According to the industry characteristics of the service-oriented city and its corresponding power load characteristics, the necessity of accelerating construction of efficiency power plant (EPP) is discussed. The EPP mentioned here can shift electricity usage from peak hours to off-peak hours using thermal storage technology. This paper presents an integrated resource planning (IRP) model with the aim to minimize the total cost over a planning horizon. The EPP at demand side is considered along with traditional supply resources to meet the planning. In addition to common aspects of scheduling, this model takes a peaking capacity constrain into account to meet the big peak-valley difference in the city. Then, an improved dual population invasive weed algorithm (IWO) is proposed for solving the model. Case study results show that the proposed model and the improved algorithm are effective, and the IRP model can realize the system total cost minimization, emission reduction and power peak shifting effectively.