Improving the performance of the electric distribution network is essential to meet the needs of the customer and guarantee the service continuity. Installing generators with small sizes known as distributed generators (DGs) can contribute to enhance the network operation by mitigating the network loss and improving the voltage profile. Integrating these generators in inappropriate places can cause serious consequences to the network operation. Therefore, this paper proposes a novel metaheuristic approach of artificial hummingbird algorithm (AHA) to identify the best locations and sizes of biomass-based DGs in radial distribution network. The proposed approach has enriched exploration and exploitation phases that enhancing its search capability and avoiding stuck in local optima. The network active power loss and the voltage deviation are selected as the targets to be minimized. Moreover, a new version of AHA is programmed to solve multi-objective problem with the purpose of mitigating both targets. The analysis is conducted on three radial distribution networks of IEEE 33-bus, IEEE 69-bus, and IEEE 119-bus. Three scenarios are implemented in each network, the first one is minimizing the active power loss, the second one is mitigating the voltage deviation, and the last one is multi-objective problem. Also, biomass-based DGs with unity, fixed, and optimal power factors are analyzed. Excessive comparison to fractal search algorithm, particle swarm optimizer, genetic algorithm, the whale optimization algorithm, sperm swarm optimization, tunicate swarm algorithm, pathfinder algorithm, seagull optimization algorithm, and sine cosine algorithm, multi-objective water cycle algorithm, multi-objective grey wolf optimizer, and multi-objective sparrow search algorithm is conducted. Moreover, statistical tests of Wilcoxon, Friedman, ANOVA, and Kruskal Wallis are performed to assess the performance of the proposed approach. The gotten results confirmed the preference and competence of the proposed approach in integrating the biomass-based DGs in radial distribution networks.