. Thus, a runtime control to preserve the system properties could improve the robustness of the system with respect to timing violations. Common control approaches may require a precise analytical model of the system which is difficult to be provided at design time. Reinforcement learning is a promising technique to provide adaptive model-free control when the environment is stochastic, and the control problem could be formulated as a Markov Decision Process. In this paper, we propose an adaptive runtime control using reinforcement learning for real-time programs based on Programmable Logic Controllers (PLCs), to meet the response time requirements. We demonstrate through multiple experiments that our approach could control the response time efficiently to satisfy the timing requirements.
|
|
| 2. |
- Helali Moghadam, Mahshid, et al.
(författare)
-
Learning-based Response Time Analysis in Real-Time Embedded Systems : A Simulation-based Approach
- 2018
-
Ingår i: 1st International Workshop on Software Qualities and their Dependencies, located at the International Conference of Software Engineering (ICSE) 2018 SQUADE'18. - New York, NY, USA : ACM. - 9781450357371 ; , s. 21-24
-
Konferensbidrag (refereegranskat)abstract
- Response time analysis is an essential task to verify the behavior of real-time systems. Several response time analysis methods have been proposed to address this challenge, particularly for real-time systems with different levels of complexity. Static analysis is a popular approach in this context, but its practical applicability is limited due to the high complexity of the industrial real-time systems, as well as many unpredictable runtime events in these systems. In this work-in-progress paper, we propose a simulationbased response time analysis approach using reinforcement learning to find the execution scenarios leading to the worst-case response time. The approach learns how to provide a practical estimation of the worst-case response time through simulating the program without performing static analysis. Our initial study suggests that the proposed approach could be applicable in the simulation environments of the industrial real-time control systems to provide a practical estimation of the execution scenarios leading to the worst-case response time.
|
|
| 3. |
- Helali Moghadam, Mahshid, et al.
(författare)
-
Learning-Based Self-Adaptive Assurance of Timing Properties in a Real-Time Embedded System
- 2018
-
Ingår i: ICST Workshop on Testing Extra-Functional Properties and Quality Characteristics of Software Systems ITEQS'18. - 9781538663523 ; , s. 77-80
-
Konferensbidrag (refereegranskat)abstract
- Providing an adaptive runtime assurance technique to meet the performance requirements of a real-time system without the need for a precise model could be a challenge. Adaptive performance assurance based on monitoring the status of timing properties can bring more robustness to the underlying platform. At the same time, the results or the achieved policy of this adaptive procedure could be used as feedback to update the initial model, and consequently for producing proper test cases. Reinforcement-learning has been considered as a promising adaptive technique for assuring the satisfaction of the performance properties of software-intensive systems in recent years. In this work-in-progress paper, we propose an adaptive runtime timing assurance procedure based on reinforcement learning to satisfy the performance requirements in terms of response time. The timing control problem is formulated as a Markov Decision Process and the details of applying the proposed learning-based timing assurance technique are described.
|
|
| 4. |
- Helali Moghadam, Mahshid, et al.
(författare)
-
Machine Learning to Guide Performance Testing : An Autonomous Test Framework
- 2019
-
Ingår i: ICST Workshop on Testing Extra-Functional Properties and Quality Characteristics of Software Systems ITEQS'19, 2019.
-
Konferensbidrag (refereegranskat)abstract
- Satisfying performance requirements is of great importance for performance-critical software systems. Performance analysis to provide an estimation of performance indices and ascertain whether the requirements are met is essential for achieving this target. Model-based analysis as a common approach might provide useful information but inferring a precise performance model is challenging, especially for complex systems. Performance testing is considered as a dynamic approach for doing performance analysis. In this work-in-progress paper, we propose a self-adaptive learning-based test framework which learns how to apply stress testing as one aspect of performance testing on various software systems to find the performance breaking point. It learns the optimal policy of generating stress test cases for different types of software systems, then replays the learned policy to generate the test cases with less required effort. Our study indicates that the proposed learning-based framework could be applied to different types of software systems and guides towards autonomous performance testing.
|
|
| 5. |
|
|
| 6. |
- Zinser, Markus, et al.
(författare)
-
Comparison of microscopic and macroscopic approaches to simulating the effects of infrastructure disruptions on railway networks
- 2018
-
Ingår i: Proceedings of 7th Transport Research Arena TRA 2018, April 16-19, 2018, Vienna, Austr. - : Zenodo.
-
Konferensbidrag (refereegranskat)abstract
- The current state-of-the-art in timetable analysis in the presence of disruptions is to use railway microsimulation, which typically yields detailed results on infrastructure or timetable performance. However, micro-simulation is time-consuming and requires a detailed infrastructure model. This paper outlines a macroscopic approach which aims at reducing execution time by restricting the level of detail to high-level relations between significant events. In particular, the effect of disruptions is modelled by sampling delay times from probability distributions obtained from historical data. In this paper, we test whether this approach, given common disruption scenarios, still allows accurate results on delays to be obtained. Two disruption scenarios were simulated in RailSys and with the new method, using limited parameter tuning. In the results, visually similar delay distributions were observed. Although there is some room for improvements in accuracy, the new approach appears promising, and we found no evidence against its suitability in the presence of disruptions.
|
|
| 7. |
- Bohlin, Markus, et al.
