Algorithm 1 Distance-based Sampling with Fixed Threshold Algorithm (DSFT)
Input: D = {Di|1 ≤ i ≤ N, i ∈ Z}, T, C and ε.
Output: D̃ = {D̃i|1 ≤ i ≤ N, i ∈ Z}
1:	Set ε1 = kε, ε2 = ε − ε1, k is computed due to theorem 5.4;
2:	Set $\stackrel{\sim }{T}=T+\mathit{\text{Lap}}\left(\frac{2\mathrm{\Delta }}{{\epsilon }_1}\right)$, Δ is computed due to lemma 4.1;
3:	For D1, release a DP dataset D̃1 with $\frac{{\epsilon }_2}{C}$ privacy budget;
4:	Set count = 1, and j = 1;
5:	for each time point ti with i ≥ 2 do
6:	if count ≥ C, then set D̃i = D̃j continue;
7:	Set $\stackrel{\sim }{d}(D_i,{\stackrel{\sim }{D}}_j)=d(D_i,{\stackrel{\sim }{D}}_j)+\mathit{\text{Lap}}\left(\frac{2C\mathrm{\Delta }}{{\epsilon }_1}\right)$
8:	if d̃(Di, D̃j) ≥ T̃, then release D̃i at ti with $\frac{{\epsilon }_2}{C}$ budget, and set count = count + 1, and j = i;
9:	else use D̃j as the release of Di;
10:	if i == N and count < C, then release D̃N with all remaining privacy budget;
11:	end for