• 한국통신학회논문지
• /
• 제33권8A호
• /
• pp.794-804
• /
• 2008

본 논문에서는 EPCglobal Class-1 Generation-2 (Gen2) 기반 Probabilistic Slotted 충돌방지 알고리즘에 대하여 살펴보고, 태그인식시간, 충돌 비율을 감소시키고, 데이터 처리량, 시스템 효율을 증가 시킬 수 있는 QueryAdjust 명령어를 사용한 FAFQ (fixed adjustable framed Q) 알고리즘과 AAFQ (adaptive adjustable framed Q) 알고리즘을 제안하며, 또한 Gen2 기반으로 태그 인식 효율을 향상 시킬 수 있는 Grouping 방법을 제안한다. 제안한 방법들 모두 Q 알고리즘의 성능 향상을 보이며, 제안하는 방법 중 AAFQ 알고리즘이 가장 높은 성능 향상을 나타낸다. 즉, AAFQ 알고리즘에 의하여 5% 정도의 시스템 효율 성능 향상과 4.5% 정도의 충돌 비율 감소를 얻을 수 있다. Grouping 방법은 FAFQ 알고리즘과 AAFQ 알고리즘에 대해선 Ungrouping 방법과 비슷한 성능을 보이지만, Gen2 Q 알고리즘의 경우 Ungrouping 방법과 비교 하였을 때 태그인식시간 및 충돌 비율을 감소시키고, 데이터 처리량 및 시스템 효율을 증가 시킨다.

• Journal of information and communication convergence engineering
• /
• 제7권4호
• /
• pp.469-474
• /
• 2009

Q-algorithm is proposed at EPC global Class-1 Generation-2 RFID systems to determine the frame size of next query round. In Q-algorithm, the reader calculates the frame size without estimating the number of tags. But, it uses only the slot conditions: empty, success, or collision. Therefore, it wastes less computational cost and is simpler than other algorithms. However, the constant parameter C value, which is used for calculating the next frame size, is not optimized. In this paper, we propose the optimized C values of Q-algorithm according to the number of tags within the identification range of reader through a lot of computer simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.164.1-164
• /
• 2001

Q-learning is a recent reinforcement learning algorithm that does not need a modeling of environment and it is a suitable approach to learn behaviors for autonomous agents. But when it is applied to multi-agent learning with many I/O states, it is usually too complex and slow. To overcome this problem in the multi-agent learning system, we propose the successive Q-learning algorithm. Successive Q-learning algorithm divides state-action pairs, which agents can have, into several Q-functions, so it can reduce complexity and calculation amounts. This algorithm is suitable for multi-agent learning in a dynamically changing environment. The proposed successive Q-learning algorithm is applied to the prey-predator problem with the one-prey and two-predators, and its effectiveness is verified from the efficient avoidance ability of the prey agent.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.635-637
• /
• 2012

In Gen-2 Q-algorithm, the value of initial $Q_{fp}$ and weight C is not defined in the standard. If we let the initial $Q_{fp}$ be large or small, the number of empty slot will be large during the initial query round or almost all the slots will be collided, respectively. Also, if the reader selects an inappropriate weight, there are a lot of empty or collided slots. As a result, it is anticipated that the performance will be declined because the frame size does not converge to the optimal point quickly during the query round. In this paper, we analyze how the performances of Gen-2 Q-algorithm will be affected by the weight and initial slot-count size.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권3호
• /
• pp.220-224
• /
• 2008

This paper presents the polygon-based Q-leaning and Parallel SVM algorithm for object search with multiple robots. We organized an experimental environment with one hundred mobile robots, two hundred obstacles, and ten objects. Then we sent the robots to a hallway, where some obstacles were lying about, to search for a hidden object. In experiment, we used four different control methods: a random search, a fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process to determine the next action of the robots, and hexagon-based Q-learning, and dodecagon-based Q-learning and parallel SVM algorithm to enhance the fusion model with Distance-based action making (DBAM) and Area-based action making (ABAM) process. In this paper, the result show that dodecagon-based Q-learning and parallel SVM algorithm is better than the other algorithm to tracking for object.

• 한국인터넷방송통신학회논문지
• /
• 제13권3호
• /
• pp.93-101
• /
• 2013

본 논문은 경쟁업체 $F_B$가 q개의 상점을 운영하고 있는 상황에서 신규 업체 $F_A$가 시장 점유율을 최대로 하는 p,(p$V=V{\backslash}F_B$ 후보 노드들 중 최단거리를 기준으로 최대로 확보한 상위 노드들 q개를 선택하였다. q개 노드에 대해 포함-배제 원리를 적용하여 p개의 확보 고객수 합을 구해 경쟁을 통해 최대 값을 가진 노드 집합을 $F_A$의 상점 위치로 결정하는 경쟁 알고리즘이다. 제안된 경쟁 알고리즘은 q=5에 대해 p1,2,3,4의 상점 위치를 최적으로 간단히 결정하였으며, 시장 점유율도 최대로 높일 수 있음을 보였다.

