Commercial buildings often rely on stationary batteries to address emergency power needs and control energy expenses. However, the capital and maintenance costs associated with stationary batteries are prohibitively high. Concurrently, Electric Vehicles (EVs) spend roughly 95% of their operational lifespan in an inactive state, representing a substantial resource under utilization. The increasing prevalence of EVs on the road necessitates a significant expansion of energy resources to accommodate EV charging demands. Vehicle-to-Building (V2B) technology emerges as a solution, harnessing the energy storage capacity of EVs to manage both heavy and light building loads. This not only ensures occupant comfort and safety but also reduces EV charging costs and optimizes energy consumption. This thesis endeavors to establish a proof of concept for V2B integration, specifically by combining EVs with smart buildings through the application of Temporal Planning, a subdomain of Artificial Intelligence (AI) Planning. The Planning Domain Definition Language (PDDL) is employed to model the domain and problem, utilizing temporal planning versions PDDL 2.1 and PDDL 2.2, which accommodate numeric fluent constraints capable of dynamic changes over time. Timed Initial Fluent (TIF) and Timed Initial Literal (TIL) constructs are employed to modify numeric fluent and predicate values as needed. By incorporating durative actions, representing actions occurring over time, the plan effectively integrates EVs with smart buildings. The resulting plan includes a set of actions to schedule EV charging and discharging, aligning with the building’s energy demand and ensuring occupants needs and comfort over a 24-hour period. The V2B model encompasses various factors, including energy market dynamics and EV-specific information such as EV entering and leaving times, State of Charge (SOC), daily driving distance, minimum charging thresholds, and EV priority levels. It also integrates environmental data relevant to the building, encompassing occupancy patterns, external natural light conditions, current temperature, and operating hours. These elements are harmoniously integrated into a domain model and an associated problem file. The proposed model leverages the capabilities of the Partial Order Planning Forwards – TIF (POPF-TIF) planner, adept at resolving TIFs and TILs, to generate a comprehensive plan for seamlessly integrating EVs with smart buildings and managing building loads efficiently. In the evaluation, the performance of the POPF planner in handling temporal constraints, such as TIFs and TILs, is assessed to ensure the efficient integration of EVs with smart buildings. The impact of various parameters and values on planner performance is analyzed, providing insights into the optimization of energy utilization, cost reduction, and overall sustainability in commercial buildings.