(författare)
-
Maintenance optimization with duration-dependent costs
- 2015
-
Ingår i: Annals of Operations Research. - : Springer Science and Business Media LLC. - 0254-5330 .- 1572-9338. ; 224:1, s. 1-23
-
Tidskriftsartikel (refereegranskat)abstract
- High levels of availability and reliability are essential in many industries where production is subject to high costs due to downtime. Examples include the mechanical drive in natural gas pipelines and power generation on oil platforms, where gas turbines are commonly used as a power source. To mitigate the effects of service outages and increase overall reliability, it is also possible to use one or more redundant units serving as cold standby backup units. In this paper, we consider preventive maintenance optimization for parallel k-out-of-n multi-unit systems, where production at a reduced level is possible when some of the units are still operational. In such systems, there are both positive and negative effects of grouping activities together. The positive effects come from parallel execution of maintenance activities and shared setup costs, while the negative effects come from the limited number of units which can be maintained at the same time. To show the possible economic effects, we evaluate the approach on models of two production environments under a no-fault assumption. We conclude that savings were substantial in our experiments on preventive maintenance, compared to a traditional preventive maintenance plan. For single-unit systems, costs were on average 39 % lower when using optimization. For multi-unit systems, average savings were 19 %. We also used the optimization models to evaluate the effects of re-planning at breakdown and effects due to modeling of inclusion relations. Breakdown re-planning saved between 0 and 11 % of the maintenance costs, depending on which component failed, while inclusion relation modeling resulted in an 7 % average cost reduction.
|
|
| 8. |
- Bohlin, Markus, et al.
(författare)
-
Optimization Methods for Multistage Freight Train Formation
- 2015. - 6
-
Ingår i: Transportation Science. - : Institute for Operations Research and the Management Sciences. - 0041-1655 .- 1526-5447. ; 50:3, s. 823-840
-
Tidskriftsartikel (refereegranskat)abstract
- This paper considers mathematical optimization for the multistage train formation problem, which at the core is the allocation of classification yard formation tracks to outbound freight trains, subject to realistic constraints on train scheduling, arrival and departure timeliness, and track capacity. The problem formulation allows the temporary storage of freight cars on a dedicated mixed-usage track. This real-world practice increases the capacity of the yard, measured in the number of simultaneous trains that can be successfully handled. Two optimization models are proposed and evaluated for the multistage train formation problem. The first one is a column-based integer programming model, which is solved using branch and price. The second model is a simplified reformulation of the first model as an arc-indexed integer linear program, which has the same linear programming relaxation as the first model. Both models are adapted for rolling horizon planning and evaluated on a five-month historical data set from the largest freight yard in Scandinavia. From this data set, 784 instances of different types and lengths, spanning from two to five days, were created. In contrast to earlier approaches, all instances could be solved to optimality using the two models. In the experiments, the arc-indexed model proved optimality on average twice as fast as the column-based model for the independent instances, and three times faster for the rolling horizon instances. For the arc-indexed model, the average solution time for a reasonably sized planning horizon of three days was 16 seconds. Regardless of size, no instance took longer than eight minutes to be solved. The results indicate that optimization approaches are suitable alternatives for scheduling and track allocation at classification yards.
|
|
| 9. |
- Bohlin, Markus, 1976-, et al.
(författare)
-
Optimization of Railway Freight Shunting
- 2018
-
Ingår i: Handbook of Optimization in the Railway Industry. - Cham : Springer-Verlag New York. ; , s. 181-212
-
Bokkapitel (refereegranskat)abstract
- Railway freight shunting is the process of forming departing trains from arriving freight trains. The process is continuously performed at rail yards. The shunting procedure is complex and rail yards constitute bottlenecks in the rail freight network, often causing delays to individual shipments. One of the problems is that planning for the allocation of tracks at rail yards is difficult, given that the planner has limited resources (tracks, shunting engines, etc.) and needs to foresee the consequences of committed actions for the current inbound trains. The required schedules highly depend on the particular infrastructure of the rail yard, on the configuration of inbound and outbound trains, and on the business objectives. Thus, new optimization tools as active decision support for the dispatchers are closely tailored to the actual processes. Due to its practical relevance, a broad range of variants has been discussed and solved by the scientific community in recent years. For selected relevant variants, we describe their fruitful relation to scientific research topics such as graph coloring, sequence partitioning, and scheduling, we discuss their computational complexity and approximability, and we outline efficient optimization procedures. In particular, we consider a set of models and algorithms which are applicable in practice, and discuss their application to the shunting yards in Ludwigshafen, Germany and in Hallsberg, Sweden. We also discuss similarities and differences between the different approaches and outline the need for future research.
|
|
| 10. |
- Bohlin, Markus, 1976-, et al.
(författare)
-
Optimization of railway freight shunting
- 2018
-
Ingår i: Handbook of Optimization in the Railway Industry. - Cham : Springer. - 9783319721521 ; , s. 181-212
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)
|
|