• Journal of information and communication convergence engineering
• /
• 제8권5호
• /
• pp.519-523
• /
• 2010

In Gen-2 RFID system, the initial value of $Q_{fp}$, which is the slot-count parameter of Q-algorithm, is not defined in the standard. In this case, if the number of tags within the reader's identification range is small and we let the initial $Q_{fp}$ be large, the number of empty slot will be large. On the other hand, if we let the initial $Q_{fp}$ be small in spite of many tags, almost all the slots will be collided. As a result, the performance will be declined because the frame size does not converge to the optimal point quickly during the query round. In this paper, we propose a scheme to allocate the optimal initial $Q_{fp}$ through the tag number estimation before the query round begins. Through computer simulations, it is demonstrated that the proposed scheme achieves more stable performance than Gen-2 Q-algorithm.

• 한국통신학회논문지
• /
• 제34권12B호
• /
• pp.1444-1451
• /
• 2009

본 논문은 EPCglobal C1 Gen 2 표준에서 제안한 Q 알고리즘에서 사용되는 C값에 대한 다양한 모델을 제시하고 시뮬레이션을 통하여 그 성능을 비교, 평가한다. EPCglobal C1 Gen 2 표준에서는 다중 태그 인식을 위해서 slot-count (Q) Selection Algorithm을 제안하고 있지만, Q 알고리즘에서 태그의 충돌과 무응답의 상태에 따라서 Q값을 변화시키는 값인 C 값에 대한 정확한 정의가 내려져 있지 않다. Q 알고리즘에서는 태그 충돌의 경우 C를 Q에 더하고 무응답인 경우에는 C를 감산하여 변화되는 Q값으로 태그들의 새로운 slot-count를 결정하기 때문에 다중 태그 인식 환경에 있어서 이 C값은 태그 인식 속도에 커다란 영향을 준다. 하지만 기존 연구들에서는 C값에 따른 태그 인식 속도 성능 평가나 비교 없이, Q 알고리즘을 변형하거나 새로운 방법을 제안하여 태그 인식 속도를 늘리기 위한 연구들이 존재한다. 본 연구에서는 EPCglobal C1 Gen 2 표준을 만족하는 C값의 다양한 모델을 제시하고 각각에 대해 다중 태그 인식 환경에 있어서 그 성능을 비교하고 평가한다. 본 연구의 결과물은 향후 EPCglobal C1 Gen 2 C 모델에 대한 연구나 태그 인식 성능 연구를 위한 하나의 지표로 쓰일 수 있다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 추계학술대회
• /
• pp.653-655
• /
• 2011

EPCglobal proposed a Q-algorithm, which is used for selecting a slot-count in the next query round. However, it is impossible to allocate an optimized slot-count because the original Q-algorithm did not define an optimized weight C value. In this paper, we propose an adaptive Q-algorithm, in which we differentiate the weight values with respect to collision and empty slots. The weight values are defined with the identification time as well as the collision probability.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권2호
• /
• pp.131-147
• /
• 2020

Purpose The purpose of this study is to develop intelligent vehicle parking distribution system based on LoRa network at the circumstance of traffic congestion during cultural festival in a local city. This paper proposes a parking dispatch and distribution system using a Q-learning algorithm to rapidly disperse traffics that increases suddenly because of in-bound traffics from the outside of a city in the real-time base as well as to increase parking probability in a parking lot which is widely located in a city. Design/methodology/approach The system get information on realtime-base from the sensor network of IoT (LoRa network). It will contribute to solve the sudden increase in traffic and parking bottlenecks during local cultural festival. We applied the simulation system with Queuing model to the Yudeung Festival in Jinju, Korea. We proposed a Q-learning algorithm that could change the learning policy by setting the acceptability value of each parking lot as a threshold from the Jinju highway IC (Interchange) to the 7 parking lots. LoRa Network platform supports to browse parking resource information to each vehicle in realtime. The system updates Q-table periodically using Q-learning algorithm as soon as get information from parking lots. The Queuing Theory with Poisson arrival distribution is used to get probability distribution function. The Dijkstra algorithm is used to find the shortest distance. Findings This paper suggest a simulation test to verify the efficiency of Q-learning algorithm at the circumstance of high traffic jam in a city during local festival. As a result of the simulation, the proposed algorithm performed well even when each parking lot was somewhat saturated. When an intelligent learning system such as an O-learning algorithm is applied, it is possible to more effectively distribute the vehicle to a lot with a high parking probability when the vehicle inflow from the outside rapidly increases at a specific time, such as a local city cultural festival.