Identify Optimal Traffic Condition and Speed Limit for Hard Shoulder Running Strategy

Highway system is experiencing increasing traffic congestion with fast-growing number of vehicles in metropolitan areas. Implementing management strategies such as utilizing the hard shoulder an extra lane could increase highway capacity without construction work. This paper presents a method determining optimal condition and speed limit opening shoulder. Firstly, states are clustered using K-Means, mean shift, agglomerative spectral clustering methods, algorithm selected indexes including silhouette score, Davies-Bouldin Index Caliski-Harabaz Score. The results suggested that effect K-Means three categories optimal. Then, cellular automata model used to simulate conditions before after running strategy applied. parameters model, probabilities random deceleration, slow start change, calibrated real data. Four indicators volume, average speed, variance travel time emergency rescue during accident obtained evaluate various strategies. By factor analysis TOPSIS (Technique for Order Preference by Similarity Ideal Solution) be determined. applied segments lanes different limits optimize management.