交通信息与安全
交通信息與安全
교통신식여안전
JOURNAL OF TRANSPORT INFORMATION AND SAFETY
2015年
2期
26-30,56
,共6页
智能交通系统%短时预测%状态空间模型%卡尔曼滤波%速度信息
智能交通繫統%短時預測%狀態空間模型%卡爾曼濾波%速度信息
지능교통계통%단시예측%상태공간모형%잡이만려파%속도신식
intelligent transportation systems%short period forecasts%state space model%Kalman filter%speed data
利用速度消息的时变特性，提出了1种无需假设状态变量为平稳的基于卡尔曼滤波算法的短时交通量预测模型。依据城市道路网上下游路段交通流之间的时空演化关系，利用实时采集的路段平均速度信息构建时变的状态转移矩阵来取代常数状态转移矩阵，对现有基于卡尔曼滤波算法的短时交通量预测模型进行改进。最后以2个真实路段4d的交通量进行预测试验，相关计算结果表明：由于加强了模型的动态性，改进后的预测模型较原模型的预测精度在整体上有所提高，其中平均绝对相对误差由7．64％及16．04％分别下降至7．25％及15．75％，均等系数则由0．9572及0．9250分别提高至0．9602及0．9268，而对于交通量急速变化的时段，提高的幅度更为明显，平均绝对相对误差可降低14.8％，从而验证了所提出方法的有效性。
利用速度消息的時變特性，提齣瞭1種無需假設狀態變量為平穩的基于卡爾曼濾波算法的短時交通量預測模型。依據城市道路網上下遊路段交通流之間的時空縯化關繫，利用實時採集的路段平均速度信息構建時變的狀態轉移矩陣來取代常數狀態轉移矩陣，對現有基于卡爾曼濾波算法的短時交通量預測模型進行改進。最後以2箇真實路段4d的交通量進行預測試驗，相關計算結果錶明：由于加彊瞭模型的動態性，改進後的預測模型較原模型的預測精度在整體上有所提高，其中平均絕對相對誤差由7．64％及16．04％分彆下降至7．25％及15．75％，均等繫數則由0．9572及0．9250分彆提高至0．9602及0．9268，而對于交通量急速變化的時段，提高的幅度更為明顯，平均絕對相對誤差可降低14.8％，從而驗證瞭所提齣方法的有效性。
이용속도소식적시변특성，제출료1충무수가설상태변량위평은적기우잡이만려파산법적단시교통량예측모형。의거성시도로망상하유로단교통류지간적시공연화관계，이용실시채집적로단평균속도신식구건시변적상태전이구진래취대상수상태전이구진，대현유기우잡이만려파산법적단시교통량예측모형진행개진。최후이2개진실로단4d적교통량진행예측시험，상관계산결과표명：유우가강료모형적동태성，개진후적예측모형교원모형적예측정도재정체상유소제고，기중평균절대상대오차유7．64％급16．04％분별하강지7．25％급15．75％，균등계수칙유0．9572급0．9250분별제고지0．9602급0．9268，이대우교통량급속변화적시단，제고적폭도경위명현，평균절대상대오차가강저14.8％，종이험증료소제출방법적유효성。
A short period traffic volume forecasting model ,which based on Kalman filtering algorithm and without assuming the state variables to be stationary ,is proposed with considering the characteristics of speed variation .On the basis of the spatial temporal evolution relationship between the traffic flow of upstream and downstream in urban road net‐work ,a time variant state transition matrix is developed from the average speed data collected in field .The new state transition matrix will replace the constant state transition matrix of the existing short period traffic volume forecasting model based on Kalman filtering algorithm .Traffic volume forecasts of 4 days on 2 real road sections were conducted ,the results show that the improved model has a better overall forecasting accuracy than the original model due to the enhance‐ment of dynamic performance .The mean absolute relative error (MARE) decreased from 7 .64% to 7 .25% and from 16 . 04% to 15 .75% ;equality coefficient (EC) increased from 0 .957 2 to 0 .960 2 and from 0 .925 0 to 0 .926 8 .For those time periods when the traffic volume changed rapidly ,the improvement is even more significant .In this case ,the mean absolute relative error reduced by 14 .8% .The results also verified the effectiveness of the proposed approach .
