The threat of North Korea's long-range firepower is recognized as a typical asymmetric threat, and South Korea is prioritizing the development of a Korean-style missile defense system to defend against it. To address this, previous research modeled North Korean long-range artillery attacks as a Markov Decision Process (MDP) and used Approximate Dynamic Programming as an algorithm for missile defense, but due to its limitations, there is an intention to apply deep reinforcement learning techniques that incorporate deep learning. In this paper, we aim to develop a missile defense system algorithm by applying a modified DQN with multi-agent-based deep reinforcement learning techniques. Through this, we have researched to ensure an efficient missile defense system can be implemented considering the style of attacks in recent wars, such as how effectively it can respond to enemy missile attacks, and have proven that the results learned through deep reinforcement learning show superior outcomes.

첨단 과학기술의 발전은 미중 패권경쟁의 양상을 변화시키고 있다. 특히, 탄도미사일, 순항미사일, 초음속 순항미사일 등과 같은 첨단 미사일을 중심으로 진행된 중국 해군의 군사 무기체계 변화는 공세적 군사전략에 유리한 환경을 조성하고 있다. 중화민족의 위 대한 부흥을 선포한 시진핑 주석은 ‘해양강국 건설’을 선언하며 방어 중심의 군사전략에 서 탈피하여, 힘의 투사력과 국익의 범위를 확장시켜 나가고 있다. 이에 대응하여 바이든 정부 역시 쿼드(Quad)를 축으로 아시아‧태평양 지역에서의 군사동맹을 강화하고 있으며, 강력한 對중국 봉쇄 및 견제정책을 전개하고 있다. 본 연구는 ‘공격-방어 균형 이론’을 통해 공격이 우월 전략인 안보환경에서는 안보의 딜레마가 심화되며, 이로 인한 우발적 무력충돌과 오판은 참혹한 전쟁으로 귀결될 수 있음을 경고한다. 또한, 비대칭적 군사전 력을 중심으로 전개되고 있는 미중 간의 新패권경쟁이 과거의 전면전과는 어떤 다른 양 상으로 전개될지에 대해 논하고 있다.

With the development of modern science and technology, weapon systems such as tanks, submarines, combat planes, radar are also dramatically advanced. Among these weapon systems, the ballistic missile, one of the asymmetric forces, could be considered as a very economical means to attack the core facilities of the other country in order to achieve the strategic goals of the country during the war. Because of the current ballistic missile threat from the North Korea, establishing a missile defense (MD) system becomes one of the major national defense issues. This study focused on the optimization of air defense artillery units’ deployment for effective ballistic missile defense. To optimize the deployment of the units, firstly this study examined the possibility of defense, according to the presence of orbital coordinates of ballistic missiles in the limited defense range of air defense artillery units. This constraint on the defense range is originated from the characteristics of anti-ballistic missiles (ABMs) such as PATRIOT. Secondly, this study proposed the optimized mathematical model considering the total covering problem of binary integer programming, as an optimal deployment of air defense artillery units for defending every core defense facility with the least number of such units. Finally, numerical experiments were conducted to show how the suggested approach works. Assuming the current state of the Korean peninsula, the study arbitrarily set ballistic missile bases of the North Korea and core defense facilities of the South Korea. Under these conditions, numerical experiments were executed by utilizing MATLAB R2010a of the MathWorks, Inc.

When offense launches missiles at valuable assets of the defense, the defense must assign its weapons to these missiles so as to maximize the total value of surviving assets threatened by them. Recently, a new asset-based linear approximation model was proposed for weapon target assignment problem with shootlook- shoot engagement policy and fixed set-up time between each anti-missile launch from each defense unit. In this paper, we apply the proposed to several ballistic missile defense examples and we show their weapon target assignment results specified with launch order time.