신경회로망과 3차원 지형데이터를 이용한 마이크로셀 전파손실 예측

Microcellular Propagation Loss Prediction Using Neural Networks and 3-D Digital Terrain Maps

  • 양서민 (광운대학교 컴퓨터공학과) ;
  • 이혁준 (광운대학교 컴퓨터공학과)
  • 발행 : 1999.06.01

초록

전파의 유효 수신 신호 도달영역을 정확히 식별하는 것은 기지국 최적화를 이룩하는데 있어 가장 중요한 요소중 하나이다. 서울 도심 지역과 같이 고층건물이 밀집되어 있고, 넓은 도로와 좁은 도로가 불규칙적으로 배치되어 있으며, 고개와 강 등이 혼재된 지역에서도 높은 정확도를 갖는 전파손실 예측모델을 소개한다. 이 모델은 기 측정된 필드데이터로 훈련된 신경회로망을 기반으로 한다. 전파손실에 영향을 주는 가장 기본적인 변수들은 3차원 DEM 데이터와 벡터 데이터로부터 추출하여 신경회로망의 입력으로 사용한다. 학습이 완료된 신경회로망은 전파손실 모델의 근사함수이며, 학습에 사용된 필드 측정데이터에 포함되지 않은 타지역에서도 정확한 예측이 가능한 일반화 능력을 갖는다. 서울 도심 지역의 실제 서비스 환경에 대한 비교 실험결과를 통해 제안하는 모델의 우수성을 보인다.

Identifying the boundary of the effective receiving power of waves is one of the most important factors for cell optimization. In this paper, we introduce a propagation loss prediction model which yields highly accurate prediction in very complex areas as Seoul where a mixture of many large buildings, small buildings, broad streets, narrow alleys, rivers and forests co-exist in an irregular arrangement. This prediction model is based on neural networks trained on field measurement data collected in the past. Using these data along with 3-D digital elevation maps and vector data for building structures, we extract the parameter values which mainly affect the amount of propagation loss. These parameter values are then used as the inputs to the neural network. Trained neural network becomes the approximated function of the propagation loss model which generalizes very well and can predict accurately in the regions not included in training the neural network. The experimental results show a superior performance over the other models in the cells operating in the city of Seoul.

키워드

참고문헌

  1. IEEE Trans. Veh. Technol. v.VT-26 no.4 Radio propagation for vehilar communications K. Bullington
  2. Rev. Elec. Common. Lab. v.16 Field strength and its variability in VHF and UHF land-mobile radio service Y. Okumura(et al.)
  3. IEEE Trans. Veh. Technol. v.VT-29 no.3 Empirical formula for propagation loss in land mobile radio services M. Hata
  4. IEEE 42nd. Veh. Technol. Conf. v.2 A ray tracing method for predicting path loss and delay spread in microcellular environments K. R. Schaubach;N. H. Davis;T. S. Rappaport
  5. IEEE Trans. on Veh. Technol. v.43 no.4 The application of deterministic ray launching algorithm for the prediction of radio channel characteristics in small-cell environments M. C. Lawton;J. P. McGeehan
  6. Journal of the Optical Society of America v.52 no.2 Geometrical theory of diffraction J. B. Keller
  7. IEEE Trans. Antennas and Prop. v.36 A theoretical model of UHF propagation in urban environments J. Walfish;H. L. Bertoni
  8. IEEE Trans. Antennas and Prop. v.39 Theoretical prediction of mean field strength for urban mobile radio F. Ikegami;T. Takeuchi;S. Yoshida
  9. IEEE Journal on Selected Area in Communications v.11 no.7 Concepts and results for 3D digital terrain-based wave propagation model: an overview T. Kurner;D. J. Cichon;W. Wiesbeck
  10. IEE Proc. H. v.140 no.4 Neural network approach to prediction of terrestrial wave propagation for mobile radio K. E. Stocker(et al.)
  11. IEEE Trans. Veh. Technol. v.46 no.1 Environment-adaptation mobile radio propagation prediction using radial basis function neural networks P. R. Chang;W. H. Yang
  12. Neural Networks v.2 Multi-layer feedforward networks are universal approximators K. Hornick;M. Stinchcombe;H. White
  13. Parallel Distributed Processing D. E. Rumelhart;G. E. Hinton;R. J. Williams