Globalization of economy leads to create new markets for all industries and increases competitive pressures in this field. The main goal of any companies is trying to fulfill the needs of their customers without spending a lot of time. In recent decade, one of the significant visions is major increase in level of customer service in Just-In-Time (JIT) in make to order systems. In Just In Time system, production is coordinated somehow that there is no need to keep inventory and orders are not delayed. In this paper, the general lot sizing and scheduling problem with earliness/ tardiness penalties with sequence-dependent setup times and costs have been investigated. There are n orders waiting to be processed on a machine. Each order has its own due date, tardiness and earliness penalty that considered as holding cost. Each order is only delivered once in planning horizon; on the due date or if it has tardiness, immediately after the production of this order is completed. In this thesis a model similar to traveling salesman problem for mentioned (noted) problem is presented. The problem objective is to determine the production lot sizes and their schedules in order to minimize the sum of the total setup cost, total holding cost, and total tardy cost. Since the model can not solve the NP-hard large size problems, two meta heuristic algorithms, Tabu Search and Ant Colony System are proposed to solve this group of problems. Then the efficiency of these algorithms in different groups of problemare evaluated. The results show thatamong 333 problems, Ant Colony System and Tabu Searche reachthe optimal solution of 196 and 203 problems, respectively. The average errors of these two algorithms are 1.76 and 1.88, respectively. Computational experiments indicate the effectiveness and appropriateness of these algorithms. Statistically, there is no preference between these two methods. Beside that solution times of tabu search are lower than ones of ant colony system.